{ "best_metric": 3.895061492919922, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj2/transformer/1/checkpoints/checkpoint-839520", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 2442240, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 11.0032, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8354, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1938, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9758, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8037, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.697, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.5986, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5281, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4457, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.3904, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3359, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.2962, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2572, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.202, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1711, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1166, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1003, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0651, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0277, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0066, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0048, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9582, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815558291179756e-05, "loss": 4.9452, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807172343669236e-05, "loss": 4.9205, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798786396158716e-05, "loss": 4.8958, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.8853, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8514, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8489, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8297, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8011, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.7972, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7753, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7745, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 4.7553, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.9714943299857244e-05, "loss": 4.7388, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7338, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.7348, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.6987, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.6905, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6858, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.666, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6603, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6616, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6505, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.636, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6272, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6182, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6196, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5866, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5885, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5946, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957246408619706e-05, "loss": 4.5854, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956407813868654e-05, "loss": 4.572, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5541, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5619, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5414, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5591, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.527, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 4.5422, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5223, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5109, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5144, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 4.5001, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4955, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4865, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.4961, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4721, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4678, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4566, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4574, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4751, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4639, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4461, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4442, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4485, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4432, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4278, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4309, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4217, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.421, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4152, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4121, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4151, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 4.4073, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.3863, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 4.3959, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 4.3963, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 4.3903, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3852, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925391273242342e-05, "loss": 4.3734, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.92455267849129e-05, "loss": 4.3792, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923714083740238e-05, "loss": 4.3681, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3743, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3627, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3571, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.376, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3426, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3397, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3497, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3485, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3516, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3365, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3312, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3282, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3338, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3145, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3133, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3262, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3158, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3076, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.9077906107524886e-05, "loss": 4.3027, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.9069520160014366e-05, "loss": 4.3012, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.9061134212503846e-05, "loss": 4.3112, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.298, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.2954, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.2997, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.2999, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.2885, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2926, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.2905, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.2875, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.2709, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.2835, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2775, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2819, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2656, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2745, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2629, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2666, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2477, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2743, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2717, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889348077750837e-05, "loss": 4.2545, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888509482999785e-05, "loss": 4.2453, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887670888248733e-05, "loss": 4.2659, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2508, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2532, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515674187595e-05, "loss": 4.2464, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2543, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2449, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2448, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2291, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809654060010626e-05, "loss": 4.2423, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801268112500106e-05, "loss": 4.2384, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2298, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2476, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877612664877228e-05, "loss": 4.2253, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876774070126176e-05, "loss": 4.2313, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875935475375124e-05, "loss": 4.2347, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875096880624072e-05, "loss": 4.2239, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.237559795379639, "eval_runtime": 304.2346, "eval_samples_per_second": 1254.265, "eval_steps_per_second": 39.197, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.87425828587302e-05, "loss": 4.2103, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873421329002341e-05, "loss": 4.216, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872582734251289e-05, "loss": 4.2254, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871744139500237e-05, "loss": 4.2138, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.2163, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2005, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869229993127454e-05, "loss": 4.2023, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683913983764027e-05, "loss": 4.1989, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2093, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.1941, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658772520036196e-05, "loss": 4.2013, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650402951329405e-05, "loss": 4.206, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642017003818885e-05, "loss": 4.1892, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633631056308365e-05, "loss": 4.1848, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625245108797845e-05, "loss": 4.1756, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616859161287324e-05, "loss": 4.1822, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608473213776804e-05, "loss": 4.1785, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860008726626628e-05, "loss": 4.1746, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591701318755764e-05, "loss": 4.1742, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583315371245244e-05, "loss": 4.201, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1712, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856655985502793e-05, "loss": 4.173, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.855817390751741e-05, "loss": 4.1797, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854978796000689e-05, "loss": 4.1716, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1667, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853303244378958e-05, "loss": 4.1602, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852464649627906e-05, "loss": 4.1648, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851626054876854e-05, "loss": 4.1597, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850787460125802e-05, "loss": 4.1485, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849950503255123e-05, "loss": 4.1619, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849111908504072e-05, "loss": 4.1493, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.84827331375302e-05, "loss": 4.162, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847434719001968e-05, "loss": 4.1572, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846597762131289e-05, "loss": 4.1419, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845759167380237e-05, "loss": 4.157, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844920572629185e-05, "loss": 4.1636, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844081977878133e-05, "loss": 4.1367, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.8432450210074536e-05, "loss": 4.1468, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.8424064262564016e-05, "loss": 4.1407, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.8415678315053496e-05, "loss": 4.1327, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.8407292367542976e-05, "loss": 4.1372, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398922798836185e-05, "loss": 4.1461, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839053685132567e-05, "loss": 4.1433, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838215090381515e-05, "loss": 4.134, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837376495630463e-05, "loss": 4.1414, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836539538759784e-05, "loss": 4.1304, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835700944008732e-05, "loss": 4.1374, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.83486234925768e-05, "loss": 4.1175, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834023754506628e-05, "loss": 4.1189, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833186797635949e-05, "loss": 4.1338, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.83234984076527e-05, "loss": 4.1347, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831511246014218e-05, "loss": 4.122, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830672651263166e-05, "loss": 4.1137, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829834056512114e-05, "loss": 4.125, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289954617610625e-05, "loss": 4.1067, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281568670100105e-05, "loss": 4.1323, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273182722589585e-05, "loss": 4.1138, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264796775079065e-05, "loss": 4.1286, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256427206372274e-05, "loss": 4.1149, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248041258861754e-05, "loss": 4.1054, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.8239655311351234e-05, "loss": 4.1097, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823128574264444e-05, "loss": 4.1119, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822289979513392e-05, "loss": 4.0998, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.82145138476234e-05, "loss": 4.0985, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820612790011288e-05, "loss": 4.1141, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819775833140609e-05, "loss": 4.0992, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818937238389558e-05, "loss": 4.0901, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818098643638506e-05, "loss": 4.0903, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817260048887454e-05, "loss": 4.0904, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816423092016775e-05, "loss": 4.1104, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815584497265723e-05, "loss": 4.1066, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814745902514671e-05, "loss": 4.0912, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813907307763619e-05, "loss": 4.0936, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81307035089294e-05, "loss": 4.0973, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812231756141888e-05, "loss": 4.0952, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811393161390836e-05, "loss": 4.0889, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810554566639784e-05, "loss": 4.0936, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.8097176097691046e-05, "loss": 4.0882, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808879015018053e-05, "loss": 4.0931, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808040420267001e-05, "loss": 4.083, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807201825515949e-05, "loss": 4.088, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.80636486864527e-05, "loss": 4.0891, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805526273894218e-05, "loss": 4.0885, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804687679143166e-05, "loss": 4.0718, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803849084392114e-05, "loss": 4.0818, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803012127521435e-05, "loss": 4.0802, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802173532770383e-05, "loss": 4.0831, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801336575899704e-05, "loss": 4.0799, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800497981148652e-05, "loss": 4.0655, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996593863976e-05, "loss": 4.0784, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988207916465486e-05, "loss": 4.069, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979821968954966e-05, "loss": 4.0789, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971436021444446e-05, "loss": 4.0646, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963050073933926e-05, "loss": 4.0699, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.7954680505227135e-05, "loss": 4.0802, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.7946294557716615e-05, "loss": 4.0673, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.7937908610206095e-05, "loss": 4.0503, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.7929539041499304e-05, "loss": 4.0654, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.7921153093988784e-05, "loss": 4.0689, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.7912767146478264e-05, "loss": 4.0704, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.7904381198967744e-05, "loss": 4.0627, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.7895995251457224e-05, "loss": 4.0591, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887609303946704e-05, "loss": 4.0524, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.7879223356436184e-05, "loss": 4.066, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870837408925664e-05, "loss": 4.0453, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786248421902261e-05, "loss": 4.0499, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785409827151209e-05, "loss": 4.0592, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784571232400157e-05, "loss": 4.0601, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783732637649105e-05, "loss": 4.0372, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782895680778426e-05, "loss": 4.051, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782057086027374e-05, "loss": 4.0407, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781218491276322e-05, "loss": 4.0572, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.78037989652527e-05, "loss": 4.0438, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779541301774218e-05, "loss": 4.0396, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778702707023166e-05, "loss": 4.0582, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777864112272114e-05, "loss": 4.0515, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770271554014354e-05, "loss": 4.0433, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761885606503834e-05, "loss": 4.0488, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775349965899331e-05, "loss": 4.0443, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774511371148279e-05, "loss": 4.0491, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.7736744142776e-05, "loss": 4.0281, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772835819526548e-05, "loss": 4.0489, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719972247754956e-05, "loss": 4.0364, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.7711586300244436e-05, "loss": 4.0442, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703200352733916e-05, "loss": 4.0356, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694814405223396e-05, "loss": 4.0406, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686428457712876e-05, "loss": 4.0337, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.7678042510202355e-05, "loss": 4.0351, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766967294149557e-05, "loss": 4.0172, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766128699398505e-05, "loss": 4.0489, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765290104647453e-05, "loss": 4.0399, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764453147776774e-05, "loss": 4.0336, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763614553025722e-05, "loss": 4.0236, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.76277595827467e-05, "loss": 4.0418, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761937363523618e-05, "loss": 4.0365, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761098768772566e-05, "loss": 4.029, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760260174021514e-05, "loss": 4.0259, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759423217150835e-05, "loss": 4.036, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758584622399783e-05, "loss": 4.0296, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757746027648731e-05, "loss": 4.039, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569074328976796e-05, "loss": 4.015, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560704760270005e-05, "loss": 4.0307, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552318812759485e-05, "loss": 4.0278, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543932865248965e-05, "loss": 4.021, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535546917738445e-05, "loss": 4.0403, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527177349031654e-05, "loss": 4.0192, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518791401521134e-05, "loss": 4.0241, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510405454010614e-05, "loss": 4.0243, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7502019506500094e-05, "loss": 4.0224, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.068605422973633, "eval_runtime": 305.2926, "eval_samples_per_second": 1249.919, "eval_steps_per_second": 39.061, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493633558989574e-05, "loss": 4.0074, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.7485247611479054e-05, "loss": 4.0163, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.7476861663968534e-05, "loss": 4.0245, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468475716458014e-05, "loss": 4.0164, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460089768947494e-05, "loss": 4.0231, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451703821436974e-05, "loss": 4.0026, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443317873926453e-05, "loss": 4.0095, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.743494830521967e-05, "loss": 4.0054, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742656235770914e-05, "loss": 4.0167, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741817641019862e-05, "loss": 4.0047, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.74097904626881e-05, "loss": 4.0129, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740140451517758e-05, "loss": 4.0161, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739303494647079e-05, "loss": 3.9994, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738464899896027e-05, "loss": 4.0034, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737626305144975e-05, "loss": 3.9861, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736789348274297e-05, "loss": 3.9984, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735950753523245e-05, "loss": 3.9985, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735112158772193e-05, "loss": 3.9927, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734273564021141e-05, "loss": 3.9936, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733434969270089e-05, "loss": 4.0183, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732596374519037e-05, "loss": 3.9955, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.7317594176483576e-05, "loss": 3.9925, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309208228973056e-05, "loss": 4.0012, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.7300822281462536e-05, "loss": 3.9992, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292436333952016e-05, "loss": 3.9889, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7284066765245225e-05, "loss": 3.9852, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275680817734705e-05, "loss": 3.9942, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267294870224185e-05, "loss": 3.9825, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258908922713665e-05, "loss": 3.9804, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725053935400688e-05, "loss": 3.9926, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724215340649636e-05, "loss": 3.9818, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723376745898584e-05, "loss": 3.9921, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722538151147532e-05, "loss": 3.9875, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721701194276853e-05, "loss": 3.9756, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720862599525801e-05, "loss": 3.9894, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720024004774749e-05, "loss": 4.0013, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719185410023697e-05, "loss": 3.9715, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718346815272645e-05, "loss": 3.9842, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717509858401966e-05, "loss": 3.9737, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716671263650914e-05, "loss": 3.9757, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715832668899862e-05, "loss": 3.9726, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149940741488105e-05, "loss": 3.9884, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141571172781314e-05, "loss": 3.9832, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133185225270794e-05, "loss": 3.9763, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.7124799277760274e-05, "loss": 3.9822, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116413330249754e-05, "loss": 3.9718, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7108043761542963e-05, "loss": 3.984, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099657814032443e-05, "loss": 3.9642, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709127186652192e-05, "loss": 3.9648, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.70828859190114e-05, "loss": 3.9772, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707451635030461e-05, "loss": 3.9776, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706613040279409e-05, "loss": 3.9688, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705774445528357e-05, "loss": 3.9634, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704935850777306e-05, "loss": 3.9728, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704098893906627e-05, "loss": 3.9542, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703260299155575e-05, "loss": 3.9796, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702421704404523e-05, "loss": 3.9671, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701583109653471e-05, "loss": 3.9784, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700746152782792e-05, "loss": 3.9716, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.69990755803174e-05, "loss": 3.9573, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699068963280688e-05, "loss": 3.9619, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698230368529636e-05, "loss": 3.9666, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697391773778584e-05, "loss": 3.9537, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965548169079046e-05, "loss": 3.9544, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.6957162221568526e-05, "loss": 3.9666, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694877627405801e-05, "loss": 3.9583, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694039032654749e-05, "loss": 3.9452, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.69320207578407e-05, "loss": 3.9479, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692363481033018e-05, "loss": 3.9486, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691524886281966e-05, "loss": 3.9685, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690686291530914e-05, "loss": 3.9632, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689849334660235e-05, "loss": 3.9523, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689010739909183e-05, "loss": 3.9583, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688172145158131e-05, "loss": 3.9555, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687333550407079e-05, "loss": 3.9594, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864965935364e-05, "loss": 3.9485, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685657998785348e-05, "loss": 3.9598, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848194040342966e-05, "loss": 3.9543, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839808092832446e-05, "loss": 3.9561, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831438524125655e-05, "loss": 3.9465, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6823052576615135e-05, "loss": 3.9542, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814666629104615e-05, "loss": 3.9546, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806280681594095e-05, "loss": 3.9531, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797911112887304e-05, "loss": 3.9413, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789525165376784e-05, "loss": 3.9469, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781139217866264e-05, "loss": 3.948, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772753270355744e-05, "loss": 3.9491, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676438370164895e-05, "loss": 3.9514, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675599775413843e-05, "loss": 3.9336, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674761180662792e-05, "loss": 3.9466, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.67392258591174e-05, "loss": 3.9423, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673085629041061e-05, "loss": 3.95, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672247034290009e-05, "loss": 3.9323, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671408439538957e-05, "loss": 3.9421, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670569844787904e-05, "loss": 3.9535, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669732887917226e-05, "loss": 3.9391, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668894293166174e-05, "loss": 3.9237, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668055698415122e-05, "loss": 3.9388, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667217103664069e-05, "loss": 3.9433, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666380146793391e-05, "loss": 3.9443, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665541552042339e-05, "loss": 3.941, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6647029572912874e-05, "loss": 3.9305, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663864362540235e-05, "loss": 3.9297, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663025767789183e-05, "loss": 3.9413, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662188810918504e-05, "loss": 3.9234, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613502161674516e-05, "loss": 3.9288, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6605116214163996e-05, "loss": 3.9364, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596730266653476e-05, "loss": 3.938, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658836069794669e-05, "loss": 3.9127, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579974750436165e-05, "loss": 3.9301, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571588802925645e-05, "loss": 3.9208, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6563202855415125e-05, "loss": 3.9341, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655483328670834e-05, "loss": 3.9291, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654644733919782e-05, "loss": 3.9209, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.65380613916873e-05, "loss": 3.9381, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652967544417678e-05, "loss": 3.9349, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652130587546999e-05, "loss": 3.9232, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651291992795947e-05, "loss": 3.9304, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650453398044895e-05, "loss": 3.9295, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649614803293843e-05, "loss": 3.9271, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648777846423164e-05, "loss": 3.9145, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647939251672112e-05, "loss": 3.9287, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.64710065692106e-05, "loss": 3.9226, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646262062170008e-05, "loss": 3.9257, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454251052993294e-05, "loss": 3.9243, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445865105482774e-05, "loss": 3.9288, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437479157972254e-05, "loss": 3.9142, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429093210461734e-05, "loss": 3.919, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642072364175494e-05, "loss": 3.9066, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641233769424442e-05, "loss": 3.9355, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.64039517467339e-05, "loss": 3.9231, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639556579922338e-05, "loss": 3.9227, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638719623051659e-05, "loss": 3.9126, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637881028300607e-05, "loss": 3.929, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637042433549555e-05, "loss": 3.926, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636203838798503e-05, "loss": 3.9155, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635366881927825e-05, "loss": 3.9154, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634528287176773e-05, "loss": 3.9233, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633689692425721e-05, "loss": 3.9195, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632851097674669e-05, "loss": 3.9266, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.63201414080399e-05, "loss": 3.9084, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631175546052938e-05, "loss": 3.9195, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630336951301886e-05, "loss": 3.9163, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629498356550834e-05, "loss": 3.9104, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286613996801546e-05, "loss": 3.9307, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278228049291026e-05, "loss": 3.9114, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.6269842101780506e-05, "loss": 3.9154, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.6261456154269986e-05, "loss": 3.9171, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.62530865855632e-05, "loss": 3.9119, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9972167015075684, "eval_runtime": 302.4616, "eval_samples_per_second": 1261.618, "eval_steps_per_second": 39.426, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624470063805268e-05, "loss": 3.9094, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623631469054216e-05, "loss": 3.9073, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622792874303164e-05, "loss": 3.9171, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621955917432485e-05, "loss": 3.9116, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621117322681433e-05, "loss": 3.9173, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620278727930381e-05, "loss": 3.9006, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619440133179329e-05, "loss": 3.9078, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.61860317630865e-05, "loss": 3.8956, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617764581557598e-05, "loss": 3.9176, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616925986806546e-05, "loss": 3.8987, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160890299358675e-05, "loss": 3.9098, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.6152504351848155e-05, "loss": 3.9113, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6144134783141364e-05, "loss": 3.9017, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135748835630844e-05, "loss": 3.8943, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127362888120324e-05, "loss": 3.8921, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118976940609804e-05, "loss": 3.8924, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110590993099284e-05, "loss": 3.8994, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.6102205045588764e-05, "loss": 3.8941, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093819098078244e-05, "loss": 3.8942, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085433150567724e-05, "loss": 3.9147, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607706358186093e-05, "loss": 3.8976, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606867763435041e-05, "loss": 3.893, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606029168683989e-05, "loss": 3.9009, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.605190573932937e-05, "loss": 3.9001, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604353617062259e-05, "loss": 3.8916, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603515022311207e-05, "loss": 3.8864, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602676427560155e-05, "loss": 3.9007, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601837832809103e-05, "loss": 3.8799, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.601000875938424e-05, "loss": 3.8857, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600162281187372e-05, "loss": 3.8913, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.59932368643632e-05, "loss": 3.8852, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598485091685268e-05, "loss": 3.8984, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597648134814589e-05, "loss": 3.8898, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596809540063537e-05, "loss": 3.8822, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595970945312485e-05, "loss": 3.8947, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595133988441806e-05, "loss": 3.9022, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594295393690754e-05, "loss": 3.8807, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593456798939702e-05, "loss": 3.89, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.59261820418865e-05, "loss": 3.875, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591781247317971e-05, "loss": 3.8893, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590942652566919e-05, "loss": 3.8749, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590104057815867e-05, "loss": 3.8977, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589265463064815e-05, "loss": 3.8884, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588428506194136e-05, "loss": 3.8847, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587589911443084e-05, "loss": 3.8883, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586751316692032e-05, "loss": 3.8815, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.58591272194098e-05, "loss": 3.8892, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850757650703016e-05, "loss": 3.873, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.5842371703192496e-05, "loss": 3.8709, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.5833985755681976e-05, "loss": 3.8881, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.5825616186975185e-05, "loss": 3.8842, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.5817230239464665e-05, "loss": 3.8822, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808844291954145e-05, "loss": 3.8711, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.5800458344443625e-05, "loss": 3.8799, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.5792072396933105e-05, "loss": 3.8643, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.5783686449422585e-05, "loss": 3.8885, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.5775300501912065e-05, "loss": 3.8769, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576691455440154e-05, "loss": 3.8921, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758544985694754e-05, "loss": 3.8825, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5750159038184234e-05, "loss": 3.8707, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741773090673714e-05, "loss": 3.8689, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733387143163194e-05, "loss": 3.8783, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572501757445641e-05, "loss": 3.8677, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.571663162694589e-05, "loss": 3.8667, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570824567943537e-05, "loss": 3.8762, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569985973192484e-05, "loss": 3.8755, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569149016321806e-05, "loss": 3.8564, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568310421570754e-05, "loss": 3.8609, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567471826819701e-05, "loss": 3.8594, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566633232068649e-05, "loss": 3.8837, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565796275197971e-05, "loss": 3.8749, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564957680446919e-05, "loss": 3.8648, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564119085695867e-05, "loss": 3.8726, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632821288251884e-05, "loss": 3.8676, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624435340741364e-05, "loss": 3.8783, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.5616049393230843e-05, "loss": 3.8588, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560766344572032e-05, "loss": 3.8794, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.559929387701353e-05, "loss": 3.8662, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559090792950301e-05, "loss": 3.8707, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.5582521981992486e-05, "loss": 3.868, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.5574136034481966e-05, "loss": 3.866, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556576646577518e-05, "loss": 3.8749, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555738051826466e-05, "loss": 3.8662, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554899457075414e-05, "loss": 3.8574, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554060862324362e-05, "loss": 3.8657, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553223905453684e-05, "loss": 3.8609, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552385310702631e-05, "loss": 3.8722, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551546715951579e-05, "loss": 3.8672, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550708121200527e-05, "loss": 3.8507, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498711643298486e-05, "loss": 3.8659, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549032569578796e-05, "loss": 3.855, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548193974827744e-05, "loss": 3.8664, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547355380076692e-05, "loss": 3.8543, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.5465184232060135e-05, "loss": 3.8626, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.5456798284549615e-05, "loss": 3.871, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.5448412337039095e-05, "loss": 3.8563, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.5440026389528575e-05, "loss": 3.8464, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431656820821784e-05, "loss": 3.8592, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.5423270873311264e-05, "loss": 3.8559, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414884925800744e-05, "loss": 3.8693, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406498978290224e-05, "loss": 3.8597, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539812940958343e-05, "loss": 3.8511, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538974346207291e-05, "loss": 3.8515, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538135751456239e-05, "loss": 3.8628, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537297156705187e-05, "loss": 3.8415, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536460199834508e-05, "loss": 3.8529, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535621605083457e-05, "loss": 3.8531, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534783010332405e-05, "loss": 3.8598, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533944415581353e-05, "loss": 3.8305, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533107458710674e-05, "loss": 3.8524, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532268863959622e-05, "loss": 3.8502, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.53143026920857e-05, "loss": 3.8487, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530591674457518e-05, "loss": 3.8543, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529754717586839e-05, "loss": 3.8405, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528916122835787e-05, "loss": 3.8619, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528077528084735e-05, "loss": 3.8552, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527238933333683e-05, "loss": 3.8464, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.5264019764630036e-05, "loss": 3.8533, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525563381711952e-05, "loss": 3.8526, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5247247869609e-05, "loss": 3.8515, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523886192209848e-05, "loss": 3.833, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523049235339169e-05, "loss": 3.8556, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522210640588117e-05, "loss": 3.8438, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521372045837065e-05, "loss": 3.8479, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520533451086013e-05, "loss": 3.8474, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519696494215334e-05, "loss": 3.8534, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518857899464282e-05, "loss": 3.8433, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.51801930471323e-05, "loss": 3.8389, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517180709962178e-05, "loss": 3.8356, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516343753091499e-05, "loss": 3.8564, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.5155051583404476e-05, "loss": 3.8476, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.5146665635893956e-05, "loss": 3.8486, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.5138279688383436e-05, "loss": 3.8377, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.5129910119676645e-05, "loss": 3.8541, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.5121524172166125e-05, "loss": 3.85, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.5113138224655605e-05, "loss": 3.8419, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104752277145085e-05, "loss": 3.8414, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5096382708438294e-05, "loss": 3.848, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087996760927774e-05, "loss": 3.8485, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079610813417254e-05, "loss": 3.8525, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5071224865906734e-05, "loss": 3.8354, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506287167600368e-05, "loss": 3.847, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505448572849316e-05, "loss": 3.8422, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504609978098264e-05, "loss": 3.8411, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503771383347212e-05, "loss": 3.8554, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.50293278859616e-05, "loss": 3.8402, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502094193845108e-05, "loss": 3.8447, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501255599094056e-05, "loss": 3.8381, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500417004343004e-05, "loss": 3.844, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.955796003341675, "eval_runtime": 301.8628, "eval_samples_per_second": 1264.121, "eval_steps_per_second": 39.505, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.499580047472325e-05, "loss": 3.8275, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498741452721273e-05, "loss": 3.8387, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497902857970221e-05, "loss": 3.8439, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497064263219169e-05, "loss": 3.8407, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496225668468117e-05, "loss": 3.8494, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.495387073717065e-05, "loss": 3.8277, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.4945501168463863e-05, "loss": 3.8378, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493711522095334e-05, "loss": 3.8264, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.492872927344282e-05, "loss": 3.8434, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.49203433259323e-05, "loss": 3.8352, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.491195737842178e-05, "loss": 3.8365, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490357143091126e-05, "loss": 3.8365, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.489520186220447e-05, "loss": 3.8321, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.488681591469395e-05, "loss": 3.8241, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.487842996718343e-05, "loss": 3.828, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.487004401967291e-05, "loss": 3.8171, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861658072162385e-05, "loss": 3.8307, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.4853272124651865e-05, "loss": 3.8239, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.484488617714135e-05, "loss": 3.823, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.483651660843456e-05, "loss": 3.8511, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.482813066092404e-05, "loss": 3.8241, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481976109221726e-05, "loss": 3.8278, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481137514470674e-05, "loss": 3.8317, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480298919719622e-05, "loss": 3.8286, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479460324968569e-05, "loss": 3.8251, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478621730217517e-05, "loss": 3.821, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477783135466465e-05, "loss": 3.8324, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476944540715413e-05, "loss": 3.8072, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476107583844734e-05, "loss": 3.8196, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475268989093682e-05, "loss": 3.8191, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.47443039434263e-05, "loss": 3.8201, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.4735917995915786e-05, "loss": 3.83, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.4727532048405266e-05, "loss": 3.8257, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.4719146100894746e-05, "loss": 3.8186, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.4710760153384226e-05, "loss": 3.8274, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.4702374205873705e-05, "loss": 3.8302, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.4694004637166915e-05, "loss": 3.8157, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.4685618689656395e-05, "loss": 3.8243, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.4677232742145874e-05, "loss": 3.8098, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.4668846794635354e-05, "loss": 3.8236, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.4660477225928564e-05, "loss": 3.8059, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.4652091278418043e-05, "loss": 3.8345, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.4643705330907523e-05, "loss": 3.8233, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.4635319383397003e-05, "loss": 3.8181, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462694981469022e-05, "loss": 3.8235, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461858024598343e-05, "loss": 3.8171, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.461019429847291e-05, "loss": 3.8239, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460180835096239e-05, "loss": 3.8094, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459342240345187e-05, "loss": 3.8058, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458503645594135e-05, "loss": 3.825, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457666688723456e-05, "loss": 3.8184, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456828093972404e-05, "loss": 3.818, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455989499221352e-05, "loss": 3.8093, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.4551509044703e-05, "loss": 3.8151, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.454312309719248e-05, "loss": 3.8062, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.453473714968196e-05, "loss": 3.82, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.452635120217144e-05, "loss": 3.8132, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517965254660924e-05, "loss": 3.8299, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.450959568595413e-05, "loss": 3.818, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450120973844361e-05, "loss": 3.8066, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.449282379093309e-05, "loss": 3.8098, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.448443784342257e-05, "loss": 3.8141, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.447606827471578e-05, "loss": 3.804, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446768232720526e-05, "loss": 3.8067, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445931275849847e-05, "loss": 3.8111, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445092681098795e-05, "loss": 3.8135, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.444254086347743e-05, "loss": 3.7938, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.443415491596691e-05, "loss": 3.8015, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.442576896845639e-05, "loss": 3.7982, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.441738302094588e-05, "loss": 3.8153, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.440899707343535e-05, "loss": 3.8123, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.4400627504728566e-05, "loss": 3.8057, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.4392241557218046e-05, "loss": 3.8103, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.4383855609707526e-05, "loss": 3.8065, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.4375469662197e-05, "loss": 3.8214, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436708371468648e-05, "loss": 3.7972, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435869776717596e-05, "loss": 3.8138, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435031181966544e-05, "loss": 3.8081, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434194225095865e-05, "loss": 3.8074, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433355630344813e-05, "loss": 3.8089, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.4325170355937615e-05, "loss": 3.8063, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.4316784408427095e-05, "loss": 3.8107, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.4308398460916575e-05, "loss": 3.8073, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.4300012513406055e-05, "loss": 3.7915, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291626565895535e-05, "loss": 3.8067, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4283240618385015e-05, "loss": 3.8025, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.4274871049678224e-05, "loss": 3.8097, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.426650148097143e-05, "loss": 3.8052, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.425811553346091e-05, "loss": 3.7911, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.424972958595039e-05, "loss": 3.806, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424134363843987e-05, "loss": 3.7991, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423295769092935e-05, "loss": 3.8091, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422457174341883e-05, "loss": 3.7907, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.421618579590831e-05, "loss": 3.8044, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420779984839779e-05, "loss": 3.818, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419943027969101e-05, "loss": 3.7957, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419104433218049e-05, "loss": 3.7831, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418265838466997e-05, "loss": 3.7986, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417427243715945e-05, "loss": 3.8005, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416590286845266e-05, "loss": 3.8068, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415751692094214e-05, "loss": 3.8021, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.414913097343162e-05, "loss": 3.7924, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414076140472483e-05, "loss": 3.7934, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.413237545721431e-05, "loss": 3.8047, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.412398950970379e-05, "loss": 3.7826, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115619940997e-05, "loss": 3.7944, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.410723399348648e-05, "loss": 3.7963, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.409884804597596e-05, "loss": 3.8019, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.409046209846544e-05, "loss": 3.7748, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.408207615095492e-05, "loss": 3.7953, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.407370658224813e-05, "loss": 3.7895, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.406532063473761e-05, "loss": 3.7952, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.405693468722709e-05, "loss": 3.7936, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.404854873971657e-05, "loss": 3.7865, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.404016279220605e-05, "loss": 3.8008, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.403177684469553e-05, "loss": 3.8012, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.402340727598874e-05, "loss": 3.7882, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401502132847822e-05, "loss": 3.7994, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.40066353809677e-05, "loss": 3.7916, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399824943345719e-05, "loss": 3.7972, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398986348594666e-05, "loss": 3.7796, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.3981493917239876e-05, "loss": 3.798, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.3973107969729356e-05, "loss": 3.7819, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396472202221883e-05, "loss": 3.7936, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.395633607470831e-05, "loss": 3.7856, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394795012719779e-05, "loss": 3.7999, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393956417968727e-05, "loss": 3.7901, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393117823217675e-05, "loss": 3.7843, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392280866346996e-05, "loss": 3.7758, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.391442271595944e-05, "loss": 3.8053, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3906036768448925e-05, "loss": 3.7859, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897650820938405e-05, "loss": 3.7934, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3889281252231614e-05, "loss": 3.7826, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.3880895304721094e-05, "loss": 3.798, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.3872509357210574e-05, "loss": 3.7985, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.3864123409700054e-05, "loss": 3.7837, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.385575384099326e-05, "loss": 3.7858, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.384736789348274e-05, "loss": 3.7943, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383898194597222e-05, "loss": 3.7953, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.38305959984617e-05, "loss": 3.7993, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382221005095118e-05, "loss": 3.7781, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381382410344066e-05, "loss": 3.7912, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380543815593014e-05, "loss": 3.7854, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379706858722336e-05, "loss": 3.7903, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.378868263971284e-05, "loss": 3.797, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.378029669220232e-05, "loss": 3.784, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.37719107446918e-05, "loss": 3.7963, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.376352479718128e-05, "loss": 3.7803, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375513884967076e-05, "loss": 3.7955, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.931006669998169, "eval_runtime": 306.1997, "eval_samples_per_second": 1246.216, "eval_steps_per_second": 38.945, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374675290216024e-05, "loss": 3.777, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373836695464972e-05, "loss": 3.7869, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372999738594293e-05, "loss": 3.7876, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.372161143843241e-05, "loss": 3.7853, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.371322549092189e-05, "loss": 3.793, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.370483954341137e-05, "loss": 3.7778, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.369648635350831e-05, "loss": 3.781, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.368810040599779e-05, "loss": 3.7722, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.367971445848727e-05, "loss": 3.7903, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367132851097675e-05, "loss": 3.7858, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366294256346623e-05, "loss": 3.7793, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365455661595571e-05, "loss": 3.7863, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364618704724892e-05, "loss": 3.7757, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.36378010997384e-05, "loss": 3.7737, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.362941515222788e-05, "loss": 3.7755, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362102920471736e-05, "loss": 3.7635, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361264325720684e-05, "loss": 3.7764, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360427368850005e-05, "loss": 3.7692, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359588774098953e-05, "loss": 3.7712, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.358750179347901e-05, "loss": 3.8039, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357911584596849e-05, "loss": 3.7719, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357072989845797e-05, "loss": 3.7768, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356234395094745e-05, "loss": 3.7773, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355395800343693e-05, "loss": 3.7784, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.354558843473014e-05, "loss": 3.7708, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.353720248721962e-05, "loss": 3.7735, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.35288165397091e-05, "loss": 3.7779, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.352043059219858e-05, "loss": 3.7577, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351204464468806e-05, "loss": 3.768, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350367507598127e-05, "loss": 3.7668, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349528912847075e-05, "loss": 3.7735, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.3486903180960234e-05, "loss": 3.7759, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.3478517233449714e-05, "loss": 3.7754, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.3470131285939194e-05, "loss": 3.7704, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.3461745338428674e-05, "loss": 3.7757, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.3453359390918154e-05, "loss": 3.778, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.344498982221136e-05, "loss": 3.7669, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.343660387470084e-05, "loss": 3.7771, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.342821792719032e-05, "loss": 3.7561, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.34198319796798e-05, "loss": 3.7758, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.341146241097301e-05, "loss": 3.7519, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.340309284226622e-05, "loss": 3.7875, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.33947068947557e-05, "loss": 3.7718, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.338632094724519e-05, "loss": 3.7686, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.337793499973467e-05, "loss": 3.7724, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.336956543102788e-05, "loss": 3.7709, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.336117948351736e-05, "loss": 3.7708, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.335279353600684e-05, "loss": 3.7572, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334440758849632e-05, "loss": 3.7499, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.3336038019789526e-05, "loss": 3.7813, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.3327652072279006e-05, "loss": 3.7669, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.3319266124768486e-05, "loss": 3.7726, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.3310880177257966e-05, "loss": 3.7591, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.3302494229747446e-05, "loss": 3.7658, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.3294124661040655e-05, "loss": 3.7559, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328573871353014e-05, "loss": 3.7714, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327735276601962e-05, "loss": 3.7617, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.32689668185091e-05, "loss": 3.7775, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326058087099858e-05, "loss": 3.7725, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325219492348806e-05, "loss": 3.756, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324380897597754e-05, "loss": 3.7615, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.323543940727075e-05, "loss": 3.7683, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322705345976023e-05, "loss": 3.7563, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321866751224971e-05, "loss": 3.7552, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.321028156473919e-05, "loss": 3.7654, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.32019119960324e-05, "loss": 3.7632, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319352604852188e-05, "loss": 3.7449, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.318514010101136e-05, "loss": 3.7536, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317675415350084e-05, "loss": 3.7493, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.3168368205990326e-05, "loss": 3.7676, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.3159998637283535e-05, "loss": 3.7617, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.3151612689773015e-05, "loss": 3.7582, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.3143226742262495e-05, "loss": 3.7669, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.3134840794751975e-05, "loss": 3.7542, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312645484724145e-05, "loss": 3.7748, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.3118085278534664e-05, "loss": 3.7484, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.3109699331024144e-05, "loss": 3.7666, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.310131338351362e-05, "loss": 3.7596, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.30929274360031e-05, "loss": 3.7604, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308454148849258e-05, "loss": 3.7631, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.3076155540982064e-05, "loss": 3.76, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.3067769593471544e-05, "loss": 3.7615, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.3059383645961024e-05, "loss": 3.7618, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.305101407725423e-05, "loss": 3.7459, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.304262812974371e-05, "loss": 3.7596, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.303424218223319e-05, "loss": 3.7554, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.302585623472267e-05, "loss": 3.7647, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.301750304481962e-05, "loss": 3.7548, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.300911709730909e-05, "loss": 3.747, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.300073114979857e-05, "loss": 3.7567, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.299234520228805e-05, "loss": 3.7543, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298395925477753e-05, "loss": 3.759, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297558968607075e-05, "loss": 3.7461, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.2967203738560227e-05, "loss": 3.7576, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.2958817791049707e-05, "loss": 3.7683, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.2950431843539186e-05, "loss": 3.7529, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.2942062274832396e-05, "loss": 3.7348, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.2933676327321876e-05, "loss": 3.7527, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.2925290379811355e-05, "loss": 3.7544, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.2916904432300835e-05, "loss": 3.7571, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.2908518484790315e-05, "loss": 3.7609, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.2900148916083525e-05, "loss": 3.7486, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.2891762968573004e-05, "loss": 3.7461, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.2883377021062484e-05, "loss": 3.7569, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.287499107355197e-05, "loss": 3.7389, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.286660512604145e-05, "loss": 3.7498, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.285823555733466e-05, "loss": 3.7462, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.284984960982414e-05, "loss": 3.7571, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284146366231362e-05, "loss": 3.7321, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.28330777148031e-05, "loss": 3.7448, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.282469176729258e-05, "loss": 3.7485, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.281630581978206e-05, "loss": 3.7473, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.280791987227154e-05, "loss": 3.7507, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.279953392476102e-05, "loss": 3.7402, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.279116435605423e-05, "loss": 3.7572, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278279478734744e-05, "loss": 3.7556, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277440883983692e-05, "loss": 3.7423, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.2766022892326405e-05, "loss": 3.7567, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.2757636944815885e-05, "loss": 3.7436, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.2749267376109094e-05, "loss": 3.7548, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.2740881428598574e-05, "loss": 3.7397, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.2732495481088054e-05, "loss": 3.7499, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.2724109533577534e-05, "loss": 3.7375, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.2715723586067014e-05, "loss": 3.7477, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.2707337638556494e-05, "loss": 3.7441, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.26989680698497e-05, "loss": 3.7517, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.269058212233918e-05, "loss": 3.7441, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.268219617482866e-05, "loss": 3.7436, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267381022731814e-05, "loss": 3.7288, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266542427980762e-05, "loss": 3.7619, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265705471110084e-05, "loss": 3.7418, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264866876359032e-05, "loss": 3.75, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.26402828160798e-05, "loss": 3.7371, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.263189686856928e-05, "loss": 3.7536, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.262351092105876e-05, "loss": 3.7517, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261512497354823e-05, "loss": 3.7415, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260675540484145e-05, "loss": 3.7459, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259836945733093e-05, "loss": 3.7487, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.25899835098204e-05, "loss": 3.75, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258159756230988e-05, "loss": 3.7614, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.257321161479936e-05, "loss": 3.7306, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.2564842046092576e-05, "loss": 3.7515, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.2556456098582056e-05, "loss": 3.7373, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.2548070151071536e-05, "loss": 3.7509, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539684203561016e-05, "loss": 3.7502, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.2531298256050496e-05, "loss": 3.7391, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.2522912308539976e-05, "loss": 3.7536, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.2514542739833185e-05, "loss": 3.7397, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.2506156792322665e-05, "loss": 3.7466, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.9170572757720947, "eval_runtime": 309.1665, "eval_samples_per_second": 1234.257, "eval_steps_per_second": 38.571, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.2497770844812145e-05, "loss": 3.7334, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.2489384897301625e-05, "loss": 3.739, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.2480998949791105e-05, "loss": 3.7483, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.2472613002280585e-05, "loss": 3.7434, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.2464227054770065e-05, "loss": 3.7482, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.245585748606328e-05, "loss": 3.7397, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.244747153855276e-05, "loss": 3.7307, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.243908559104224e-05, "loss": 3.7358, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.243069964353172e-05, "loss": 3.7434, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.24223136960212e-05, "loss": 3.7449, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241392774851068e-05, "loss": 3.7367, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.240554180100016e-05, "loss": 3.7452, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.239717223229337e-05, "loss": 3.7292, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.238878628478285e-05, "loss": 3.7336, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.238040033727233e-05, "loss": 3.734, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.237201438976181e-05, "loss": 3.7221, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.236362844225129e-05, "loss": 3.7355, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.23552588735445e-05, "loss": 3.7242, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234687292603398e-05, "loss": 3.7298, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.233848697852346e-05, "loss": 3.7626, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.2330101031012945e-05, "loss": 3.732, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.2321731462306154e-05, "loss": 3.7337, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.2313345514795634e-05, "loss": 3.735, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.2304959567285114e-05, "loss": 3.7418, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.229657361977459e-05, "loss": 3.7215, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.22882040510678e-05, "loss": 3.7333, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.227981810355728e-05, "loss": 3.7343, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.227143215604676e-05, "loss": 3.7203, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.2263046208536236e-05, "loss": 3.727, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.2254660261025716e-05, "loss": 3.7248, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.2246274313515196e-05, "loss": 3.7334, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.223790474480841e-05, "loss": 3.7371, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.222951879729789e-05, "loss": 3.7318, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222113284978737e-05, "loss": 3.7292, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221274690227685e-05, "loss": 3.7322, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220436095476633e-05, "loss": 3.7373, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219597500725581e-05, "loss": 3.7259, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.218758905974529e-05, "loss": 3.7392, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.21792194910385e-05, "loss": 3.7154, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217083354352798e-05, "loss": 3.7332, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.216244759601746e-05, "loss": 3.7116, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.215406164850694e-05, "loss": 3.7452, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.214567570099642e-05, "loss": 3.7304, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.2137306132289637e-05, "loss": 3.7316, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128920184779116e-05, "loss": 3.7314, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120534237268596e-05, "loss": 3.7312, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.2112148289758076e-05, "loss": 3.7337, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.2103762342247556e-05, "loss": 3.7175, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.2095392773540765e-05, "loss": 3.7073, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.2087006826030245e-05, "loss": 3.7415, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.2078620878519725e-05, "loss": 3.7253, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.2070234931009205e-05, "loss": 3.7364, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.2061848983498685e-05, "loss": 3.7179, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.2053463035988165e-05, "loss": 3.7256, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.2045093467281374e-05, "loss": 3.7121, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.2036707519770854e-05, "loss": 3.7339, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.2028321572260334e-05, "loss": 3.7273, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201993562474982e-05, "loss": 3.7331, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.20115496772393e-05, "loss": 3.7347, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.200316372972878e-05, "loss": 3.7143, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.1994777782218254e-05, "loss": 3.7201, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.198640821351147e-05, "loss": 3.734, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.197802226600095e-05, "loss": 3.7125, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.196963631849042e-05, "loss": 3.7172, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.19612503709799e-05, "loss": 3.724, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.195288080227312e-05, "loss": 3.7311, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.19444948547626e-05, "loss": 3.7042, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.193610890725207e-05, "loss": 3.7132, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192772295974156e-05, "loss": 3.7121, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.1919353391034775e-05, "loss": 3.7183, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191096744352425e-05, "loss": 3.7278, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190258149601373e-05, "loss": 3.7207, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189419554850321e-05, "loss": 3.7242, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188580960099269e-05, "loss": 3.7154, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187742365348217e-05, "loss": 3.7378, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186905408477538e-05, "loss": 3.7118, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186066813726486e-05, "loss": 3.7269, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185228218975434e-05, "loss": 3.7213, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.1843896242243817e-05, "loss": 3.7198, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.1835526673537026e-05, "loss": 3.7253, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.182714072602651e-05, "loss": 3.7229, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.181875477851599e-05, "loss": 3.7188, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.181036883100547e-05, "loss": 3.7249, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180199926229868e-05, "loss": 3.7095, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179361331478816e-05, "loss": 3.7178, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178522736727764e-05, "loss": 3.7203, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.177684141976712e-05, "loss": 3.7266, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.17684554722566e-05, "loss": 3.7154, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.176008590354981e-05, "loss": 3.7084, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175169995603929e-05, "loss": 3.7169, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174331400852877e-05, "loss": 3.7211, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173492806101825e-05, "loss": 3.7206, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.1726558492311466e-05, "loss": 3.7068, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.1718172544800946e-05, "loss": 3.7201, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.1709786597290426e-05, "loss": 3.7288, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.1701400649779906e-05, "loss": 3.717, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.1693031081073115e-05, "loss": 3.6994, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.1684645133562595e-05, "loss": 3.7159, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.1676259186052075e-05, "loss": 3.7114, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.1667873238541555e-05, "loss": 3.7243, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.1659503669834764e-05, "loss": 3.723, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.1651117722324244e-05, "loss": 3.7101, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.1642731774813724e-05, "loss": 3.7103, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.1634345827303204e-05, "loss": 3.7194, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.162597625859642e-05, "loss": 3.7024, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.16175903110859e-05, "loss": 3.7146, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.160920436357538e-05, "loss": 3.7067, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160081841606486e-05, "loss": 3.7246, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159244884735807e-05, "loss": 3.6946, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158406289984755e-05, "loss": 3.7051, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.157567695233703e-05, "loss": 3.7082, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.156729100482651e-05, "loss": 3.7156, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155890505731599e-05, "loss": 3.7117, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.15505354886092e-05, "loss": 3.7035, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154214954109868e-05, "loss": 3.7149, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153376359358816e-05, "loss": 3.7171, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152537764607764e-05, "loss": 3.7047, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151699169856712e-05, "loss": 3.7238, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.15086057510566e-05, "loss": 3.7067, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.150023618234981e-05, "loss": 3.7134, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149185023483929e-05, "loss": 3.7039, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148346428732877e-05, "loss": 3.7113, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147507833981825e-05, "loss": 3.7027, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146669239230773e-05, "loss": 3.7107, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145832282360094e-05, "loss": 3.7142, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144993687609042e-05, "loss": 3.7109, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.14415509285799e-05, "loss": 3.7074, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.143316498106938e-05, "loss": 3.709, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.142479541236259e-05, "loss": 3.693, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.141640946485207e-05, "loss": 3.7214, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140802351734155e-05, "loss": 3.7066, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.139963756983103e-05, "loss": 3.7141, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139126800112425e-05, "loss": 3.7029, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138288205361373e-05, "loss": 3.7207, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137449610610321e-05, "loss": 3.7122, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136611015859268e-05, "loss": 3.7056, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357740589885896e-05, "loss": 3.7087, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.1349354642375376e-05, "loss": 3.712, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1340968694864856e-05, "loss": 3.7128, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.133258274735433e-05, "loss": 3.7249, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.132419679984381e-05, "loss": 3.6954, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.131581085233329e-05, "loss": 3.714, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1307441283626505e-05, "loss": 3.7047, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1299055336115985e-05, "loss": 3.7158, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.1290669388605465e-05, "loss": 3.711, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.1282283441094945e-05, "loss": 3.7051, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.1273897493584425e-05, "loss": 3.716, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.1265527924877634e-05, "loss": 3.7053, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.1257141977367114e-05, "loss": 3.7114, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.9071083068847656, "eval_runtime": 306.1144, "eval_samples_per_second": 1246.563, "eval_steps_per_second": 38.956, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.1248756029856594e-05, "loss": 3.7061, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.1240370082346074e-05, "loss": 3.6995, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.123200051363928e-05, "loss": 3.7099, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.122361456612876e-05, "loss": 3.7098, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.121522861861824e-05, "loss": 3.7155, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.120684267110773e-05, "loss": 3.7013, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.119845672359721e-05, "loss": 3.696, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.119008715489042e-05, "loss": 3.6967, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.11817012073799e-05, "loss": 3.7103, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117331525986938e-05, "loss": 3.7111, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116492931235886e-05, "loss": 3.6981, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115655974365207e-05, "loss": 3.7088, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.114817379614155e-05, "loss": 3.6998, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.113978784863103e-05, "loss": 3.6972, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.113140190112051e-05, "loss": 3.6961, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.1123032332413716e-05, "loss": 3.6919, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.1114646384903196e-05, "loss": 3.6984, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110626043739268e-05, "loss": 3.6947, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.109787448988216e-05, "loss": 3.6928, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108948854237164e-05, "loss": 3.7227, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.108111897366485e-05, "loss": 3.7, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.107273302615433e-05, "loss": 3.6964, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106434707864381e-05, "loss": 3.6987, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105596113113329e-05, "loss": 3.707, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.10475915624265e-05, "loss": 3.6879, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103920561491598e-05, "loss": 3.7006, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.103081966740546e-05, "loss": 3.7001, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.102243371989494e-05, "loss": 3.6883, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.101404777238442e-05, "loss": 3.6892, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.1005678203677637e-05, "loss": 3.6899, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.0997292256167117e-05, "loss": 3.6998, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.0988906308656597e-05, "loss": 3.7033, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.0980520361146076e-05, "loss": 3.6996, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.0972134413635556e-05, "loss": 3.6932, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.0963748466125036e-05, "loss": 3.6966, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.0955362518614516e-05, "loss": 3.7005, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.0946992949907725e-05, "loss": 3.6962, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.0938623381200935e-05, "loss": 3.6987, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.0930237433690414e-05, "loss": 3.6839, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.0921851486179894e-05, "loss": 3.6972, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.0913465538669374e-05, "loss": 3.6811, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.0905079591158854e-05, "loss": 3.7091, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.0896693643648334e-05, "loss": 3.6979, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.088832407494155e-05, "loss": 3.697, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.087993812743103e-05, "loss": 3.7011, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.087155217992051e-05, "loss": 3.6951, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.086316623240999e-05, "loss": 3.6983, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.085478028489946e-05, "loss": 3.6875, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084641071619268e-05, "loss": 3.6684, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083802476868216e-05, "loss": 3.7091, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.082963882117163e-05, "loss": 3.6903, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082125287366111e-05, "loss": 3.7037, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081288330495433e-05, "loss": 3.687, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080449735744381e-05, "loss": 3.691, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079611140993329e-05, "loss": 3.6764, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078772546242277e-05, "loss": 3.6987, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.0779355893715984e-05, "loss": 3.6945, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.0770969946205464e-05, "loss": 3.6958, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076258399869494e-05, "loss": 3.704, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075419805118442e-05, "loss": 3.6836, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.074582848247763e-05, "loss": 3.6861, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.0737442534967106e-05, "loss": 3.7017, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.0729056587456586e-05, "loss": 3.6797, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.0720670639946066e-05, "loss": 3.6824, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.0712284692435546e-05, "loss": 3.6928, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070391512372876e-05, "loss": 3.695, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069552917621824e-05, "loss": 3.6759, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068714322870772e-05, "loss": 3.6799, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.06787572811972e-05, "loss": 3.6767, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.067038771249041e-05, "loss": 3.686, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.066200176497989e-05, "loss": 3.6946, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.065361581746937e-05, "loss": 3.6892, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064522986995885e-05, "loss": 3.6887, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.063686030125206e-05, "loss": 3.6856, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.062847435374154e-05, "loss": 3.7038, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.062008840623102e-05, "loss": 3.678, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.06117024587205e-05, "loss": 3.6999, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.060331651120998e-05, "loss": 3.6863, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.0594946942503195e-05, "loss": 3.6824, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0586560994992675e-05, "loss": 3.6955, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.0578175047482155e-05, "loss": 3.6924, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.0569789099971635e-05, "loss": 3.6856, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.0561419531264844e-05, "loss": 3.6927, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.0553033583754324e-05, "loss": 3.6776, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.0544647636243804e-05, "loss": 3.6834, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.0536261688733284e-05, "loss": 3.6859, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.052789212002649e-05, "loss": 3.6964, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.051950617251597e-05, "loss": 3.6823, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.051112022500545e-05, "loss": 3.6815, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.050273427749493e-05, "loss": 3.678, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049436470878815e-05, "loss": 3.6901, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048597876127763e-05, "loss": 3.6887, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047759281376711e-05, "loss": 3.6739, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.046920686625659e-05, "loss": 3.6909, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.04608372975498e-05, "loss": 3.6951, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045245135003928e-05, "loss": 3.6826, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044406540252876e-05, "loss": 3.6673, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.043567945501824e-05, "loss": 3.6836, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.042730988631145e-05, "loss": 3.6777, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041892393880093e-05, "loss": 3.6933, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.041053799129041e-05, "loss": 3.6904, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040215204377989e-05, "loss": 3.678, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.03937824750731e-05, "loss": 3.6794, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038539652756258e-05, "loss": 3.6819, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037701058005206e-05, "loss": 3.674, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036862463254154e-05, "loss": 3.6811, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.036023868503102e-05, "loss": 3.6719, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.035186911632423e-05, "loss": 3.6929, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.034348316881371e-05, "loss": 3.6638, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.033509722130319e-05, "loss": 3.6732, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.032671127379267e-05, "loss": 3.6739, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.031834170508588e-05, "loss": 3.6848, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.030995575757536e-05, "loss": 3.6772, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.030156981006484e-05, "loss": 3.6742, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.029318386255432e-05, "loss": 3.6845, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.0284814293847536e-05, "loss": 3.689, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.0276428346337016e-05, "loss": 3.6726, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.0268042398826496e-05, "loss": 3.6884, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.0259656451315976e-05, "loss": 3.6799, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.0251286882609185e-05, "loss": 3.6805, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.0242900935098665e-05, "loss": 3.6736, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.0234514987588145e-05, "loss": 3.6761, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.0226129040077625e-05, "loss": 3.6718, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.0217759471370834e-05, "loss": 3.6826, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.0209373523860314e-05, "loss": 3.6841, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.0200987576349794e-05, "loss": 3.6786, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.0192601628839274e-05, "loss": 3.677, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.0184215681328754e-05, "loss": 3.6762, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.017584611262197e-05, "loss": 3.6634, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.016746016511145e-05, "loss": 3.6925, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.015907421760093e-05, "loss": 3.6732, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015068827009041e-05, "loss": 3.6822, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014231870138362e-05, "loss": 3.6715, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.01339327538731e-05, "loss": 3.6887, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012554680636258e-05, "loss": 3.6824, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011716085885206e-05, "loss": 3.6739, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.010879129014527e-05, "loss": 3.68, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.010040534263475e-05, "loss": 3.6768, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.009201939512423e-05, "loss": 3.6806, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.008363344761371e-05, "loss": 3.6996, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.007524750010319e-05, "loss": 3.6626, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.0066877931396404e-05, "loss": 3.6872, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.0058491983885883e-05, "loss": 3.6725, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.0050106036375363e-05, "loss": 3.6834, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.0041720088864837e-05, "loss": 3.6764, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.003335052015805e-05, "loss": 3.6785, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002496457264753e-05, "loss": 3.6838, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.0016578625137006e-05, "loss": 3.6763, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.0008192677626486e-05, "loss": 3.678, "step": 610304 }, { "epoch": 1.03, "eval_loss": 3.901350259780884, "eval_runtime": 305.4695, "eval_samples_per_second": 1249.195, "eval_steps_per_second": 39.038, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.9999806730115966e-05, "loss": 3.6756, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.9991420782605445e-05, "loss": 3.6686, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.998303483509493e-05, "loss": 3.6803, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997464888758441e-05, "loss": 3.6773, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996626294007389e-05, "loss": 3.6856, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.99578933713671e-05, "loss": 3.6708, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994950742385658e-05, "loss": 3.6699, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.994112147634606e-05, "loss": 3.6715, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.993273552883554e-05, "loss": 3.6771, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992436596012875e-05, "loss": 3.6796, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991598001261823e-05, "loss": 3.6678, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.990759406510771e-05, "loss": 3.676, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.989920811759719e-05, "loss": 3.6734, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.98908385488904e-05, "loss": 3.6631, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.9882452601379886e-05, "loss": 3.6717, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.9874066653869366e-05, "loss": 3.6594, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.9865680706358846e-05, "loss": 3.6673, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.9857311137652055e-05, "loss": 3.6625, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.9848925190141535e-05, "loss": 3.6638, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.9840539242631015e-05, "loss": 3.6894, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.9832153295120495e-05, "loss": 3.6741, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.9823783726413704e-05, "loss": 3.6695, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9815397778903184e-05, "loss": 3.6681, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.9807011831392664e-05, "loss": 3.6765, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.9798625883882144e-05, "loss": 3.6532, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.979025631517535e-05, "loss": 3.6727, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978187036766484e-05, "loss": 3.6726, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.977348442015432e-05, "loss": 3.6566, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.97650984726438e-05, "loss": 3.6568, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.975672890393701e-05, "loss": 3.6621, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.974834295642649e-05, "loss": 3.6686, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.973995700891597e-05, "loss": 3.6734, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.973157106140545e-05, "loss": 3.6665, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972320149269866e-05, "loss": 3.6666, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971481554518814e-05, "loss": 3.6695, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970642959767762e-05, "loss": 3.6689, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.96980436501671e-05, "loss": 3.6687, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.9689674081460306e-05, "loss": 3.6688, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.968128813394979e-05, "loss": 3.6531, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967290218643927e-05, "loss": 3.6675, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.966451623892875e-05, "loss": 3.6553, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.965613029141823e-05, "loss": 3.678, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.964776072271144e-05, "loss": 3.6707, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.963937477520092e-05, "loss": 3.6661, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.96309888276904e-05, "loss": 3.671, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962261925898361e-05, "loss": 3.6668, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.961423331147309e-05, "loss": 3.6722, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.960584736396257e-05, "loss": 3.6587, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.959746141645205e-05, "loss": 3.6357, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958909184774526e-05, "loss": 3.6778, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.958070590023475e-05, "loss": 3.6608, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957231995272423e-05, "loss": 3.6761, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956393400521371e-05, "loss": 3.6577, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.955554805770319e-05, "loss": 3.6594, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.9547178488996396e-05, "loss": 3.6505, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.9538792541485876e-05, "loss": 3.667, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.9530406593975356e-05, "loss": 3.6696, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.9522020646464836e-05, "loss": 3.6664, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.9513651077758045e-05, "loss": 3.6757, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.9505265130247525e-05, "loss": 3.6562, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.9496879182737005e-05, "loss": 3.6534, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.9488493235226485e-05, "loss": 3.6738, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.9480107287715965e-05, "loss": 3.6532, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.947173771900918e-05, "loss": 3.6534, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.946335177149866e-05, "loss": 3.6623, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945496582398814e-05, "loss": 3.6688, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.944657987647762e-05, "loss": 3.6469, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.943821030777083e-05, "loss": 3.6551, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.942982436026031e-05, "loss": 3.6483, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.942143841274979e-05, "loss": 3.6559, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.941305246523926e-05, "loss": 3.6663, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.940466651772874e-05, "loss": 3.6578, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939629694902196e-05, "loss": 3.6596, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.938791100151144e-05, "loss": 3.6585, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.937952505400092e-05, "loss": 3.6768, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.93711391064904e-05, "loss": 3.6506, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.9362769537783614e-05, "loss": 3.6682, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935438359027309e-05, "loss": 3.6585, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934599764276257e-05, "loss": 3.655, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.933761169525205e-05, "loss": 3.6673, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.932924212654526e-05, "loss": 3.6638, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.9320856179034736e-05, "loss": 3.6614, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.9312470231524216e-05, "loss": 3.6602, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.9304084284013696e-05, "loss": 3.6544, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.929571471530691e-05, "loss": 3.652, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.9287328767796385e-05, "loss": 3.6601, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.927894282028587e-05, "loss": 3.6657, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.927055687277535e-05, "loss": 3.6517, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.926218730406856e-05, "loss": 3.6532, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.925380135655804e-05, "loss": 3.6509, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.924541540904752e-05, "loss": 3.6652, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.9237029461537e-05, "loss": 3.6594, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.922865989283021e-05, "loss": 3.6464, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.922027394531969e-05, "loss": 3.6602, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.921188799780917e-05, "loss": 3.6672, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.920350205029865e-05, "loss": 3.6567, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.919513248159186e-05, "loss": 3.6396, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918674653408134e-05, "loss": 3.6536, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.9178360586570826e-05, "loss": 3.6496, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.9169974639060306e-05, "loss": 3.6652, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.9161605070353515e-05, "loss": 3.6617, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.9153219122842995e-05, "loss": 3.6585, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.9144833175332475e-05, "loss": 3.6513, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.9136447227821955e-05, "loss": 3.6527, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.9128077659115164e-05, "loss": 3.6491, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.9119691711604644e-05, "loss": 3.6511, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.9111305764094124e-05, "loss": 3.6455, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.9102919816583604e-05, "loss": 3.6646, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.909455024787681e-05, "loss": 3.641, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.908616430036629e-05, "loss": 3.6412, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.907777835285578e-05, "loss": 3.6499, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906939240534526e-05, "loss": 3.6512, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.906100645783474e-05, "loss": 3.654, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.905263688912795e-05, "loss": 3.6469, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904425094161743e-05, "loss": 3.6549, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.903586499410691e-05, "loss": 3.6641, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.902747904659639e-05, "loss": 3.6443, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.90191094778896e-05, "loss": 3.6577, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.901072353037908e-05, "loss": 3.6528, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.900233758286856e-05, "loss": 3.6549, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.899395163535804e-05, "loss": 3.648, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.8985582066651246e-05, "loss": 3.6466, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.897719611914073e-05, "loss": 3.6464, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.896881017163021e-05, "loss": 3.6543, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.896042422411969e-05, "loss": 3.6557, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.89520546554129e-05, "loss": 3.65, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.894366870790238e-05, "loss": 3.6506, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.893528276039186e-05, "loss": 3.6487, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892689681288134e-05, "loss": 3.6366, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891852724417455e-05, "loss": 3.6629, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.891014129666403e-05, "loss": 3.6442, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.890175534915351e-05, "loss": 3.6594, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889336940164299e-05, "loss": 3.6416, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.88849998329362e-05, "loss": 3.6617, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.887661388542569e-05, "loss": 3.6543, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.8868227937915167e-05, "loss": 3.6474, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.8859841990404647e-05, "loss": 3.6503, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.8851472421697856e-05, "loss": 3.6512, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.8843086474187336e-05, "loss": 3.6551, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.8834700526676816e-05, "loss": 3.67, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.8826314579166295e-05, "loss": 3.6361, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.8817945010459505e-05, "loss": 3.6632, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.8809559062948985e-05, "loss": 3.6427, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.8801173115438465e-05, "loss": 3.6559, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.8792787167927944e-05, "loss": 3.6526, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.8784417599221154e-05, "loss": 3.6512, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.877603165171064e-05, "loss": 3.6557, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.876764570420012e-05, "loss": 3.6527, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.87592597566896e-05, "loss": 3.6505, "step": 686592 }, { "epoch": 0.03, "eval_loss": 3.8975584506988525, "eval_runtime": 306.3478, "eval_samples_per_second": 1245.614, "eval_steps_per_second": 38.926, "step": 686880 }, { "epoch": 1.0, "learning_rate": 3.875089018798281e-05, "loss": 3.6467, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.874250424047229e-05, "loss": 3.6455, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.873411829296177e-05, "loss": 3.6528, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.872573234545125e-05, "loss": 3.6507, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.871736277674446e-05, "loss": 3.6563, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.870897682923394e-05, "loss": 3.6448, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.870059088172342e-05, "loss": 3.6445, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.86922049342129e-05, "loss": 3.6443, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.868383536550611e-05, "loss": 3.6477, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.8675449417995594e-05, "loss": 3.6524, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.8667063470485074e-05, "loss": 3.6446, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.8658677522974554e-05, "loss": 3.6468, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.8650291575464034e-05, "loss": 3.65, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.864192200675724e-05, "loss": 3.6362, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.863353605924672e-05, "loss": 3.644, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.86251501117362e-05, "loss": 3.6356, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.861676416422568e-05, "loss": 3.6345, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.860839459551889e-05, "loss": 3.6387, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.860000864800837e-05, "loss": 3.6385, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.859162270049785e-05, "loss": 3.6593, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.858323675298733e-05, "loss": 3.6509, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.857486718428055e-05, "loss": 3.6442, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.856648123677003e-05, "loss": 3.6433, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.855809528925951e-05, "loss": 3.6515, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.854970934174899e-05, "loss": 3.6298, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.8541339773042197e-05, "loss": 3.6462, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.8532953825531677e-05, "loss": 3.6472, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.8524567878021156e-05, "loss": 3.6279, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.8516181930510636e-05, "loss": 3.6369, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.8507812361803846e-05, "loss": 3.6334, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.8499426414293326e-05, "loss": 3.6435, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.8491040466782805e-05, "loss": 3.6434, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.8482654519272285e-05, "loss": 3.6422, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.8474284950565495e-05, "loss": 3.6496, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.846589900305498e-05, "loss": 3.6374, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.845751305554446e-05, "loss": 3.6436, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.844912710803394e-05, "loss": 3.6488, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.844075753932715e-05, "loss": 3.6386, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.843237159181663e-05, "loss": 3.6285, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.842398564430611e-05, "loss": 3.6413, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.841559969679558e-05, "loss": 3.6302, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.84072301280888e-05, "loss": 3.6497, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.839884418057828e-05, "loss": 3.6476, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.839045823306776e-05, "loss": 3.6376, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.838207228555723e-05, "loss": 3.647, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.837370271685045e-05, "loss": 3.6409, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.8365316769339935e-05, "loss": 3.6453, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.8356930821829415e-05, "loss": 3.6398, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.834854487431889e-05, "loss": 3.6071, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.8340175305612104e-05, "loss": 3.653, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.8331789358101584e-05, "loss": 3.6382, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.832340341059106e-05, "loss": 3.6457, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.831501746308054e-05, "loss": 3.6345, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.830664789437375e-05, "loss": 3.6346, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.829826194686323e-05, "loss": 3.625, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.8289875999352706e-05, "loss": 3.6415, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.8281490051842186e-05, "loss": 3.6422, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.827310410433167e-05, "loss": 3.6379, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.826473453562489e-05, "loss": 3.6541, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.825634858811436e-05, "loss": 3.6322, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.824796264060384e-05, "loss": 3.6245, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.823957669309332e-05, "loss": 3.652, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.823120712438653e-05, "loss": 3.6278, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.822282117687601e-05, "loss": 3.6245, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.821443522936549e-05, "loss": 3.6416, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.820604928185497e-05, "loss": 3.64, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.819767971314818e-05, "loss": 3.625, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.818929376563766e-05, "loss": 3.6268, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.818090781812714e-05, "loss": 3.6237, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.8172521870616626e-05, "loss": 3.6286, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.8164152301909835e-05, "loss": 3.6419, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.8155766354399315e-05, "loss": 3.6335, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.8147380406888795e-05, "loss": 3.6355, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.8138994459378275e-05, "loss": 3.6307, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.8130624890671484e-05, "loss": 3.6504, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.8122238943160964e-05, "loss": 3.6253, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.8113852995650444e-05, "loss": 3.6457, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.8105467048139924e-05, "loss": 3.6312, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.8097097479433133e-05, "loss": 3.6319, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808872791072635e-05, "loss": 3.6391, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.808034196321583e-05, "loss": 3.642, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.807195601570531e-05, "loss": 3.6327, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.806357006819479e-05, "loss": 3.6381, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.805518412068427e-05, "loss": 3.628, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.804679817317375e-05, "loss": 3.628, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.803841222566323e-05, "loss": 3.6339, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.803002627815271e-05, "loss": 3.641, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.802165670944592e-05, "loss": 3.6273, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.80132707619354e-05, "loss": 3.6321, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.800488481442488e-05, "loss": 3.6295, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.799649886691436e-05, "loss": 3.6357, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.798812929820757e-05, "loss": 3.6372, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.797974335069705e-05, "loss": 3.6219, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.7971357403186534e-05, "loss": 3.6369, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.7962971455676014e-05, "loss": 3.6377, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.795460188696922e-05, "loss": 3.6375, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.79462159394587e-05, "loss": 3.6142, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.793782999194818e-05, "loss": 3.6293, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.792944404443766e-05, "loss": 3.6256, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.792107447573087e-05, "loss": 3.6426, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.791268852822035e-05, "loss": 3.6334, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.790430258070983e-05, "loss": 3.6367, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.789591663319931e-05, "loss": 3.628, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.788754706449252e-05, "loss": 3.6258, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.7879161116982e-05, "loss": 3.6228, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.787077516947149e-05, "loss": 3.6311, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.786238922196097e-05, "loss": 3.6226, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.7854019653254176e-05, "loss": 3.6326, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.7845633705743656e-05, "loss": 3.6202, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.7837247758233136e-05, "loss": 3.6158, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.7828861810722616e-05, "loss": 3.6247, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.7820492242015825e-05, "loss": 3.6252, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.7812106294505305e-05, "loss": 3.6268, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.7803720346994785e-05, "loss": 3.6216, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.7795334399484265e-05, "loss": 3.6334, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.7786964830777474e-05, "loss": 3.6384, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.7778578883266954e-05, "loss": 3.6213, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.777019293575644e-05, "loss": 3.6326, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.776182336704965e-05, "loss": 3.6321, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.775343741953913e-05, "loss": 3.6297, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.774505147202861e-05, "loss": 3.6243, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.773666552451809e-05, "loss": 3.6209, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.77282959558113e-05, "loss": 3.6254, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.771991000830078e-05, "loss": 3.6279, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.771152406079026e-05, "loss": 3.6322, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.770313811327974e-05, "loss": 3.6283, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.769476854457295e-05, "loss": 3.6225, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.768638259706243e-05, "loss": 3.6249, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.767799664955191e-05, "loss": 3.6097, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.766961070204139e-05, "loss": 3.6388, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.7661241133334604e-05, "loss": 3.6211, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.7652855185824084e-05, "loss": 3.6375, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.7644469238313564e-05, "loss": 3.6177, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.7636083290803044e-05, "loss": 3.6371, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.762771372209625e-05, "loss": 3.6329, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.761932777458573e-05, "loss": 3.6213, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.761094182707521e-05, "loss": 3.6272, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.760255587956469e-05, "loss": 3.6239, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.75941863108579e-05, "loss": 3.6351, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.758580036334738e-05, "loss": 3.6413, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.757741441583686e-05, "loss": 3.6158, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.756902846832634e-05, "loss": 3.6328, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.756065889961956e-05, "loss": 3.6231, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.755227295210904e-05, "loss": 3.6314, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.754388700459852e-05, "loss": 3.6268, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.7535501057088e-05, "loss": 3.6329, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.7527131488381206e-05, "loss": 3.627, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.7518745540870686e-05, "loss": 3.6297, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.7510359593360166e-05, "loss": 3.6283, "step": 762880 }, { "epoch": 1.03, "eval_loss": 3.8971972465515137, "eval_runtime": 304.118, "eval_samples_per_second": 1254.747, "eval_steps_per_second": 39.212, "step": 763200 }, { "epoch": 0.0, "learning_rate": 3.7501973645849646e-05, "loss": 3.6235, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.7493587698339126e-05, "loss": 3.6186, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.7485201750828606e-05, "loss": 3.6277, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.747681580331808e-05, "loss": 3.6306, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.7468446234611295e-05, "loss": 3.633, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.746006028710078e-05, "loss": 3.6233, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.745167433959026e-05, "loss": 3.623, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.7443288392079735e-05, "loss": 3.6234, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.743491882337295e-05, "loss": 3.6217, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.742653287586243e-05, "loss": 3.629, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.7418146928351904e-05, "loss": 3.6216, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.7409760980841384e-05, "loss": 3.6195, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.74013914121346e-05, "loss": 3.6287, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.739300546462408e-05, "loss": 3.6122, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.738461951711355e-05, "loss": 3.6236, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.737623356960303e-05, "loss": 3.6111, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.736786400089625e-05, "loss": 3.6107, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.7359478053385736e-05, "loss": 3.6177, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.735109210587521e-05, "loss": 3.6124, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.734270615836469e-05, "loss": 3.6319, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.7334336589657905e-05, "loss": 3.6311, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.732595064214738e-05, "loss": 3.6208, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.731756469463686e-05, "loss": 3.6203, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.730917874712634e-05, "loss": 3.6233, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.7300809178419554e-05, "loss": 3.611, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.729242323090903e-05, "loss": 3.6238, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.728403728339851e-05, "loss": 3.6214, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.727565133588799e-05, "loss": 3.604, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.72672817671812e-05, "loss": 3.6115, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.725889581967068e-05, "loss": 3.6118, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.725050987216016e-05, "loss": 3.6232, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.724212392464964e-05, "loss": 3.6187, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.723375435594285e-05, "loss": 3.6195, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.722536840843233e-05, "loss": 3.6241, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.721698246092181e-05, "loss": 3.612, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.720861289221503e-05, "loss": 3.6239, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.72002269447045e-05, "loss": 3.6289, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.719184099719398e-05, "loss": 3.6098, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.718345504968346e-05, "loss": 3.6107, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.717506910217294e-05, "loss": 3.6142, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.7166699533466156e-05, "loss": 3.6089, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.7158313585955636e-05, "loss": 3.626, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.7149927638445116e-05, "loss": 3.6248, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.7141558069738325e-05, "loss": 3.6143, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.7133172122227805e-05, "loss": 3.622, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.7124786174717285e-05, "loss": 3.6177, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.7116400227206765e-05, "loss": 3.6192, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.7108030658499974e-05, "loss": 3.618, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.7099644710989454e-05, "loss": 3.5874, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.7091258763478934e-05, "loss": 3.6274, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.7082872815968414e-05, "loss": 3.6138, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.707450324726163e-05, "loss": 3.6229, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.706611729975111e-05, "loss": 3.6153, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.705773135224059e-05, "loss": 3.6111, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.704934540473007e-05, "loss": 3.6045, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.704097583602328e-05, "loss": 3.6188, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.703258988851276e-05, "loss": 3.6184, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.702420394100224e-05, "loss": 3.6146, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.701581799349172e-05, "loss": 3.6305, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.700744842478493e-05, "loss": 3.617, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.699906247727441e-05, "loss": 3.5949, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.699067652976389e-05, "loss": 3.625, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.698229058225337e-05, "loss": 3.6064, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.6973921013546584e-05, "loss": 3.6034, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.6965535066036064e-05, "loss": 3.6177, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.6957149118525544e-05, "loss": 3.6166, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.6948763171015024e-05, "loss": 3.6034, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.694039360230823e-05, "loss": 3.6058, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.693200765479771e-05, "loss": 3.6017, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.692362170728719e-05, "loss": 3.6047, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.691523575977667e-05, "loss": 3.6183, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.690686619106988e-05, "loss": 3.6118, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689848024355936e-05, "loss": 3.6136, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.689009429604884e-05, "loss": 3.6074, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.688170834853832e-05, "loss": 3.6262, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.687333877983154e-05, "loss": 3.6066, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.686495283232102e-05, "loss": 3.6227, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.68565668848105e-05, "loss": 3.6059, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.684818093729998e-05, "loss": 3.6123, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.6839811368593186e-05, "loss": 3.6185, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.6831425421082666e-05, "loss": 3.6175, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.6823039473572146e-05, "loss": 3.6084, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.6814653526061626e-05, "loss": 3.6194, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.6806267578551106e-05, "loss": 3.6006, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.6797881631040586e-05, "loss": 3.606, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.6789495683530066e-05, "loss": 3.6141, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.6781109736019546e-05, "loss": 3.6205, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.6772740167312755e-05, "loss": 3.6064, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.6764354219802235e-05, "loss": 3.6075, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.675596827229172e-05, "loss": 3.6053, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.67475823247812e-05, "loss": 3.6115, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.673921275607441e-05, "loss": 3.614, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.673082680856389e-05, "loss": 3.6012, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.672244086105337e-05, "loss": 3.6113, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.671405491354285e-05, "loss": 3.6167, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.670568534483606e-05, "loss": 3.6168, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.669729939732554e-05, "loss": 3.5874, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.668891344981502e-05, "loss": 3.6081, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.66805275023045e-05, "loss": 3.6057, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.667215793359771e-05, "loss": 3.6181, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.666377198608719e-05, "loss": 3.6145, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.6655386038576675e-05, "loss": 3.6111, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.6647000091066155e-05, "loss": 3.6032, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.6638630522359364e-05, "loss": 3.6087, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.6630244574848844e-05, "loss": 3.6009, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.6621858627338324e-05, "loss": 3.6062, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.6613472679827804e-05, "loss": 3.6001, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.6605103111121013e-05, "loss": 3.6115, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.6596717163610493e-05, "loss": 3.5991, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.658833121609997e-05, "loss": 3.5936, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.657996164739318e-05, "loss": 3.5985, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.657157569988266e-05, "loss": 3.6037, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.656318975237214e-05, "loss": 3.609, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.655480380486163e-05, "loss": 3.6005, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.654643423615484e-05, "loss": 3.6071, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.653804828864432e-05, "loss": 3.6139, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.65296623411338e-05, "loss": 3.6043, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.652127639362328e-05, "loss": 3.6106, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.651290682491649e-05, "loss": 3.6078, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.650452087740597e-05, "loss": 3.6082, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.649613492989545e-05, "loss": 3.6001, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.648774898238493e-05, "loss": 3.5976, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.6479379413678136e-05, "loss": 3.6063, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.6470993466167616e-05, "loss": 3.6046, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.6462607518657096e-05, "loss": 3.6086, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.645422157114658e-05, "loss": 3.6089, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644585200243979e-05, "loss": 3.5989, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.643746605492927e-05, "loss": 3.6012, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.642909648622248e-05, "loss": 3.5925, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.642071053871196e-05, "loss": 3.6155, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.641232459120144e-05, "loss": 3.5988, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.640393864369092e-05, "loss": 3.6134, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.63955526961804e-05, "loss": 3.599, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.6387166748669874e-05, "loss": 3.6139, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.6378780801159354e-05, "loss": 3.6119, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.6370394853648834e-05, "loss": 3.5975, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.636202528494205e-05, "loss": 3.6082, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.635363933743153e-05, "loss": 3.6, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.634525338992101e-05, "loss": 3.6165, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.633686744241049e-05, "loss": 3.6147, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.6328497873703705e-05, "loss": 3.6014, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.632011192619318e-05, "loss": 3.6054, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.631172597868266e-05, "loss": 3.6043, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.630334003117214e-05, "loss": 3.6146, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.629497046246535e-05, "loss": 3.602, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.628658451495483e-05, "loss": 3.6167, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.627819856744431e-05, "loss": 3.6006, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.626981261993379e-05, "loss": 3.6133, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.6261443051227e-05, "loss": 3.604, "step": 839168 }, { "epoch": 0.03, "eval_loss": 3.895061492919922, "eval_runtime": 302.5132, "eval_samples_per_second": 1261.403, "eval_steps_per_second": 39.42, "step": 839520 }, { "epoch": 1.0, "learning_rate": 3.625305710371648e-05, "loss": 3.6035, "step": 839680 }, { "epoch": 1.0, "learning_rate": 3.624467115620596e-05, "loss": 3.597, "step": 840192 }, { "epoch": 1.0, "learning_rate": 3.623628520869544e-05, "loss": 3.6045, "step": 840704 }, { "epoch": 1.0, "learning_rate": 3.622791563998865e-05, "loss": 3.6088, "step": 841216 }, { "epoch": 1.0, "learning_rate": 3.621952969247813e-05, "loss": 3.6153, "step": 841728 }, { "epoch": 1.0, "learning_rate": 3.621114374496761e-05, "loss": 3.6015, "step": 842240 }, { "epoch": 1.0, "learning_rate": 3.620275779745709e-05, "loss": 3.6011, "step": 842752 }, { "epoch": 1.0, "learning_rate": 3.61943882287503e-05, "loss": 3.6037, "step": 843264 }, { "epoch": 1.0, "learning_rate": 3.618600228123978e-05, "loss": 3.6045, "step": 843776 }, { "epoch": 1.0, "learning_rate": 3.617761633372926e-05, "loss": 3.6047, "step": 844288 }, { "epoch": 1.0, "learning_rate": 3.616923038621874e-05, "loss": 3.5986, "step": 844800 }, { "epoch": 1.0, "learning_rate": 3.616086081751196e-05, "loss": 3.5988, "step": 845312 }, { "epoch": 1.0, "learning_rate": 3.615247487000144e-05, "loss": 3.6107, "step": 845824 }, { "epoch": 1.0, "learning_rate": 3.614408892249092e-05, "loss": 3.5933, "step": 846336 }, { "epoch": 1.0, "learning_rate": 3.61357029749804e-05, "loss": 3.5973, "step": 846848 }, { "epoch": 1.0, "learning_rate": 3.6127333406273606e-05, "loss": 3.5891, "step": 847360 }, { "epoch": 1.0, "learning_rate": 3.6118947458763086e-05, "loss": 3.5877, "step": 847872 }, { "epoch": 1.0, "learning_rate": 3.6110561511252566e-05, "loss": 3.599, "step": 848384 }, { "epoch": 1.0, "learning_rate": 3.6102175563742046e-05, "loss": 3.5963, "step": 848896 }, { "epoch": 1.0, "learning_rate": 3.6093805995035255e-05, "loss": 3.6073, "step": 849408 }, { "epoch": 1.0, "learning_rate": 3.6085420047524735e-05, "loss": 3.6101, "step": 849920 }, { "epoch": 1.0, "learning_rate": 3.6077034100014215e-05, "loss": 3.599, "step": 850432 }, { "epoch": 1.0, "learning_rate": 3.6068648152503695e-05, "loss": 3.601, "step": 850944 }, { "epoch": 1.0, "learning_rate": 3.606027858379691e-05, "loss": 3.6019, "step": 851456 }, { "epoch": 1.0, "learning_rate": 3.605189263628639e-05, "loss": 3.5861, "step": 851968 }, { "epoch": 1.0, "learning_rate": 3.604350668877587e-05, "loss": 3.6055, "step": 852480 }, { "epoch": 1.0, "learning_rate": 3.603512074126535e-05, "loss": 3.598, "step": 852992 }, { "epoch": 1.0, "learning_rate": 3.602675117255856e-05, "loss": 3.5858, "step": 853504 }, { "epoch": 1.0, "learning_rate": 3.601836522504804e-05, "loss": 3.5892, "step": 854016 }, { "epoch": 1.0, "learning_rate": 3.600997927753752e-05, "loss": 3.5924, "step": 854528 }, { "epoch": 1.01, "learning_rate": 3.6001593330027e-05, "loss": 3.5969, "step": 855040 }, { "epoch": 1.01, "learning_rate": 3.599322376132021e-05, "loss": 3.5965, "step": 855552 }, { "epoch": 1.01, "learning_rate": 3.598483781380969e-05, "loss": 3.6044, "step": 856064 }, { "epoch": 1.01, "learning_rate": 3.597645186629917e-05, "loss": 3.5985, "step": 856576 }, { "epoch": 1.01, "learning_rate": 3.596806591878865e-05, "loss": 3.5894, "step": 857088 }, { "epoch": 1.01, "learning_rate": 3.5959696350081864e-05, "loss": 3.6047, "step": 857600 }, { "epoch": 1.01, "learning_rate": 3.5951310402571344e-05, "loss": 3.6064, "step": 858112 }, { "epoch": 1.01, "learning_rate": 3.5942924455060824e-05, "loss": 3.5913, "step": 858624 }, { "epoch": 1.01, "learning_rate": 3.5934538507550304e-05, "loss": 3.5907, "step": 859136 }, { "epoch": 1.01, "learning_rate": 3.592616893884351e-05, "loss": 3.5925, "step": 859648 }, { "epoch": 1.01, "learning_rate": 3.591778299133299e-05, "loss": 3.5861, "step": 860160 }, { "epoch": 1.01, "learning_rate": 3.59094134226262e-05, "loss": 3.6032, "step": 860672 }, { "epoch": 1.01, "learning_rate": 3.590102747511568e-05, "loss": 3.6033, "step": 861184 }, { "epoch": 1.01, "learning_rate": 3.589264152760516e-05, "loss": 3.601, "step": 861696 }, { "epoch": 1.01, "learning_rate": 3.588425558009464e-05, "loss": 3.5961, "step": 862208 }, { "epoch": 1.01, "learning_rate": 3.587586963258412e-05, "loss": 3.5994, "step": 862720 }, { "epoch": 1.01, "learning_rate": 3.58674836850736e-05, "loss": 3.5994, "step": 863232 }, { "epoch": 1.01, "learning_rate": 3.585909773756308e-05, "loss": 3.5964, "step": 863744 }, { "epoch": 1.01, "learning_rate": 3.58507281688563e-05, "loss": 3.5692, "step": 864256 }, { "epoch": 1.01, "learning_rate": 3.584234222134578e-05, "loss": 3.606, "step": 864768 }, { "epoch": 1.01, "learning_rate": 3.583397265263899e-05, "loss": 3.5934, "step": 865280 }, { "epoch": 1.01, "learning_rate": 3.582558670512847e-05, "loss": 3.605, "step": 865792 }, { "epoch": 1.01, "learning_rate": 3.581720075761795e-05, "loss": 3.5933, "step": 866304 }, { "epoch": 1.01, "learning_rate": 3.580881481010743e-05, "loss": 3.5886, "step": 866816 }, { "epoch": 1.01, "learning_rate": 3.580042886259691e-05, "loss": 3.5838, "step": 867328 }, { "epoch": 1.01, "learning_rate": 3.579204291508639e-05, "loss": 3.5944, "step": 867840 }, { "epoch": 1.01, "learning_rate": 3.578365696757587e-05, "loss": 3.6047, "step": 868352 }, { "epoch": 1.01, "learning_rate": 3.577527102006535e-05, "loss": 3.5907, "step": 868864 }, { "epoch": 1.01, "learning_rate": 3.5766901451358556e-05, "loss": 3.6096, "step": 869376 }, { "epoch": 1.01, "learning_rate": 3.5758515503848036e-05, "loss": 3.5946, "step": 869888 }, { "epoch": 1.01, "learning_rate": 3.575012955633752e-05, "loss": 3.575, "step": 870400 }, { "epoch": 1.01, "learning_rate": 3.574175998763073e-05, "loss": 3.6064, "step": 870912 }, { "epoch": 1.01, "learning_rate": 3.573337404012021e-05, "loss": 3.5885, "step": 871424 }, { "epoch": 1.01, "learning_rate": 3.572498809260969e-05, "loss": 3.5852, "step": 871936 }, { "epoch": 1.01, "learning_rate": 3.571660214509917e-05, "loss": 3.5941, "step": 872448 }, { "epoch": 1.01, "learning_rate": 3.570823257639238e-05, "loss": 3.5993, "step": 872960 }, { "epoch": 1.01, "learning_rate": 3.569984662888186e-05, "loss": 3.5792, "step": 873472 }, { "epoch": 1.01, "learning_rate": 3.569146068137134e-05, "loss": 3.5857, "step": 873984 }, { "epoch": 1.01, "learning_rate": 3.568307473386082e-05, "loss": 3.5787, "step": 874496 }, { "epoch": 1.01, "learning_rate": 3.567470516515403e-05, "loss": 3.5906, "step": 875008 }, { "epoch": 1.01, "learning_rate": 3.566631921764351e-05, "loss": 3.5949, "step": 875520 }, { "epoch": 1.01, "learning_rate": 3.565793327013299e-05, "loss": 3.5894, "step": 876032 }, { "epoch": 1.01, "learning_rate": 3.5649547322622476e-05, "loss": 3.597, "step": 876544 }, { "epoch": 1.01, "learning_rate": 3.5641177753915685e-05, "loss": 3.5846, "step": 877056 }, { "epoch": 1.01, "learning_rate": 3.5632791806405165e-05, "loss": 3.6055, "step": 877568 }, { "epoch": 1.01, "learning_rate": 3.5624405858894645e-05, "loss": 3.5905, "step": 878080 }, { "epoch": 1.01, "learning_rate": 3.5616019911384125e-05, "loss": 3.6021, "step": 878592 }, { "epoch": 1.01, "learning_rate": 3.5607650342677334e-05, "loss": 3.5874, "step": 879104 }, { "epoch": 1.01, "learning_rate": 3.5599264395166814e-05, "loss": 3.5912, "step": 879616 }, { "epoch": 1.01, "learning_rate": 3.559089482646002e-05, "loss": 3.599, "step": 880128 }, { "epoch": 1.01, "learning_rate": 3.55825088789495e-05, "loss": 3.5967, "step": 880640 }, { "epoch": 1.01, "learning_rate": 3.557412293143898e-05, "loss": 3.5925, "step": 881152 }, { "epoch": 1.01, "learning_rate": 3.556573698392846e-05, "loss": 3.598, "step": 881664 }, { "epoch": 1.01, "learning_rate": 3.555735103641794e-05, "loss": 3.5802, "step": 882176 }, { "epoch": 1.01, "learning_rate": 3.554896508890743e-05, "loss": 3.5862, "step": 882688 }, { "epoch": 1.01, "learning_rate": 3.55405791413969e-05, "loss": 3.5894, "step": 883200 }, { "epoch": 1.01, "learning_rate": 3.553219319388638e-05, "loss": 3.6021, "step": 883712 }, { "epoch": 1.01, "learning_rate": 3.55238236251796e-05, "loss": 3.5857, "step": 884224 }, { "epoch": 1.01, "learning_rate": 3.551543767766908e-05, "loss": 3.5879, "step": 884736 }, { "epoch": 1.01, "learning_rate": 3.550705173015855e-05, "loss": 3.5871, "step": 885248 }, { "epoch": 1.02, "learning_rate": 3.549866578264803e-05, "loss": 3.5896, "step": 885760 }, { "epoch": 1.02, "learning_rate": 3.549029621394125e-05, "loss": 3.5947, "step": 886272 }, { "epoch": 1.02, "learning_rate": 3.548191026643072e-05, "loss": 3.5814, "step": 886784 }, { "epoch": 1.02, "learning_rate": 3.54735243189202e-05, "loss": 3.5885, "step": 887296 }, { "epoch": 1.02, "learning_rate": 3.546513837140968e-05, "loss": 3.5992, "step": 887808 }, { "epoch": 1.02, "learning_rate": 3.54567688027029e-05, "loss": 3.5952, "step": 888320 }, { "epoch": 1.02, "learning_rate": 3.544838285519238e-05, "loss": 3.5722, "step": 888832 }, { "epoch": 1.02, "learning_rate": 3.543999690768186e-05, "loss": 3.5873, "step": 889344 }, { "epoch": 1.02, "learning_rate": 3.543161096017134e-05, "loss": 3.583, "step": 889856 }, { "epoch": 1.02, "learning_rate": 3.542324139146455e-05, "loss": 3.5978, "step": 890368 }, { "epoch": 1.02, "learning_rate": 3.5414855443954026e-05, "loss": 3.595, "step": 890880 }, { "epoch": 1.02, "learning_rate": 3.5406469496443506e-05, "loss": 3.5893, "step": 891392 }, { "epoch": 1.02, "learning_rate": 3.5398083548932986e-05, "loss": 3.5836, "step": 891904 }, { "epoch": 1.02, "learning_rate": 3.5389713980226195e-05, "loss": 3.5859, "step": 892416 }, { "epoch": 1.02, "learning_rate": 3.5381328032715675e-05, "loss": 3.5803, "step": 892928 }, { "epoch": 1.02, "learning_rate": 3.5372942085205155e-05, "loss": 3.5874, "step": 893440 }, { "epoch": 1.02, "learning_rate": 3.5364556137694635e-05, "loss": 3.5832, "step": 893952 }, { "epoch": 1.02, "learning_rate": 3.535618656898785e-05, "loss": 3.5889, "step": 894464 }, { "epoch": 1.02, "learning_rate": 3.534780062147733e-05, "loss": 3.5839, "step": 894976 }, { "epoch": 1.02, "learning_rate": 3.533941467396681e-05, "loss": 3.5714, "step": 895488 }, { "epoch": 1.02, "learning_rate": 3.533102872645629e-05, "loss": 3.5777, "step": 896000 }, { "epoch": 1.02, "learning_rate": 3.53226591577495e-05, "loss": 3.5812, "step": 896512 }, { "epoch": 1.02, "learning_rate": 3.531427321023898e-05, "loss": 3.5919, "step": 897024 }, { "epoch": 1.02, "learning_rate": 3.530588726272846e-05, "loss": 3.5805, "step": 897536 }, { "epoch": 1.02, "learning_rate": 3.529750131521794e-05, "loss": 3.5901, "step": 898048 }, { "epoch": 1.02, "learning_rate": 3.528913174651115e-05, "loss": 3.588, "step": 898560 }, { "epoch": 1.02, "learning_rate": 3.528074579900063e-05, "loss": 3.5881, "step": 899072 }, { "epoch": 1.02, "learning_rate": 3.527235985149011e-05, "loss": 3.5906, "step": 899584 }, { "epoch": 1.02, "learning_rate": 3.5263990282783324e-05, "loss": 3.5861, "step": 900096 }, { "epoch": 1.02, "learning_rate": 3.5255604335272804e-05, "loss": 3.5911, "step": 900608 }, { "epoch": 1.02, "learning_rate": 3.5247218387762284e-05, "loss": 3.5798, "step": 901120 }, { "epoch": 1.02, "learning_rate": 3.52388488190555e-05, "loss": 3.5799, "step": 901632 }, { "epoch": 1.02, "learning_rate": 3.523046287154497e-05, "loss": 3.5873, "step": 902144 }, { "epoch": 1.02, "learning_rate": 3.522207692403445e-05, "loss": 3.5856, "step": 902656 }, { "epoch": 1.02, "learning_rate": 3.521369097652393e-05, "loss": 3.5911, "step": 903168 }, { "epoch": 1.02, "learning_rate": 3.520530502901341e-05, "loss": 3.5859, "step": 903680 }, { "epoch": 1.02, "learning_rate": 3.519691908150289e-05, "loss": 3.5795, "step": 904192 }, { "epoch": 1.02, "learning_rate": 3.518853313399237e-05, "loss": 3.5801, "step": 904704 }, { "epoch": 1.02, "learning_rate": 3.518016356528558e-05, "loss": 3.5746, "step": 905216 }, { "epoch": 1.02, "learning_rate": 3.517177761777506e-05, "loss": 3.5912, "step": 905728 }, { "epoch": 1.02, "learning_rate": 3.516339167026454e-05, "loss": 3.5846, "step": 906240 }, { "epoch": 1.02, "learning_rate": 3.515500572275403e-05, "loss": 3.5955, "step": 906752 }, { "epoch": 1.02, "learning_rate": 3.514661977524351e-05, "loss": 3.5784, "step": 907264 }, { "epoch": 1.02, "learning_rate": 3.513825020653672e-05, "loss": 3.5927, "step": 907776 }, { "epoch": 1.02, "learning_rate": 3.51298642590262e-05, "loss": 3.5916, "step": 908288 }, { "epoch": 1.02, "learning_rate": 3.512147831151568e-05, "loss": 3.5795, "step": 908800 }, { "epoch": 1.02, "learning_rate": 3.511309236400516e-05, "loss": 3.5827, "step": 909312 }, { "epoch": 1.02, "learning_rate": 3.510470641649464e-05, "loss": 3.5842, "step": 909824 }, { "epoch": 1.02, "learning_rate": 3.509632046898412e-05, "loss": 3.5965, "step": 910336 }, { "epoch": 1.02, "learning_rate": 3.50879345214736e-05, "loss": 3.5959, "step": 910848 }, { "epoch": 1.02, "learning_rate": 3.507954857396308e-05, "loss": 3.5856, "step": 911360 }, { "epoch": 1.02, "learning_rate": 3.5071179005256286e-05, "loss": 3.5798, "step": 911872 }, { "epoch": 1.02, "learning_rate": 3.5062793057745766e-05, "loss": 3.5881, "step": 912384 }, { "epoch": 1.02, "learning_rate": 3.5054407110235246e-05, "loss": 3.5917, "step": 912896 }, { "epoch": 1.02, "learning_rate": 3.5046021162724726e-05, "loss": 3.5817, "step": 913408 }, { "epoch": 1.02, "learning_rate": 3.503765159401794e-05, "loss": 3.5958, "step": 913920 }, { "epoch": 1.02, "learning_rate": 3.502926564650742e-05, "loss": 3.5815, "step": 914432 }, { "epoch": 1.02, "learning_rate": 3.50208796989969e-05, "loss": 3.5931, "step": 914944 }, { "epoch": 1.02, "learning_rate": 3.501251013029011e-05, "loss": 3.5821, "step": 915456 }, { "epoch": 1.03, "eval_loss": 3.8951046466827393, "eval_runtime": 302.6511, "eval_samples_per_second": 1260.828, "eval_steps_per_second": 39.402, "step": 915840 }, { "epoch": 0.0, "learning_rate": 3.500412418277959e-05, "loss": 3.5922, "step": 915968 }, { "epoch": 0.0, "learning_rate": 3.499573823526907e-05, "loss": 3.5747, "step": 916480 }, { "epoch": 0.0, "learning_rate": 3.498735228775855e-05, "loss": 3.584, "step": 916992 }, { "epoch": 0.0, "learning_rate": 3.497896634024803e-05, "loss": 3.5905, "step": 917504 }, { "epoch": 0.0, "learning_rate": 3.497059677154124e-05, "loss": 3.5925, "step": 918016 }, { "epoch": 0.0, "learning_rate": 3.496221082403072e-05, "loss": 3.5848, "step": 918528 }, { "epoch": 0.0, "learning_rate": 3.49538248765202e-05, "loss": 3.5816, "step": 919040 }, { "epoch": 0.0, "learning_rate": 3.494543892900968e-05, "loss": 3.5844, "step": 919552 }, { "epoch": 0.0, "learning_rate": 3.4937069360302896e-05, "loss": 3.5829, "step": 920064 }, { "epoch": 0.0, "learning_rate": 3.4928683412792376e-05, "loss": 3.5821, "step": 920576 }, { "epoch": 0.0, "learning_rate": 3.4920297465281856e-05, "loss": 3.5825, "step": 921088 }, { "epoch": 0.0, "learning_rate": 3.4911911517771336e-05, "loss": 3.5803, "step": 921600 }, { "epoch": 0.0, "learning_rate": 3.4903541949064545e-05, "loss": 3.5918, "step": 922112 }, { "epoch": 0.0, "learning_rate": 3.4895156001554025e-05, "loss": 3.5702, "step": 922624 }, { "epoch": 0.0, "learning_rate": 3.4886770054043505e-05, "loss": 3.5773, "step": 923136 }, { "epoch": 0.0, "learning_rate": 3.487838410653298e-05, "loss": 3.5733, "step": 923648 }, { "epoch": 0.0, "learning_rate": 3.4870014537826194e-05, "loss": 3.5687, "step": 924160 }, { "epoch": 0.0, "learning_rate": 3.4861628590315674e-05, "loss": 3.5776, "step": 924672 }, { "epoch": 0.0, "learning_rate": 3.4853242642805154e-05, "loss": 3.5748, "step": 925184 }, { "epoch": 0.0, "learning_rate": 3.4844856695294634e-05, "loss": 3.5887, "step": 925696 }, { "epoch": 0.0, "learning_rate": 3.483648712658785e-05, "loss": 3.5913, "step": 926208 }, { "epoch": 0.0, "learning_rate": 3.482810117907733e-05, "loss": 3.5804, "step": 926720 }, { "epoch": 0.0, "learning_rate": 3.48197152315668e-05, "loss": 3.581, "step": 927232 }, { "epoch": 0.0, "learning_rate": 3.481132928405628e-05, "loss": 3.5862, "step": 927744 }, { "epoch": 0.0, "learning_rate": 3.48029597153495e-05, "loss": 3.5647, "step": 928256 }, { "epoch": 0.0, "learning_rate": 3.479457376783898e-05, "loss": 3.5909, "step": 928768 }, { "epoch": 0.0, "learning_rate": 3.478618782032845e-05, "loss": 3.5729, "step": 929280 }, { "epoch": 0.0, "learning_rate": 3.477780187281793e-05, "loss": 3.569, "step": 929792 }, { "epoch": 0.0, "learning_rate": 3.476943230411115e-05, "loss": 3.5736, "step": 930304 }, { "epoch": 0.0, "learning_rate": 3.476104635660063e-05, "loss": 3.5707, "step": 930816 }, { "epoch": 0.01, "learning_rate": 3.475266040909011e-05, "loss": 3.5788, "step": 931328 }, { "epoch": 0.01, "learning_rate": 3.474427446157959e-05, "loss": 3.5754, "step": 931840 }, { "epoch": 0.01, "learning_rate": 3.47359048928728e-05, "loss": 3.5888, "step": 932352 }, { "epoch": 0.01, "learning_rate": 3.4727518945362276e-05, "loss": 3.5772, "step": 932864 }, { "epoch": 0.01, "learning_rate": 3.4719132997851756e-05, "loss": 3.5718, "step": 933376 }, { "epoch": 0.01, "learning_rate": 3.4710747050341236e-05, "loss": 3.5822, "step": 933888 }, { "epoch": 0.01, "learning_rate": 3.470237748163445e-05, "loss": 3.5898, "step": 934400 }, { "epoch": 0.01, "learning_rate": 3.4693991534123925e-05, "loss": 3.5734, "step": 934912 }, { "epoch": 0.01, "learning_rate": 3.4685605586613405e-05, "loss": 3.5675, "step": 935424 }, { "epoch": 0.01, "learning_rate": 3.4677219639102885e-05, "loss": 3.5753, "step": 935936 }, { "epoch": 0.01, "learning_rate": 3.46688500703961e-05, "loss": 3.5684, "step": 936448 }, { "epoch": 0.01, "learning_rate": 3.466048050168931e-05, "loss": 3.5806, "step": 936960 }, { "epoch": 0.01, "learning_rate": 3.465209455417879e-05, "loss": 3.5824, "step": 937472 }, { "epoch": 0.01, "learning_rate": 3.464370860666828e-05, "loss": 3.5854, "step": 937984 }, { "epoch": 0.01, "learning_rate": 3.463532265915775e-05, "loss": 3.5793, "step": 938496 }, { "epoch": 0.01, "learning_rate": 3.462693671164723e-05, "loss": 3.5785, "step": 939008 }, { "epoch": 0.01, "learning_rate": 3.461855076413671e-05, "loss": 3.5789, "step": 939520 }, { "epoch": 0.01, "learning_rate": 3.461016481662619e-05, "loss": 3.5762, "step": 940032 }, { "epoch": 0.01, "learning_rate": 3.460177886911567e-05, "loss": 3.5502, "step": 940544 }, { "epoch": 0.01, "learning_rate": 3.459340930040888e-05, "loss": 3.584, "step": 941056 }, { "epoch": 0.01, "learning_rate": 3.458502335289836e-05, "loss": 3.5748, "step": 941568 }, { "epoch": 0.01, "learning_rate": 3.457663740538784e-05, "loss": 3.5849, "step": 942080 }, { "epoch": 0.01, "learning_rate": 3.456825145787732e-05, "loss": 3.5719, "step": 942592 }, { "epoch": 0.01, "learning_rate": 3.455988188917053e-05, "loss": 3.5751, "step": 943104 }, { "epoch": 0.01, "learning_rate": 3.4551512320463744e-05, "loss": 3.5622, "step": 943616 }, { "epoch": 0.01, "learning_rate": 3.4543126372953224e-05, "loss": 3.5728, "step": 944128 }, { "epoch": 0.01, "learning_rate": 3.4534740425442704e-05, "loss": 3.5899, "step": 944640 }, { "epoch": 0.01, "learning_rate": 3.4526354477932184e-05, "loss": 3.5729, "step": 945152 }, { "epoch": 0.01, "learning_rate": 3.4517968530421664e-05, "loss": 3.5887, "step": 945664 }, { "epoch": 0.01, "learning_rate": 3.4509582582911144e-05, "loss": 3.5767, "step": 946176 }, { "epoch": 0.01, "learning_rate": 3.4501196635400624e-05, "loss": 3.554, "step": 946688 }, { "epoch": 0.01, "learning_rate": 3.4492810687890104e-05, "loss": 3.5903, "step": 947200 }, { "epoch": 0.01, "learning_rate": 3.448444111918331e-05, "loss": 3.569, "step": 947712 }, { "epoch": 0.01, "learning_rate": 3.447605517167279e-05, "loss": 3.5637, "step": 948224 }, { "epoch": 0.01, "learning_rate": 3.446766922416227e-05, "loss": 3.5777, "step": 948736 }, { "epoch": 0.01, "learning_rate": 3.445928327665175e-05, "loss": 3.5781, "step": 949248 }, { "epoch": 0.01, "learning_rate": 3.445091370794497e-05, "loss": 3.5629, "step": 949760 }, { "epoch": 0.01, "learning_rate": 3.444252776043445e-05, "loss": 3.5656, "step": 950272 }, { "epoch": 0.01, "learning_rate": 3.443414181292393e-05, "loss": 3.563, "step": 950784 }, { "epoch": 0.01, "learning_rate": 3.442575586541341e-05, "loss": 3.5652, "step": 951296 }, { "epoch": 0.01, "learning_rate": 3.441738629670662e-05, "loss": 3.5796, "step": 951808 }, { "epoch": 0.01, "learning_rate": 3.44090003491961e-05, "loss": 3.5719, "step": 952320 }, { "epoch": 0.01, "learning_rate": 3.440061440168558e-05, "loss": 3.5744, "step": 952832 }, { "epoch": 0.01, "learning_rate": 3.4392244832978786e-05, "loss": 3.5667, "step": 953344 }, { "epoch": 0.01, "learning_rate": 3.4383858885468266e-05, "loss": 3.5851, "step": 953856 }, { "epoch": 0.01, "learning_rate": 3.4375472937957746e-05, "loss": 3.5694, "step": 954368 }, { "epoch": 0.01, "learning_rate": 3.4367086990447226e-05, "loss": 3.5826, "step": 954880 }, { "epoch": 0.01, "learning_rate": 3.4358701042936706e-05, "loss": 3.566, "step": 955392 }, { "epoch": 0.01, "learning_rate": 3.4350315095426186e-05, "loss": 3.5718, "step": 955904 }, { "epoch": 0.01, "learning_rate": 3.43419455267194e-05, "loss": 3.5806, "step": 956416 }, { "epoch": 0.01, "learning_rate": 3.433355957920888e-05, "loss": 3.5773, "step": 956928 }, { "epoch": 0.01, "learning_rate": 3.432517363169836e-05, "loss": 3.5728, "step": 957440 }, { "epoch": 0.01, "learning_rate": 3.431678768418784e-05, "loss": 3.5806, "step": 957952 }, { "epoch": 0.01, "learning_rate": 3.430840173667732e-05, "loss": 3.5628, "step": 958464 }, { "epoch": 0.01, "learning_rate": 3.43000157891668e-05, "loss": 3.5663, "step": 958976 }, { "epoch": 0.01, "learning_rate": 3.429162984165628e-05, "loss": 3.5715, "step": 959488 }, { "epoch": 0.01, "learning_rate": 3.428324389414576e-05, "loss": 3.5786, "step": 960000 }, { "epoch": 0.01, "learning_rate": 3.427487432543897e-05, "loss": 3.5674, "step": 960512 }, { "epoch": 0.01, "learning_rate": 3.426648837792845e-05, "loss": 3.5723, "step": 961024 }, { "epoch": 0.01, "learning_rate": 3.425810243041793e-05, "loss": 3.5678, "step": 961536 }, { "epoch": 0.02, "learning_rate": 3.424971648290741e-05, "loss": 3.5712, "step": 962048 }, { "epoch": 0.02, "learning_rate": 3.424134691420062e-05, "loss": 3.5744, "step": 962560 }, { "epoch": 0.02, "learning_rate": 3.42329609666901e-05, "loss": 3.5659, "step": 963072 }, { "epoch": 0.02, "learning_rate": 3.4224575019179586e-05, "loss": 3.5712, "step": 963584 }, { "epoch": 0.02, "learning_rate": 3.421618907166906e-05, "loss": 3.5797, "step": 964096 }, { "epoch": 0.02, "learning_rate": 3.4207819502962275e-05, "loss": 3.5818, "step": 964608 }, { "epoch": 0.02, "learning_rate": 3.4199433555451755e-05, "loss": 3.5485, "step": 965120 }, { "epoch": 0.02, "learning_rate": 3.4191047607941235e-05, "loss": 3.5696, "step": 965632 }, { "epoch": 0.02, "learning_rate": 3.418266166043071e-05, "loss": 3.5633, "step": 966144 }, { "epoch": 0.02, "learning_rate": 3.4174292091723924e-05, "loss": 3.5816, "step": 966656 }, { "epoch": 0.02, "learning_rate": 3.4165906144213404e-05, "loss": 3.5768, "step": 967168 }, { "epoch": 0.02, "learning_rate": 3.415752019670288e-05, "loss": 3.571, "step": 967680 }, { "epoch": 0.02, "learning_rate": 3.414913424919236e-05, "loss": 3.563, "step": 968192 }, { "epoch": 0.02, "learning_rate": 3.4140764680485573e-05, "loss": 3.5695, "step": 968704 }, { "epoch": 0.02, "learning_rate": 3.413237873297505e-05, "loss": 3.5652, "step": 969216 }, { "epoch": 0.02, "learning_rate": 3.412399278546453e-05, "loss": 3.5681, "step": 969728 }, { "epoch": 0.02, "learning_rate": 3.411560683795401e-05, "loss": 3.5641, "step": 970240 }, { "epoch": 0.02, "learning_rate": 3.410723726924723e-05, "loss": 3.572, "step": 970752 }, { "epoch": 0.02, "learning_rate": 3.409885132173671e-05, "loss": 3.5664, "step": 971264 }, { "epoch": 0.02, "learning_rate": 3.409046537422618e-05, "loss": 3.5554, "step": 971776 }, { "epoch": 0.02, "learning_rate": 3.40820958055194e-05, "loss": 3.5612, "step": 972288 }, { "epoch": 0.02, "learning_rate": 3.407370985800888e-05, "loss": 3.5595, "step": 972800 }, { "epoch": 0.02, "learning_rate": 3.406532391049835e-05, "loss": 3.5731, "step": 973312 }, { "epoch": 0.02, "learning_rate": 3.405693796298783e-05, "loss": 3.5625, "step": 973824 }, { "epoch": 0.02, "learning_rate": 3.404856839428105e-05, "loss": 3.5722, "step": 974336 }, { "epoch": 0.02, "learning_rate": 3.404018244677053e-05, "loss": 3.5728, "step": 974848 }, { "epoch": 0.02, "learning_rate": 3.403179649926001e-05, "loss": 3.5707, "step": 975360 }, { "epoch": 0.02, "learning_rate": 3.402341055174949e-05, "loss": 3.5696, "step": 975872 }, { "epoch": 0.02, "learning_rate": 3.40150409830427e-05, "loss": 3.5688, "step": 976384 }, { "epoch": 0.02, "learning_rate": 3.400665503553218e-05, "loss": 3.5736, "step": 976896 }, { "epoch": 0.02, "learning_rate": 3.3998269088021656e-05, "loss": 3.5598, "step": 977408 }, { "epoch": 0.02, "learning_rate": 3.3989883140511136e-05, "loss": 3.56, "step": 977920 }, { "epoch": 0.02, "learning_rate": 3.398151357180435e-05, "loss": 3.5668, "step": 978432 }, { "epoch": 0.02, "learning_rate": 3.3973127624293825e-05, "loss": 3.5685, "step": 978944 }, { "epoch": 0.02, "learning_rate": 3.3964741676783305e-05, "loss": 3.5721, "step": 979456 }, { "epoch": 0.02, "learning_rate": 3.3956355729272785e-05, "loss": 3.565, "step": 979968 }, { "epoch": 0.02, "learning_rate": 3.3947969781762265e-05, "loss": 3.5639, "step": 980480 }, { "epoch": 0.02, "learning_rate": 3.3939583834251745e-05, "loss": 3.5662, "step": 980992 }, { "epoch": 0.02, "learning_rate": 3.393121426554496e-05, "loss": 3.5587, "step": 981504 }, { "epoch": 0.02, "learning_rate": 3.392282831803444e-05, "loss": 3.5701, "step": 982016 }, { "epoch": 0.02, "learning_rate": 3.391444237052392e-05, "loss": 3.5671, "step": 982528 }, { "epoch": 0.02, "learning_rate": 3.39060564230134e-05, "loss": 3.5802, "step": 983040 }, { "epoch": 0.02, "learning_rate": 3.389767047550288e-05, "loss": 3.5605, "step": 983552 }, { "epoch": 0.02, "learning_rate": 3.388930090679609e-05, "loss": 3.569, "step": 984064 }, { "epoch": 0.02, "learning_rate": 3.388091495928557e-05, "loss": 3.5748, "step": 984576 }, { "epoch": 0.02, "learning_rate": 3.387252901177505e-05, "loss": 3.5639, "step": 985088 }, { "epoch": 0.02, "learning_rate": 3.386414306426453e-05, "loss": 3.5607, "step": 985600 }, { "epoch": 0.02, "learning_rate": 3.385575711675401e-05, "loss": 3.5657, "step": 986112 }, { "epoch": 0.02, "learning_rate": 3.384737116924349e-05, "loss": 3.5782, "step": 986624 }, { "epoch": 0.02, "learning_rate": 3.383898522173297e-05, "loss": 3.5787, "step": 987136 }, { "epoch": 0.02, "learning_rate": 3.3830615653026185e-05, "loss": 3.5681, "step": 987648 }, { "epoch": 0.02, "learning_rate": 3.3822229705515665e-05, "loss": 3.5624, "step": 988160 }, { "epoch": 0.02, "learning_rate": 3.3813843758005145e-05, "loss": 3.5704, "step": 988672 }, { "epoch": 0.02, "learning_rate": 3.3805457810494625e-05, "loss": 3.5726, "step": 989184 }, { "epoch": 0.02, "learning_rate": 3.3797071862984105e-05, "loss": 3.5622, "step": 989696 }, { "epoch": 0.02, "learning_rate": 3.3788685915473585e-05, "loss": 3.5847, "step": 990208 }, { "epoch": 0.02, "learning_rate": 3.3780299967963065e-05, "loss": 3.559, "step": 990720 }, { "epoch": 0.02, "learning_rate": 3.3771930399256274e-05, "loss": 3.575, "step": 991232 }, { "epoch": 0.02, "learning_rate": 3.3763544451745754e-05, "loss": 3.5663, "step": 991744 }, { "epoch": 0.03, "eval_loss": 3.895094633102417, "eval_runtime": 302.8316, "eval_samples_per_second": 1260.077, "eval_steps_per_second": 39.378, "step": 992160 }, { "epoch": 1.0, "learning_rate": 3.3755158504235234e-05, "loss": 3.5712, "step": 992256 }, { "epoch": 1.0, "learning_rate": 3.3746772556724714e-05, "loss": 3.5568, "step": 992768 }, { "epoch": 1.0, "learning_rate": 3.373840298801792e-05, "loss": 3.5635, "step": 993280 }, { "epoch": 1.0, "learning_rate": 3.37300170405074e-05, "loss": 3.5765, "step": 993792 }, { "epoch": 1.0, "learning_rate": 3.372163109299688e-05, "loss": 3.5681, "step": 994304 }, { "epoch": 1.0, "learning_rate": 3.371324514548636e-05, "loss": 3.572, "step": 994816 }, { "epoch": 1.0, "learning_rate": 3.370487557677958e-05, "loss": 3.561, "step": 995328 }, { "epoch": 1.0, "learning_rate": 3.369648962926906e-05, "loss": 3.5624, "step": 995840 }, { "epoch": 1.0, "learning_rate": 3.368810368175854e-05, "loss": 3.5648, "step": 996352 }, { "epoch": 1.0, "learning_rate": 3.367971773424802e-05, "loss": 3.5672, "step": 996864 }, { "epoch": 1.0, "learning_rate": 3.367134816554123e-05, "loss": 3.5624, "step": 997376 }, { "epoch": 1.0, "learning_rate": 3.366296221803071e-05, "loss": 3.5681, "step": 997888 }, { "epoch": 1.0, "learning_rate": 3.365457627052019e-05, "loss": 3.5718, "step": 998400 }, { "epoch": 1.0, "learning_rate": 3.364619032300966e-05, "loss": 3.5513, "step": 998912 }, { "epoch": 1.0, "learning_rate": 3.363782075430288e-05, "loss": 3.563, "step": 999424 }, { "epoch": 1.0, "learning_rate": 3.362943480679236e-05, "loss": 3.5507, "step": 999936 }, { "epoch": 1.0, "learning_rate": 3.3621048859281837e-05, "loss": 3.5489, "step": 1000448 }, { "epoch": 1.0, "learning_rate": 3.3612662911771317e-05, "loss": 3.5652, "step": 1000960 }, { "epoch": 1.0, "learning_rate": 3.360429334306453e-05, "loss": 3.5554, "step": 1001472 }, { "epoch": 1.0, "learning_rate": 3.359590739555401e-05, "loss": 3.5702, "step": 1001984 }, { "epoch": 1.0, "learning_rate": 3.3587521448043486e-05, "loss": 3.5745, "step": 1002496 }, { "epoch": 1.0, "learning_rate": 3.35791518793367e-05, "loss": 3.5609, "step": 1003008 }, { "epoch": 1.0, "learning_rate": 3.357076593182618e-05, "loss": 3.5642, "step": 1003520 }, { "epoch": 1.0, "learning_rate": 3.356237998431566e-05, "loss": 3.5662, "step": 1004032 }, { "epoch": 1.0, "learning_rate": 3.3553994036805135e-05, "loss": 3.5497, "step": 1004544 }, { "epoch": 1.0, "learning_rate": 3.3545608089294614e-05, "loss": 3.5686, "step": 1005056 }, { "epoch": 1.0, "learning_rate": 3.3537222141784094e-05, "loss": 3.5588, "step": 1005568 }, { "epoch": 1.0, "learning_rate": 3.3528836194273574e-05, "loss": 3.5542, "step": 1006080 }, { "epoch": 1.0, "learning_rate": 3.3520450246763054e-05, "loss": 3.556, "step": 1006592 }, { "epoch": 1.0, "learning_rate": 3.351208067805627e-05, "loss": 3.5483, "step": 1007104 }, { "epoch": 1.01, "learning_rate": 3.350369473054575e-05, "loss": 3.5575, "step": 1007616 }, { "epoch": 1.01, "learning_rate": 3.349530878303523e-05, "loss": 3.5601, "step": 1008128 }, { "epoch": 1.01, "learning_rate": 3.348692283552471e-05, "loss": 3.569, "step": 1008640 }, { "epoch": 1.01, "learning_rate": 3.347855326681792e-05, "loss": 3.5572, "step": 1009152 }, { "epoch": 1.01, "learning_rate": 3.34701673193074e-05, "loss": 3.5576, "step": 1009664 }, { "epoch": 1.01, "learning_rate": 3.346178137179688e-05, "loss": 3.5594, "step": 1010176 }, { "epoch": 1.01, "learning_rate": 3.345339542428636e-05, "loss": 3.5743, "step": 1010688 }, { "epoch": 1.01, "learning_rate": 3.344502585557957e-05, "loss": 3.557, "step": 1011200 }, { "epoch": 1.01, "learning_rate": 3.343663990806905e-05, "loss": 3.5506, "step": 1011712 }, { "epoch": 1.01, "learning_rate": 3.342825396055853e-05, "loss": 3.5565, "step": 1012224 }, { "epoch": 1.01, "learning_rate": 3.341986801304801e-05, "loss": 3.5539, "step": 1012736 }, { "epoch": 1.01, "learning_rate": 3.3411498444341224e-05, "loss": 3.5588, "step": 1013248 }, { "epoch": 1.01, "learning_rate": 3.3403112496830704e-05, "loss": 3.5685, "step": 1013760 }, { "epoch": 1.01, "learning_rate": 3.3394726549320184e-05, "loss": 3.5649, "step": 1014272 }, { "epoch": 1.01, "learning_rate": 3.3386340601809664e-05, "loss": 3.5588, "step": 1014784 }, { "epoch": 1.01, "learning_rate": 3.3377954654299144e-05, "loss": 3.5621, "step": 1015296 }, { "epoch": 1.01, "learning_rate": 3.3369568706788624e-05, "loss": 3.5599, "step": 1015808 }, { "epoch": 1.01, "learning_rate": 3.3361182759278104e-05, "loss": 3.5593, "step": 1016320 }, { "epoch": 1.01, "learning_rate": 3.3352796811767584e-05, "loss": 3.5399, "step": 1016832 }, { "epoch": 1.01, "learning_rate": 3.334442724306079e-05, "loss": 3.5634, "step": 1017344 }, { "epoch": 1.01, "learning_rate": 3.333604129555027e-05, "loss": 3.5584, "step": 1017856 }, { "epoch": 1.01, "learning_rate": 3.332765534803975e-05, "loss": 3.5658, "step": 1018368 }, { "epoch": 1.01, "learning_rate": 3.331926940052923e-05, "loss": 3.5529, "step": 1018880 }, { "epoch": 1.01, "learning_rate": 3.331089983182245e-05, "loss": 3.5578, "step": 1019392 }, { "epoch": 1.01, "learning_rate": 3.330253026311566e-05, "loss": 3.5513, "step": 1019904 }, { "epoch": 1.01, "learning_rate": 3.329414431560514e-05, "loss": 3.5497, "step": 1020416 }, { "epoch": 1.01, "learning_rate": 3.328575836809462e-05, "loss": 3.5699, "step": 1020928 }, { "epoch": 1.01, "learning_rate": 3.32773724205841e-05, "loss": 3.5546, "step": 1021440 }, { "epoch": 1.01, "learning_rate": 3.326898647307358e-05, "loss": 3.5758, "step": 1021952 }, { "epoch": 1.01, "learning_rate": 3.326060052556306e-05, "loss": 3.5542, "step": 1022464 }, { "epoch": 1.01, "learning_rate": 3.325221457805254e-05, "loss": 3.5409, "step": 1022976 }, { "epoch": 1.01, "learning_rate": 3.324382863054202e-05, "loss": 3.572, "step": 1023488 }, { "epoch": 1.01, "learning_rate": 3.3235459061835226e-05, "loss": 3.5538, "step": 1024000 }, { "epoch": 1.01, "learning_rate": 3.3227073114324706e-05, "loss": 3.5469, "step": 1024512 }, { "epoch": 1.01, "learning_rate": 3.3218687166814186e-05, "loss": 3.5541, "step": 1025024 }, { "epoch": 1.01, "learning_rate": 3.3210301219303666e-05, "loss": 3.5637, "step": 1025536 }, { "epoch": 1.01, "learning_rate": 3.3201915271793146e-05, "loss": 3.5433, "step": 1026048 }, { "epoch": 1.01, "learning_rate": 3.3193529324282626e-05, "loss": 3.5504, "step": 1026560 }, { "epoch": 1.01, "learning_rate": 3.3185143376772106e-05, "loss": 3.5483, "step": 1027072 }, { "epoch": 1.01, "learning_rate": 3.3176757429261586e-05, "loss": 3.5439, "step": 1027584 }, { "epoch": 1.01, "learning_rate": 3.3168387860554795e-05, "loss": 3.5651, "step": 1028096 }, { "epoch": 1.01, "learning_rate": 3.3160001913044275e-05, "loss": 3.5562, "step": 1028608 }, { "epoch": 1.01, "learning_rate": 3.3151615965533755e-05, "loss": 3.5545, "step": 1029120 }, { "epoch": 1.01, "learning_rate": 3.314324639682697e-05, "loss": 3.5495, "step": 1029632 }, { "epoch": 1.01, "learning_rate": 3.3134860449316444e-05, "loss": 3.5681, "step": 1030144 }, { "epoch": 1.01, "learning_rate": 3.3126474501805924e-05, "loss": 3.5557, "step": 1030656 }, { "epoch": 1.01, "learning_rate": 3.3118088554295404e-05, "loss": 3.5665, "step": 1031168 }, { "epoch": 1.01, "learning_rate": 3.3109702606784884e-05, "loss": 3.5516, "step": 1031680 }, { "epoch": 1.01, "learning_rate": 3.310131665927437e-05, "loss": 3.5529, "step": 1032192 }, { "epoch": 1.01, "learning_rate": 3.309294709056758e-05, "loss": 3.5639, "step": 1032704 }, { "epoch": 1.01, "learning_rate": 3.308456114305706e-05, "loss": 3.5568, "step": 1033216 }, { "epoch": 1.01, "learning_rate": 3.307617519554654e-05, "loss": 3.5591, "step": 1033728 }, { "epoch": 1.01, "learning_rate": 3.306778924803602e-05, "loss": 3.5625, "step": 1034240 }, { "epoch": 1.01, "learning_rate": 3.30594033005255e-05, "loss": 3.5538, "step": 1034752 }, { "epoch": 1.01, "learning_rate": 3.305101735301498e-05, "loss": 3.5452, "step": 1035264 }, { "epoch": 1.01, "learning_rate": 3.304263140550446e-05, "loss": 3.5533, "step": 1035776 }, { "epoch": 1.01, "learning_rate": 3.303424545799394e-05, "loss": 3.5626, "step": 1036288 }, { "epoch": 1.01, "learning_rate": 3.302587588928715e-05, "loss": 3.5526, "step": 1036800 }, { "epoch": 1.01, "learning_rate": 3.301748994177663e-05, "loss": 3.5549, "step": 1037312 }, { "epoch": 1.01, "learning_rate": 3.300910399426611e-05, "loss": 3.5513, "step": 1037824 }, { "epoch": 1.02, "learning_rate": 3.300071804675559e-05, "loss": 3.5538, "step": 1038336 }, { "epoch": 1.02, "learning_rate": 3.2992364856852533e-05, "loss": 3.5545, "step": 1038848 }, { "epoch": 1.02, "learning_rate": 3.298397890934201e-05, "loss": 3.5527, "step": 1039360 }, { "epoch": 1.02, "learning_rate": 3.297559296183149e-05, "loss": 3.5517, "step": 1039872 }, { "epoch": 1.02, "learning_rate": 3.296720701432097e-05, "loss": 3.5605, "step": 1040384 }, { "epoch": 1.02, "learning_rate": 3.295882106681045e-05, "loss": 3.5639, "step": 1040896 }, { "epoch": 1.02, "learning_rate": 3.295043511929993e-05, "loss": 3.5334, "step": 1041408 }, { "epoch": 1.02, "learning_rate": 3.294204917178941e-05, "loss": 3.5509, "step": 1041920 }, { "epoch": 1.02, "learning_rate": 3.293366322427889e-05, "loss": 3.5474, "step": 1042432 }, { "epoch": 1.02, "learning_rate": 3.29252936555721e-05, "loss": 3.5627, "step": 1042944 }, { "epoch": 1.02, "learning_rate": 3.291690770806158e-05, "loss": 3.5612, "step": 1043456 }, { "epoch": 1.02, "learning_rate": 3.290852176055106e-05, "loss": 3.5527, "step": 1043968 }, { "epoch": 1.02, "learning_rate": 3.290013581304054e-05, "loss": 3.5471, "step": 1044480 }, { "epoch": 1.02, "learning_rate": 3.289176624433376e-05, "loss": 3.5513, "step": 1044992 }, { "epoch": 1.02, "learning_rate": 3.288338029682324e-05, "loss": 3.5507, "step": 1045504 }, { "epoch": 1.02, "learning_rate": 3.287499434931272e-05, "loss": 3.5489, "step": 1046016 }, { "epoch": 1.02, "learning_rate": 3.28666084018022e-05, "loss": 3.5474, "step": 1046528 }, { "epoch": 1.02, "learning_rate": 3.285823883309541e-05, "loss": 3.5529, "step": 1047040 }, { "epoch": 1.02, "learning_rate": 3.284985288558489e-05, "loss": 3.5497, "step": 1047552 }, { "epoch": 1.02, "learning_rate": 3.284146693807437e-05, "loss": 3.5398, "step": 1048064 }, { "epoch": 1.02, "learning_rate": 3.2833097369367576e-05, "loss": 3.5468, "step": 1048576 }, { "epoch": 1.02, "learning_rate": 3.2824711421857056e-05, "loss": 3.5378, "step": 1049088 }, { "epoch": 1.02, "learning_rate": 3.2816325474346536e-05, "loss": 3.5578, "step": 1049600 }, { "epoch": 1.02, "learning_rate": 3.2807939526836016e-05, "loss": 3.5503, "step": 1050112 }, { "epoch": 1.02, "learning_rate": 3.2799569958129225e-05, "loss": 3.5501, "step": 1050624 }, { "epoch": 1.02, "learning_rate": 3.279118401061871e-05, "loss": 3.5555, "step": 1051136 }, { "epoch": 1.02, "learning_rate": 3.278279806310819e-05, "loss": 3.5551, "step": 1051648 }, { "epoch": 1.02, "learning_rate": 3.27744284944014e-05, "loss": 3.5501, "step": 1052160 }, { "epoch": 1.02, "learning_rate": 3.276604254689088e-05, "loss": 3.5494, "step": 1052672 }, { "epoch": 1.02, "learning_rate": 3.275765659938036e-05, "loss": 3.5591, "step": 1053184 }, { "epoch": 1.02, "learning_rate": 3.274927065186984e-05, "loss": 3.5439, "step": 1053696 }, { "epoch": 1.02, "learning_rate": 3.274088470435932e-05, "loss": 3.5421, "step": 1054208 }, { "epoch": 1.02, "learning_rate": 3.273251513565253e-05, "loss": 3.5516, "step": 1054720 }, { "epoch": 1.02, "learning_rate": 3.272412918814201e-05, "loss": 3.5529, "step": 1055232 }, { "epoch": 1.02, "learning_rate": 3.271574324063149e-05, "loss": 3.5527, "step": 1055744 }, { "epoch": 1.02, "learning_rate": 3.270735729312097e-05, "loss": 3.5476, "step": 1056256 }, { "epoch": 1.02, "learning_rate": 3.269897134561045e-05, "loss": 3.5504, "step": 1056768 }, { "epoch": 1.02, "learning_rate": 3.269058539809993e-05, "loss": 3.5492, "step": 1057280 }, { "epoch": 1.02, "learning_rate": 3.2682215829393145e-05, "loss": 3.5409, "step": 1057792 }, { "epoch": 1.02, "learning_rate": 3.2673829881882625e-05, "loss": 3.5446, "step": 1058304 }, { "epoch": 1.02, "learning_rate": 3.2665443934372105e-05, "loss": 3.5563, "step": 1058816 }, { "epoch": 1.02, "learning_rate": 3.265705798686158e-05, "loss": 3.5642, "step": 1059328 }, { "epoch": 1.02, "learning_rate": 3.264867203935106e-05, "loss": 3.5431, "step": 1059840 }, { "epoch": 1.02, "learning_rate": 3.2640302470644274e-05, "loss": 3.5483, "step": 1060352 }, { "epoch": 1.02, "learning_rate": 3.2631916523133754e-05, "loss": 3.5624, "step": 1060864 }, { "epoch": 1.02, "learning_rate": 3.262353057562323e-05, "loss": 3.5465, "step": 1061376 }, { "epoch": 1.02, "learning_rate": 3.261514462811271e-05, "loss": 3.5468, "step": 1061888 }, { "epoch": 1.02, "learning_rate": 3.260675868060219e-05, "loss": 3.5484, "step": 1062400 }, { "epoch": 1.02, "learning_rate": 3.259837273309167e-05, "loss": 3.5641, "step": 1062912 }, { "epoch": 1.02, "learning_rate": 3.258998678558115e-05, "loss": 3.5621, "step": 1063424 }, { "epoch": 1.02, "learning_rate": 3.2581600838070634e-05, "loss": 3.5518, "step": 1063936 }, { "epoch": 1.02, "learning_rate": 3.257323126936384e-05, "loss": 3.5432, "step": 1064448 }, { "epoch": 1.02, "learning_rate": 3.256484532185332e-05, "loss": 3.5538, "step": 1064960 }, { "epoch": 1.02, "learning_rate": 3.25564593743428e-05, "loss": 3.5558, "step": 1065472 }, { "epoch": 1.02, "learning_rate": 3.254807342683228e-05, "loss": 3.5423, "step": 1065984 }, { "epoch": 1.02, "learning_rate": 3.253970385812549e-05, "loss": 3.5675, "step": 1066496 }, { "epoch": 1.02, "learning_rate": 3.253131791061497e-05, "loss": 3.5453, "step": 1067008 }, { "epoch": 1.02, "learning_rate": 3.252294834190818e-05, "loss": 3.5584, "step": 1067520 }, { "epoch": 1.02, "learning_rate": 3.251456239439766e-05, "loss": 3.5503, "step": 1068032 }, { "epoch": 1.03, "eval_loss": 3.8963165283203125, "eval_runtime": 302.3395, "eval_samples_per_second": 1262.128, "eval_steps_per_second": 39.442, "step": 1068480 }, { "epoch": 0.0, "learning_rate": 3.250617644688714e-05, "loss": 3.5851, "step": 1068544 }, { "epoch": 0.0, "learning_rate": 3.249779049937662e-05, "loss": 3.5393, "step": 1069056 }, { "epoch": 0.0, "learning_rate": 3.24894045518661e-05, "loss": 3.5493, "step": 1069568 }, { "epoch": 0.0, "learning_rate": 3.248101860435559e-05, "loss": 3.561, "step": 1070080 }, { "epoch": 0.0, "learning_rate": 3.2472649035648797e-05, "loss": 3.553, "step": 1070592 }, { "epoch": 0.0, "learning_rate": 3.2464263088138277e-05, "loss": 3.5541, "step": 1071104 }, { "epoch": 0.0, "learning_rate": 3.2455877140627757e-05, "loss": 3.5487, "step": 1071616 }, { "epoch": 0.0, "learning_rate": 3.2447491193117236e-05, "loss": 3.5464, "step": 1072128 }, { "epoch": 0.0, "learning_rate": 3.2439121624410446e-05, "loss": 3.546, "step": 1072640 }, { "epoch": 0.0, "learning_rate": 3.2430735676899926e-05, "loss": 3.5513, "step": 1073152 }, { "epoch": 0.0, "learning_rate": 3.2422349729389405e-05, "loss": 3.5469, "step": 1073664 }, { "epoch": 0.0, "learning_rate": 3.2413963781878885e-05, "loss": 3.5529, "step": 1074176 }, { "epoch": 0.0, "learning_rate": 3.2405594213172095e-05, "loss": 3.5541, "step": 1074688 }, { "epoch": 0.0, "learning_rate": 3.2397208265661574e-05, "loss": 3.5358, "step": 1075200 }, { "epoch": 0.0, "learning_rate": 3.2388822318151054e-05, "loss": 3.5467, "step": 1075712 }, { "epoch": 0.0, "learning_rate": 3.238043637064054e-05, "loss": 3.5336, "step": 1076224 }, { "epoch": 0.0, "learning_rate": 3.237206680193375e-05, "loss": 3.5343, "step": 1076736 }, { "epoch": 0.0, "learning_rate": 3.236368085442323e-05, "loss": 3.5459, "step": 1077248 }, { "epoch": 0.0, "learning_rate": 3.235529490691271e-05, "loss": 3.5393, "step": 1077760 }, { "epoch": 0.0, "learning_rate": 3.234690895940219e-05, "loss": 3.552, "step": 1078272 }, { "epoch": 0.0, "learning_rate": 3.23385393906954e-05, "loss": 3.5612, "step": 1078784 }, { "epoch": 0.0, "learning_rate": 3.233015344318488e-05, "loss": 3.5415, "step": 1079296 }, { "epoch": 0.0, "learning_rate": 3.232176749567436e-05, "loss": 3.5481, "step": 1079808 }, { "epoch": 0.0, "learning_rate": 3.231338154816384e-05, "loss": 3.5484, "step": 1080320 }, { "epoch": 0.0, "learning_rate": 3.230501197945705e-05, "loss": 3.5354, "step": 1080832 }, { "epoch": 0.0, "learning_rate": 3.229662603194653e-05, "loss": 3.555, "step": 1081344 }, { "epoch": 0.0, "learning_rate": 3.228824008443601e-05, "loss": 3.5385, "step": 1081856 }, { "epoch": 0.0, "learning_rate": 3.227985413692549e-05, "loss": 3.5399, "step": 1082368 }, { "epoch": 0.0, "learning_rate": 3.2271484568218704e-05, "loss": 3.5381, "step": 1082880 }, { "epoch": 0.0, "learning_rate": 3.2263098620708184e-05, "loss": 3.5331, "step": 1083392 }, { "epoch": 0.01, "learning_rate": 3.2254712673197664e-05, "loss": 3.5406, "step": 1083904 }, { "epoch": 0.01, "learning_rate": 3.2246326725687144e-05, "loss": 3.5461, "step": 1084416 }, { "epoch": 0.01, "learning_rate": 3.2237940778176624e-05, "loss": 3.5522, "step": 1084928 }, { "epoch": 0.01, "learning_rate": 3.2229554830666104e-05, "loss": 3.5426, "step": 1085440 }, { "epoch": 0.01, "learning_rate": 3.2221168883155584e-05, "loss": 3.5375, "step": 1085952 }, { "epoch": 0.01, "learning_rate": 3.221278293564506e-05, "loss": 3.5441, "step": 1086464 }, { "epoch": 0.01, "learning_rate": 3.220441336693827e-05, "loss": 3.5615, "step": 1086976 }, { "epoch": 0.01, "learning_rate": 3.219602741942775e-05, "loss": 3.5371, "step": 1087488 }, { "epoch": 0.01, "learning_rate": 3.218764147191723e-05, "loss": 3.5367, "step": 1088000 }, { "epoch": 0.01, "learning_rate": 3.217925552440671e-05, "loss": 3.5398, "step": 1088512 }, { "epoch": 0.01, "learning_rate": 3.217088595569993e-05, "loss": 3.5355, "step": 1089024 }, { "epoch": 0.01, "learning_rate": 3.216251638699314e-05, "loss": 3.5431, "step": 1089536 }, { "epoch": 0.01, "learning_rate": 3.215413043948262e-05, "loss": 3.5487, "step": 1090048 }, { "epoch": 0.01, "learning_rate": 3.21457444919721e-05, "loss": 3.5526, "step": 1090560 }, { "epoch": 0.01, "learning_rate": 3.213735854446158e-05, "loss": 3.5432, "step": 1091072 }, { "epoch": 0.01, "learning_rate": 3.212897259695106e-05, "loss": 3.5418, "step": 1091584 }, { "epoch": 0.01, "learning_rate": 3.212058664944053e-05, "loss": 3.5409, "step": 1092096 }, { "epoch": 0.01, "learning_rate": 3.211220070193001e-05, "loss": 3.5487, "step": 1092608 }, { "epoch": 0.01, "learning_rate": 3.210381475441949e-05, "loss": 3.5189, "step": 1093120 }, { "epoch": 0.01, "learning_rate": 3.2095445185712706e-05, "loss": 3.5468, "step": 1093632 }, { "epoch": 0.01, "learning_rate": 3.2087075617005915e-05, "loss": 3.5448, "step": 1094144 }, { "epoch": 0.01, "learning_rate": 3.2078689669495395e-05, "loss": 3.5488, "step": 1094656 }, { "epoch": 0.01, "learning_rate": 3.207030372198488e-05, "loss": 3.54, "step": 1095168 }, { "epoch": 0.01, "learning_rate": 3.206191777447436e-05, "loss": 3.5332, "step": 1095680 }, { "epoch": 0.01, "learning_rate": 3.205354820576757e-05, "loss": 3.5405, "step": 1096192 }, { "epoch": 0.01, "learning_rate": 3.204516225825705e-05, "loss": 3.5317, "step": 1096704 }, { "epoch": 0.01, "learning_rate": 3.203677631074653e-05, "loss": 3.5539, "step": 1097216 }, { "epoch": 0.01, "learning_rate": 3.2028390363236004e-05, "loss": 3.5407, "step": 1097728 }, { "epoch": 0.01, "learning_rate": 3.2020004415725484e-05, "loss": 3.5573, "step": 1098240 }, { "epoch": 0.01, "learning_rate": 3.2011618468214964e-05, "loss": 3.5389, "step": 1098752 }, { "epoch": 0.01, "learning_rate": 3.2003232520704444e-05, "loss": 3.5244, "step": 1099264 }, { "epoch": 0.01, "learning_rate": 3.1994846573193924e-05, "loss": 3.5547, "step": 1099776 }, { "epoch": 0.01, "learning_rate": 3.198647700448713e-05, "loss": 3.5346, "step": 1100288 }, { "epoch": 0.01, "learning_rate": 3.197809105697662e-05, "loss": 3.5325, "step": 1100800 }, { "epoch": 0.01, "learning_rate": 3.19697051094661e-05, "loss": 3.5402, "step": 1101312 }, { "epoch": 0.01, "learning_rate": 3.196131916195558e-05, "loss": 3.5459, "step": 1101824 }, { "epoch": 0.01, "learning_rate": 3.195293321444506e-05, "loss": 3.527, "step": 1102336 }, { "epoch": 0.01, "learning_rate": 3.194454726693454e-05, "loss": 3.5342, "step": 1102848 }, { "epoch": 0.01, "learning_rate": 3.193616131942402e-05, "loss": 3.5332, "step": 1103360 }, { "epoch": 0.01, "learning_rate": 3.19277753719135e-05, "loss": 3.5302, "step": 1103872 }, { "epoch": 0.01, "learning_rate": 3.191940580320671e-05, "loss": 3.548, "step": 1104384 }, { "epoch": 0.01, "learning_rate": 3.191101985569619e-05, "loss": 3.5403, "step": 1104896 }, { "epoch": 0.01, "learning_rate": 3.190263390818567e-05, "loss": 3.5379, "step": 1105408 }, { "epoch": 0.01, "learning_rate": 3.189426433947888e-05, "loss": 3.536, "step": 1105920 }, { "epoch": 0.01, "learning_rate": 3.188587839196836e-05, "loss": 3.5503, "step": 1106432 }, { "epoch": 0.01, "learning_rate": 3.187749244445784e-05, "loss": 3.5356, "step": 1106944 }, { "epoch": 0.01, "learning_rate": 3.186910649694732e-05, "loss": 3.5471, "step": 1107456 }, { "epoch": 0.01, "learning_rate": 3.1860720549436804e-05, "loss": 3.5405, "step": 1107968 }, { "epoch": 0.01, "learning_rate": 3.1852334601926284e-05, "loss": 3.537, "step": 1108480 }, { "epoch": 0.01, "learning_rate": 3.1843965033219493e-05, "loss": 3.5462, "step": 1108992 }, { "epoch": 0.01, "learning_rate": 3.183557908570897e-05, "loss": 3.5409, "step": 1109504 }, { "epoch": 0.01, "learning_rate": 3.182719313819845e-05, "loss": 3.5434, "step": 1110016 }, { "epoch": 0.01, "learning_rate": 3.181880719068793e-05, "loss": 3.5452, "step": 1110528 }, { "epoch": 0.01, "learning_rate": 3.181042124317741e-05, "loss": 3.5432, "step": 1111040 }, { "epoch": 0.01, "learning_rate": 3.180203529566689e-05, "loss": 3.5253, "step": 1111552 }, { "epoch": 0.01, "learning_rate": 3.1793649348156366e-05, "loss": 3.5371, "step": 1112064 }, { "epoch": 0.01, "learning_rate": 3.1785263400645846e-05, "loss": 3.5479, "step": 1112576 }, { "epoch": 0.01, "learning_rate": 3.177689383193906e-05, "loss": 3.5367, "step": 1113088 }, { "epoch": 0.01, "learning_rate": 3.176850788442854e-05, "loss": 3.5377, "step": 1113600 }, { "epoch": 0.01, "learning_rate": 3.176012193691802e-05, "loss": 3.5357, "step": 1114112 }, { "epoch": 0.02, "learning_rate": 3.17517359894075e-05, "loss": 3.5373, "step": 1114624 }, { "epoch": 0.02, "learning_rate": 3.174338279950445e-05, "loss": 3.5359, "step": 1115136 }, { "epoch": 0.02, "learning_rate": 3.173499685199393e-05, "loss": 3.5388, "step": 1115648 }, { "epoch": 0.02, "learning_rate": 3.172661090448341e-05, "loss": 3.5392, "step": 1116160 }, { "epoch": 0.02, "learning_rate": 3.171822495697289e-05, "loss": 3.5412, "step": 1116672 }, { "epoch": 0.02, "learning_rate": 3.170983900946237e-05, "loss": 3.5499, "step": 1117184 }, { "epoch": 0.02, "learning_rate": 3.1701469440755576e-05, "loss": 3.5129, "step": 1117696 }, { "epoch": 0.02, "learning_rate": 3.1693083493245056e-05, "loss": 3.5389, "step": 1118208 }, { "epoch": 0.02, "learning_rate": 3.1684697545734536e-05, "loss": 3.5325, "step": 1118720 }, { "epoch": 0.02, "learning_rate": 3.1676311598224016e-05, "loss": 3.5464, "step": 1119232 }, { "epoch": 0.02, "learning_rate": 3.1667925650713496e-05, "loss": 3.5417, "step": 1119744 }, { "epoch": 0.02, "learning_rate": 3.1659539703202976e-05, "loss": 3.5374, "step": 1120256 }, { "epoch": 0.02, "learning_rate": 3.1651153755692456e-05, "loss": 3.5299, "step": 1120768 }, { "epoch": 0.02, "learning_rate": 3.1642767808181936e-05, "loss": 3.5387, "step": 1121280 }, { "epoch": 0.02, "learning_rate": 3.1634398239475145e-05, "loss": 3.5355, "step": 1121792 }, { "epoch": 0.02, "learning_rate": 3.1626012291964625e-05, "loss": 3.5296, "step": 1122304 }, { "epoch": 0.02, "learning_rate": 3.1617626344454105e-05, "loss": 3.5284, "step": 1122816 }, { "epoch": 0.02, "learning_rate": 3.1609240396943585e-05, "loss": 3.5339, "step": 1123328 }, { "epoch": 0.02, "learning_rate": 3.1600870828236794e-05, "loss": 3.5402, "step": 1123840 }, { "epoch": 0.02, "learning_rate": 3.1592484880726274e-05, "loss": 3.5204, "step": 1124352 }, { "epoch": 0.02, "learning_rate": 3.1584098933215754e-05, "loss": 3.5353, "step": 1124864 }, { "epoch": 0.02, "learning_rate": 3.1575712985705234e-05, "loss": 3.5222, "step": 1125376 }, { "epoch": 0.02, "learning_rate": 3.156734341699845e-05, "loss": 3.5432, "step": 1125888 }, { "epoch": 0.02, "learning_rate": 3.155895746948793e-05, "loss": 3.53, "step": 1126400 }, { "epoch": 0.02, "learning_rate": 3.155057152197741e-05, "loss": 3.5344, "step": 1126912 }, { "epoch": 0.02, "learning_rate": 3.154218557446689e-05, "loss": 3.5393, "step": 1127424 }, { "epoch": 0.02, "learning_rate": 3.15338160057601e-05, "loss": 3.5418, "step": 1127936 }, { "epoch": 0.02, "learning_rate": 3.1525446437053314e-05, "loss": 3.5345, "step": 1128448 }, { "epoch": 0.02, "learning_rate": 3.151706048954279e-05, "loss": 3.5353, "step": 1128960 }, { "epoch": 0.02, "learning_rate": 3.150867454203227e-05, "loss": 3.542, "step": 1129472 }, { "epoch": 0.02, "learning_rate": 3.150028859452175e-05, "loss": 3.5255, "step": 1129984 }, { "epoch": 0.02, "learning_rate": 3.149190264701123e-05, "loss": 3.5241, "step": 1130496 }, { "epoch": 0.02, "learning_rate": 3.1483533078304436e-05, "loss": 3.5359, "step": 1131008 }, { "epoch": 0.02, "learning_rate": 3.1475147130793916e-05, "loss": 3.5396, "step": 1131520 }, { "epoch": 0.02, "learning_rate": 3.1466761183283396e-05, "loss": 3.5385, "step": 1132032 }, { "epoch": 0.02, "learning_rate": 3.145837523577288e-05, "loss": 3.5311, "step": 1132544 }, { "epoch": 0.02, "learning_rate": 3.144998928826236e-05, "loss": 3.5347, "step": 1133056 }, { "epoch": 0.02, "learning_rate": 3.144160334075184e-05, "loss": 3.5336, "step": 1133568 }, { "epoch": 0.02, "learning_rate": 3.143323377204505e-05, "loss": 3.525, "step": 1134080 }, { "epoch": 0.02, "learning_rate": 3.142484782453453e-05, "loss": 3.5254, "step": 1134592 }, { "epoch": 0.02, "learning_rate": 3.141646187702401e-05, "loss": 3.5432, "step": 1135104 }, { "epoch": 0.02, "learning_rate": 3.140807592951349e-05, "loss": 3.5463, "step": 1135616 }, { "epoch": 0.02, "learning_rate": 3.139968998200297e-05, "loss": 3.5318, "step": 1136128 }, { "epoch": 0.02, "learning_rate": 3.139132041329618e-05, "loss": 3.5325, "step": 1136640 }, { "epoch": 0.02, "learning_rate": 3.138293446578566e-05, "loss": 3.54, "step": 1137152 }, { "epoch": 0.02, "learning_rate": 3.137454851827514e-05, "loss": 3.5309, "step": 1137664 }, { "epoch": 0.02, "learning_rate": 3.136616257076462e-05, "loss": 3.5291, "step": 1138176 }, { "epoch": 0.02, "learning_rate": 3.13577766232541e-05, "loss": 3.5368, "step": 1138688 }, { "epoch": 0.02, "learning_rate": 3.134939067574358e-05, "loss": 3.5455, "step": 1139200 }, { "epoch": 0.02, "learning_rate": 3.134100472823307e-05, "loss": 3.543, "step": 1139712 }, { "epoch": 0.02, "learning_rate": 3.133263515952628e-05, "loss": 3.5368, "step": 1140224 }, { "epoch": 0.02, "learning_rate": 3.1324249212015757e-05, "loss": 3.5291, "step": 1140736 }, { "epoch": 0.02, "learning_rate": 3.1315863264505237e-05, "loss": 3.538, "step": 1141248 }, { "epoch": 0.02, "learning_rate": 3.1307477316994717e-05, "loss": 3.5407, "step": 1141760 }, { "epoch": 0.02, "learning_rate": 3.1299091369484196e-05, "loss": 3.5275, "step": 1142272 }, { "epoch": 0.02, "learning_rate": 3.1290705421973676e-05, "loss": 3.5514, "step": 1142784 }, { "epoch": 0.02, "learning_rate": 3.128231947446315e-05, "loss": 3.5309, "step": 1143296 }, { "epoch": 0.02, "learning_rate": 3.127393352695263e-05, "loss": 3.5399, "step": 1143808 }, { "epoch": 0.02, "learning_rate": 3.1265563958245845e-05, "loss": 3.5299, "step": 1144320 }, { "epoch": 0.03, "eval_loss": 3.8979759216308594, "eval_runtime": 301.9173, "eval_samples_per_second": 1263.892, "eval_steps_per_second": 39.498, "step": 1144800 }, { "epoch": 1.0, "learning_rate": 3.1257178010735325e-05, "loss": 3.5372, "step": 1144832 }, { "epoch": 1.0, "learning_rate": 3.1248792063224805e-05, "loss": 3.5262, "step": 1145344 }, { "epoch": 1.0, "learning_rate": 3.1240406115714285e-05, "loss": 3.5336, "step": 1145856 }, { "epoch": 1.0, "learning_rate": 3.12320365470075e-05, "loss": 3.5428, "step": 1146368 }, { "epoch": 1.0, "learning_rate": 3.1223650599496974e-05, "loss": 3.539, "step": 1146880 }, { "epoch": 1.0, "learning_rate": 3.1215264651986454e-05, "loss": 3.5397, "step": 1147392 }, { "epoch": 1.0, "learning_rate": 3.120689508327967e-05, "loss": 3.5287, "step": 1147904 }, { "epoch": 1.0, "learning_rate": 3.119850913576915e-05, "loss": 3.5329, "step": 1148416 }, { "epoch": 1.0, "learning_rate": 3.119012318825862e-05, "loss": 3.5331, "step": 1148928 }, { "epoch": 1.0, "learning_rate": 3.11817372407481e-05, "loss": 3.5382, "step": 1149440 }, { "epoch": 1.0, "learning_rate": 3.117336767204132e-05, "loss": 3.5298, "step": 1149952 }, { "epoch": 1.0, "learning_rate": 3.11649817245308e-05, "loss": 3.5327, "step": 1150464 }, { "epoch": 1.0, "learning_rate": 3.115659577702027e-05, "loss": 3.5395, "step": 1150976 }, { "epoch": 1.0, "learning_rate": 3.114820982950976e-05, "loss": 3.522, "step": 1151488 }, { "epoch": 1.0, "learning_rate": 3.1139840260802975e-05, "loss": 3.5292, "step": 1152000 }, { "epoch": 1.0, "learning_rate": 3.113145431329245e-05, "loss": 3.5159, "step": 1152512 }, { "epoch": 1.0, "learning_rate": 3.112306836578193e-05, "loss": 3.5211, "step": 1153024 }, { "epoch": 1.0, "learning_rate": 3.111468241827141e-05, "loss": 3.5297, "step": 1153536 }, { "epoch": 1.0, "learning_rate": 3.1106312849564624e-05, "loss": 3.5223, "step": 1154048 }, { "epoch": 1.0, "learning_rate": 3.10979269020541e-05, "loss": 3.5327, "step": 1154560 }, { "epoch": 1.0, "learning_rate": 3.108954095454358e-05, "loss": 3.5451, "step": 1155072 }, { "epoch": 1.0, "learning_rate": 3.108115500703306e-05, "loss": 3.5265, "step": 1155584 }, { "epoch": 1.0, "learning_rate": 3.1072785438326266e-05, "loss": 3.5293, "step": 1156096 }, { "epoch": 1.0, "learning_rate": 3.1064399490815746e-05, "loss": 3.535, "step": 1156608 }, { "epoch": 1.0, "learning_rate": 3.1056013543305226e-05, "loss": 3.5257, "step": 1157120 }, { "epoch": 1.0, "learning_rate": 3.104762759579471e-05, "loss": 3.534, "step": 1157632 }, { "epoch": 1.0, "learning_rate": 3.103925802708792e-05, "loss": 3.5206, "step": 1158144 }, { "epoch": 1.0, "learning_rate": 3.10308720795774e-05, "loss": 3.5297, "step": 1158656 }, { "epoch": 1.0, "learning_rate": 3.102250251087062e-05, "loss": 3.5256, "step": 1159168 }, { "epoch": 1.0, "learning_rate": 3.10141165633601e-05, "loss": 3.515, "step": 1159680 }, { "epoch": 1.01, "learning_rate": 3.100573061584957e-05, "loss": 3.5321, "step": 1160192 }, { "epoch": 1.01, "learning_rate": 3.099734466833905e-05, "loss": 3.5237, "step": 1160704 }, { "epoch": 1.01, "learning_rate": 3.098895872082853e-05, "loss": 3.5336, "step": 1161216 }, { "epoch": 1.01, "learning_rate": 3.098057277331801e-05, "loss": 3.5316, "step": 1161728 }, { "epoch": 1.01, "learning_rate": 3.097218682580749e-05, "loss": 3.5227, "step": 1162240 }, { "epoch": 1.01, "learning_rate": 3.096380087829697e-05, "loss": 3.5273, "step": 1162752 }, { "epoch": 1.01, "learning_rate": 3.095543130959018e-05, "loss": 3.5454, "step": 1163264 }, { "epoch": 1.01, "learning_rate": 3.0947045362079666e-05, "loss": 3.5213, "step": 1163776 }, { "epoch": 1.01, "learning_rate": 3.0938659414569146e-05, "loss": 3.523, "step": 1164288 }, { "epoch": 1.01, "learning_rate": 3.0930273467058626e-05, "loss": 3.5263, "step": 1164800 }, { "epoch": 1.01, "learning_rate": 3.0921903898351835e-05, "loss": 3.5218, "step": 1165312 }, { "epoch": 1.01, "learning_rate": 3.0913534329645044e-05, "loss": 3.5228, "step": 1165824 }, { "epoch": 1.01, "learning_rate": 3.0905148382134524e-05, "loss": 3.5429, "step": 1166336 }, { "epoch": 1.01, "learning_rate": 3.0896762434624004e-05, "loss": 3.5337, "step": 1166848 }, { "epoch": 1.01, "learning_rate": 3.0888376487113484e-05, "loss": 3.5289, "step": 1167360 }, { "epoch": 1.01, "learning_rate": 3.0879990539602964e-05, "loss": 3.5313, "step": 1167872 }, { "epoch": 1.01, "learning_rate": 3.0871604592092444e-05, "loss": 3.5228, "step": 1168384 }, { "epoch": 1.01, "learning_rate": 3.0863218644581924e-05, "loss": 3.5344, "step": 1168896 }, { "epoch": 1.01, "learning_rate": 3.0854832697071404e-05, "loss": 3.5052, "step": 1169408 }, { "epoch": 1.01, "learning_rate": 3.084646312836461e-05, "loss": 3.5297, "step": 1169920 }, { "epoch": 1.01, "learning_rate": 3.083809355965783e-05, "loss": 3.5313, "step": 1170432 }, { "epoch": 1.01, "learning_rate": 3.082970761214731e-05, "loss": 3.5337, "step": 1170944 }, { "epoch": 1.01, "learning_rate": 3.082132166463679e-05, "loss": 3.5252, "step": 1171456 }, { "epoch": 1.01, "learning_rate": 3.081293571712627e-05, "loss": 3.5166, "step": 1171968 }, { "epoch": 1.01, "learning_rate": 3.080456614841948e-05, "loss": 3.5268, "step": 1172480 }, { "epoch": 1.01, "learning_rate": 3.079618020090896e-05, "loss": 3.5168, "step": 1172992 }, { "epoch": 1.01, "learning_rate": 3.078779425339844e-05, "loss": 3.543, "step": 1173504 }, { "epoch": 1.01, "learning_rate": 3.077940830588792e-05, "loss": 3.5236, "step": 1174016 }, { "epoch": 1.01, "learning_rate": 3.07710223583774e-05, "loss": 3.5428, "step": 1174528 }, { "epoch": 1.01, "learning_rate": 3.076263641086688e-05, "loss": 3.5244, "step": 1175040 }, { "epoch": 1.01, "learning_rate": 3.075425046335636e-05, "loss": 3.5162, "step": 1175552 }, { "epoch": 1.01, "learning_rate": 3.074586451584584e-05, "loss": 3.5343, "step": 1176064 }, { "epoch": 1.01, "learning_rate": 3.0737494947139054e-05, "loss": 3.5177, "step": 1176576 }, { "epoch": 1.01, "learning_rate": 3.0729108999628534e-05, "loss": 3.5232, "step": 1177088 }, { "epoch": 1.01, "learning_rate": 3.0720723052118014e-05, "loss": 3.5209, "step": 1177600 }, { "epoch": 1.01, "learning_rate": 3.0712337104607493e-05, "loss": 3.5323, "step": 1178112 }, { "epoch": 1.01, "learning_rate": 3.0703951157096973e-05, "loss": 3.514, "step": 1178624 }, { "epoch": 1.01, "learning_rate": 3.0695565209586453e-05, "loss": 3.5196, "step": 1179136 }, { "epoch": 1.01, "learning_rate": 3.068717926207593e-05, "loss": 3.5176, "step": 1179648 }, { "epoch": 1.01, "learning_rate": 3.0678793314565407e-05, "loss": 3.5151, "step": 1180160 }, { "epoch": 1.01, "learning_rate": 3.067044012466235e-05, "loss": 3.5326, "step": 1180672 }, { "epoch": 1.01, "learning_rate": 3.066205417715183e-05, "loss": 3.5295, "step": 1181184 }, { "epoch": 1.01, "learning_rate": 3.065366822964131e-05, "loss": 3.5209, "step": 1181696 }, { "epoch": 1.01, "learning_rate": 3.064528228213079e-05, "loss": 3.5228, "step": 1182208 }, { "epoch": 1.01, "learning_rate": 3.063689633462027e-05, "loss": 3.5342, "step": 1182720 }, { "epoch": 1.01, "learning_rate": 3.062851038710975e-05, "loss": 3.5231, "step": 1183232 }, { "epoch": 1.01, "learning_rate": 3.062012443959923e-05, "loss": 3.5312, "step": 1183744 }, { "epoch": 1.01, "learning_rate": 3.061175487089245e-05, "loss": 3.5263, "step": 1184256 }, { "epoch": 1.01, "learning_rate": 3.060336892338193e-05, "loss": 3.5231, "step": 1184768 }, { "epoch": 1.01, "learning_rate": 3.059498297587141e-05, "loss": 3.5311, "step": 1185280 }, { "epoch": 1.01, "learning_rate": 3.058659702836088e-05, "loss": 3.5253, "step": 1185792 }, { "epoch": 1.01, "learning_rate": 3.057821108085036e-05, "loss": 3.5257, "step": 1186304 }, { "epoch": 1.01, "learning_rate": 3.056982513333984e-05, "loss": 3.5336, "step": 1186816 }, { "epoch": 1.01, "learning_rate": 3.056143918582932e-05, "loss": 3.5231, "step": 1187328 }, { "epoch": 1.01, "learning_rate": 3.05530532383188e-05, "loss": 3.5077, "step": 1187840 }, { "epoch": 1.01, "learning_rate": 3.054468366961201e-05, "loss": 3.5233, "step": 1188352 }, { "epoch": 1.01, "learning_rate": 3.053629772210149e-05, "loss": 3.5303, "step": 1188864 }, { "epoch": 1.01, "learning_rate": 3.0527911774590976e-05, "loss": 3.5252, "step": 1189376 }, { "epoch": 1.01, "learning_rate": 3.0519542205884185e-05, "loss": 3.5233, "step": 1189888 }, { "epoch": 1.01, "learning_rate": 3.051115625837366e-05, "loss": 3.5183, "step": 1190400 }, { "epoch": 1.02, "learning_rate": 3.0502770310863145e-05, "loss": 3.5261, "step": 1190912 }, { "epoch": 1.02, "learning_rate": 3.0494400742156354e-05, "loss": 3.5219, "step": 1191424 }, { "epoch": 1.02, "learning_rate": 3.0486014794645834e-05, "loss": 3.5202, "step": 1191936 }, { "epoch": 1.02, "learning_rate": 3.0477628847135314e-05, "loss": 3.5258, "step": 1192448 }, { "epoch": 1.02, "learning_rate": 3.0469242899624794e-05, "loss": 3.5237, "step": 1192960 }, { "epoch": 1.02, "learning_rate": 3.0460856952114274e-05, "loss": 3.5367, "step": 1193472 }, { "epoch": 1.02, "learning_rate": 3.0452487383407486e-05, "loss": 3.5058, "step": 1193984 }, { "epoch": 1.02, "learning_rate": 3.0444101435896966e-05, "loss": 3.5187, "step": 1194496 }, { "epoch": 1.02, "learning_rate": 3.0435715488386446e-05, "loss": 3.5234, "step": 1195008 }, { "epoch": 1.02, "learning_rate": 3.0427329540875926e-05, "loss": 3.5253, "step": 1195520 }, { "epoch": 1.02, "learning_rate": 3.0418943593365406e-05, "loss": 3.5276, "step": 1196032 }, { "epoch": 1.02, "learning_rate": 3.0410557645854886e-05, "loss": 3.5279, "step": 1196544 }, { "epoch": 1.02, "learning_rate": 3.0402171698344366e-05, "loss": 3.5123, "step": 1197056 }, { "epoch": 1.02, "learning_rate": 3.0393785750833846e-05, "loss": 3.5225, "step": 1197568 }, { "epoch": 1.02, "learning_rate": 3.038541618212706e-05, "loss": 3.52, "step": 1198080 }, { "epoch": 1.02, "learning_rate": 3.037703023461654e-05, "loss": 3.5145, "step": 1198592 }, { "epoch": 1.02, "learning_rate": 3.036864428710602e-05, "loss": 3.5135, "step": 1199104 }, { "epoch": 1.02, "learning_rate": 3.03602583395955e-05, "loss": 3.5228, "step": 1199616 }, { "epoch": 1.02, "learning_rate": 3.0351888770888707e-05, "loss": 3.5275, "step": 1200128 }, { "epoch": 1.02, "learning_rate": 3.034350282337819e-05, "loss": 3.5053, "step": 1200640 }, { "epoch": 1.02, "learning_rate": 3.033511687586767e-05, "loss": 3.5154, "step": 1201152 }, { "epoch": 1.02, "learning_rate": 3.032673092835715e-05, "loss": 3.5092, "step": 1201664 }, { "epoch": 1.02, "learning_rate": 3.031836135965036e-05, "loss": 3.5263, "step": 1202176 }, { "epoch": 1.02, "learning_rate": 3.030997541213984e-05, "loss": 3.5172, "step": 1202688 }, { "epoch": 1.02, "learning_rate": 3.030158946462932e-05, "loss": 3.518, "step": 1203200 }, { "epoch": 1.02, "learning_rate": 3.02932035171188e-05, "loss": 3.5232, "step": 1203712 }, { "epoch": 1.02, "learning_rate": 3.0284833948412012e-05, "loss": 3.5276, "step": 1204224 }, { "epoch": 1.02, "learning_rate": 3.027646437970522e-05, "loss": 3.5197, "step": 1204736 }, { "epoch": 1.02, "learning_rate": 3.02680784321947e-05, "loss": 3.5237, "step": 1205248 }, { "epoch": 1.02, "learning_rate": 3.025969248468418e-05, "loss": 3.5262, "step": 1205760 }, { "epoch": 1.02, "learning_rate": 3.025130653717366e-05, "loss": 3.513, "step": 1206272 }, { "epoch": 1.02, "learning_rate": 3.0242920589663144e-05, "loss": 3.5081, "step": 1206784 }, { "epoch": 1.02, "learning_rate": 3.0234551020956354e-05, "loss": 3.521, "step": 1207296 }, { "epoch": 1.02, "learning_rate": 3.0226165073445833e-05, "loss": 3.5189, "step": 1207808 }, { "epoch": 1.02, "learning_rate": 3.0217779125935313e-05, "loss": 3.5296, "step": 1208320 }, { "epoch": 1.02, "learning_rate": 3.0209393178424793e-05, "loss": 3.514, "step": 1208832 }, { "epoch": 1.02, "learning_rate": 3.0201007230914273e-05, "loss": 3.5173, "step": 1209344 }, { "epoch": 1.02, "learning_rate": 3.0192621283403753e-05, "loss": 3.5158, "step": 1209856 }, { "epoch": 1.02, "learning_rate": 3.0184251714696966e-05, "loss": 3.5123, "step": 1210368 }, { "epoch": 1.02, "learning_rate": 3.0175865767186446e-05, "loss": 3.5095, "step": 1210880 }, { "epoch": 1.02, "learning_rate": 3.0167479819675926e-05, "loss": 3.527, "step": 1211392 }, { "epoch": 1.02, "learning_rate": 3.0159093872165406e-05, "loss": 3.5309, "step": 1211904 }, { "epoch": 1.02, "learning_rate": 3.0150707924654886e-05, "loss": 3.5209, "step": 1212416 }, { "epoch": 1.02, "learning_rate": 3.0142338355948098e-05, "loss": 3.5142, "step": 1212928 }, { "epoch": 1.02, "learning_rate": 3.0133952408437578e-05, "loss": 3.5256, "step": 1213440 }, { "epoch": 1.02, "learning_rate": 3.0125566460927058e-05, "loss": 3.519, "step": 1213952 }, { "epoch": 1.02, "learning_rate": 3.0117180513416538e-05, "loss": 3.5152, "step": 1214464 }, { "epoch": 1.02, "learning_rate": 3.010879456590601e-05, "loss": 3.5207, "step": 1214976 }, { "epoch": 1.02, "learning_rate": 3.010040861839549e-05, "loss": 3.5306, "step": 1215488 }, { "epoch": 1.02, "learning_rate": 3.0092022670884974e-05, "loss": 3.5244, "step": 1216000 }, { "epoch": 1.02, "learning_rate": 3.0083653102178184e-05, "loss": 3.5213, "step": 1216512 }, { "epoch": 1.02, "learning_rate": 3.0075267154667663e-05, "loss": 3.516, "step": 1217024 }, { "epoch": 1.02, "learning_rate": 3.0066881207157143e-05, "loss": 3.5238, "step": 1217536 }, { "epoch": 1.02, "learning_rate": 3.0058495259646623e-05, "loss": 3.5226, "step": 1218048 }, { "epoch": 1.02, "learning_rate": 3.0050109312136103e-05, "loss": 3.511, "step": 1218560 }, { "epoch": 1.02, "learning_rate": 3.0041723364625583e-05, "loss": 3.5399, "step": 1219072 }, { "epoch": 1.02, "learning_rate": 3.0033337417115067e-05, "loss": 3.5172, "step": 1219584 }, { "epoch": 1.02, "learning_rate": 3.0024967848408276e-05, "loss": 3.5254, "step": 1220096 }, { "epoch": 1.02, "learning_rate": 3.0016581900897756e-05, "loss": 3.521, "step": 1220608 }, { "epoch": 1.03, "learning_rate": 3.0008195953387236e-05, "loss": 3.5172, "step": 1221120 }, { "epoch": 1.03, "eval_loss": 3.8992996215820312, "eval_runtime": 301.7941, "eval_samples_per_second": 1264.408, "eval_steps_per_second": 39.514, "step": 1221120 }, { "epoch": 0.0, "learning_rate": 2.9999810005876716e-05, "loss": 3.514, "step": 1221632 }, { "epoch": 0.0, "learning_rate": 2.9991424058366196e-05, "loss": 3.5167, "step": 1222144 }, { "epoch": 0.0, "learning_rate": 2.9983038110855676e-05, "loss": 3.5299, "step": 1222656 }, { "epoch": 0.0, "learning_rate": 2.9974668542148888e-05, "loss": 3.5211, "step": 1223168 }, { "epoch": 0.0, "learning_rate": 2.9966282594638368e-05, "loss": 3.5258, "step": 1223680 }, { "epoch": 0.0, "learning_rate": 2.9957896647127848e-05, "loss": 3.5129, "step": 1224192 }, { "epoch": 0.0, "learning_rate": 2.9949510699617328e-05, "loss": 3.5197, "step": 1224704 }, { "epoch": 0.0, "learning_rate": 2.9941141130910537e-05, "loss": 3.5156, "step": 1225216 }, { "epoch": 0.0, "learning_rate": 2.9932755183400017e-05, "loss": 3.5234, "step": 1225728 }, { "epoch": 0.0, "learning_rate": 2.99243692358895e-05, "loss": 3.5129, "step": 1226240 }, { "epoch": 0.0, "learning_rate": 2.991598328837898e-05, "loss": 3.5241, "step": 1226752 }, { "epoch": 0.0, "learning_rate": 2.990761371967219e-05, "loss": 3.524, "step": 1227264 }, { "epoch": 0.0, "learning_rate": 2.989922777216167e-05, "loss": 3.5084, "step": 1227776 }, { "epoch": 0.0, "learning_rate": 2.989084182465115e-05, "loss": 3.5121, "step": 1228288 }, { "epoch": 0.0, "learning_rate": 2.988245587714063e-05, "loss": 3.5036, "step": 1228800 }, { "epoch": 0.0, "learning_rate": 2.987408630843384e-05, "loss": 3.5059, "step": 1229312 }, { "epoch": 0.0, "learning_rate": 2.986570036092332e-05, "loss": 3.5146, "step": 1229824 }, { "epoch": 0.0, "learning_rate": 2.98573144134128e-05, "loss": 3.5093, "step": 1230336 }, { "epoch": 0.0, "learning_rate": 2.984892846590228e-05, "loss": 3.5163, "step": 1230848 }, { "epoch": 0.0, "learning_rate": 2.9840575275999223e-05, "loss": 3.5325, "step": 1231360 }, { "epoch": 0.0, "learning_rate": 2.9832189328488703e-05, "loss": 3.5124, "step": 1231872 }, { "epoch": 0.0, "learning_rate": 2.9823803380978183e-05, "loss": 3.5173, "step": 1232384 }, { "epoch": 0.0, "learning_rate": 2.9815417433467663e-05, "loss": 3.5168, "step": 1232896 }, { "epoch": 0.0, "learning_rate": 2.9807031485957143e-05, "loss": 3.5122, "step": 1233408 }, { "epoch": 0.0, "learning_rate": 2.9798645538446623e-05, "loss": 3.5192, "step": 1233920 }, { "epoch": 0.0, "learning_rate": 2.9790259590936103e-05, "loss": 3.5069, "step": 1234432 }, { "epoch": 0.0, "learning_rate": 2.9781873643425583e-05, "loss": 3.5126, "step": 1234944 }, { "epoch": 0.0, "learning_rate": 2.9773504074718795e-05, "loss": 3.5128, "step": 1235456 }, { "epoch": 0.0, "learning_rate": 2.9765118127208275e-05, "loss": 3.5, "step": 1235968 }, { "epoch": 0.01, "learning_rate": 2.9756732179697755e-05, "loss": 3.5153, "step": 1236480 }, { "epoch": 0.01, "learning_rate": 2.9748346232187235e-05, "loss": 3.5115, "step": 1236992 }, { "epoch": 0.01, "learning_rate": 2.9739976663480444e-05, "loss": 3.5209, "step": 1237504 }, { "epoch": 0.01, "learning_rate": 2.9731590715969924e-05, "loss": 3.5135, "step": 1238016 }, { "epoch": 0.01, "learning_rate": 2.9723204768459408e-05, "loss": 3.5096, "step": 1238528 }, { "epoch": 0.01, "learning_rate": 2.9714818820948888e-05, "loss": 3.513, "step": 1239040 }, { "epoch": 0.01, "learning_rate": 2.9706432873438368e-05, "loss": 3.5315, "step": 1239552 }, { "epoch": 0.01, "learning_rate": 2.969804692592784e-05, "loss": 3.5057, "step": 1240064 }, { "epoch": 0.01, "learning_rate": 2.968966097841732e-05, "loss": 3.5105, "step": 1240576 }, { "epoch": 0.01, "learning_rate": 2.96812750309068e-05, "loss": 3.5128, "step": 1241088 }, { "epoch": 0.01, "learning_rate": 2.9672905462200016e-05, "loss": 3.5021, "step": 1241600 }, { "epoch": 0.01, "learning_rate": 2.966453589349323e-05, "loss": 3.5111, "step": 1242112 }, { "epoch": 0.01, "learning_rate": 2.965614994598271e-05, "loss": 3.5271, "step": 1242624 }, { "epoch": 0.01, "learning_rate": 2.964776399847219e-05, "loss": 3.5207, "step": 1243136 }, { "epoch": 0.01, "learning_rate": 2.963937805096167e-05, "loss": 3.51, "step": 1243648 }, { "epoch": 0.01, "learning_rate": 2.9630992103451145e-05, "loss": 3.5179, "step": 1244160 }, { "epoch": 0.01, "learning_rate": 2.9622606155940625e-05, "loss": 3.5118, "step": 1244672 }, { "epoch": 0.01, "learning_rate": 2.9614220208430105e-05, "loss": 3.5193, "step": 1245184 }, { "epoch": 0.01, "learning_rate": 2.9605834260919585e-05, "loss": 3.4936, "step": 1245696 }, { "epoch": 0.01, "learning_rate": 2.9597464692212794e-05, "loss": 3.5116, "step": 1246208 }, { "epoch": 0.01, "learning_rate": 2.958909512350601e-05, "loss": 3.5191, "step": 1246720 }, { "epoch": 0.01, "learning_rate": 2.958070917599549e-05, "loss": 3.517, "step": 1247232 }, { "epoch": 0.01, "learning_rate": 2.9572323228484967e-05, "loss": 3.5127, "step": 1247744 }, { "epoch": 0.01, "learning_rate": 2.9563937280974447e-05, "loss": 3.5009, "step": 1248256 }, { "epoch": 0.01, "learning_rate": 2.9555567712267663e-05, "loss": 3.5146, "step": 1248768 }, { "epoch": 0.01, "learning_rate": 2.9547181764757143e-05, "loss": 3.4993, "step": 1249280 }, { "epoch": 0.01, "learning_rate": 2.9538795817246616e-05, "loss": 3.5276, "step": 1249792 }, { "epoch": 0.01, "learning_rate": 2.95304098697361e-05, "loss": 3.5078, "step": 1250304 }, { "epoch": 0.01, "learning_rate": 2.952202392222558e-05, "loss": 3.5254, "step": 1250816 }, { "epoch": 0.01, "learning_rate": 2.951363797471506e-05, "loss": 3.509, "step": 1251328 }, { "epoch": 0.01, "learning_rate": 2.950525202720454e-05, "loss": 3.5033, "step": 1251840 }, { "epoch": 0.01, "learning_rate": 2.949686607969402e-05, "loss": 3.5165, "step": 1252352 }, { "epoch": 0.01, "learning_rate": 2.9488496510987228e-05, "loss": 3.5078, "step": 1252864 }, { "epoch": 0.01, "learning_rate": 2.9480110563476708e-05, "loss": 3.5107, "step": 1253376 }, { "epoch": 0.01, "learning_rate": 2.947172461596619e-05, "loss": 3.5025, "step": 1253888 }, { "epoch": 0.01, "learning_rate": 2.946333866845567e-05, "loss": 3.518, "step": 1254400 }, { "epoch": 0.01, "learning_rate": 2.945495272094515e-05, "loss": 3.5022, "step": 1254912 }, { "epoch": 0.01, "learning_rate": 2.944656677343463e-05, "loss": 3.5042, "step": 1255424 }, { "epoch": 0.01, "learning_rate": 2.943818082592411e-05, "loss": 3.4998, "step": 1255936 }, { "epoch": 0.01, "learning_rate": 2.942979487841359e-05, "loss": 3.5018, "step": 1256448 }, { "epoch": 0.01, "learning_rate": 2.9421441688510533e-05, "loss": 3.5185, "step": 1256960 }, { "epoch": 0.01, "learning_rate": 2.9413055741000013e-05, "loss": 3.5153, "step": 1257472 }, { "epoch": 0.01, "learning_rate": 2.9404669793489493e-05, "loss": 3.505, "step": 1257984 }, { "epoch": 0.01, "learning_rate": 2.9396283845978973e-05, "loss": 3.5082, "step": 1258496 }, { "epoch": 0.01, "learning_rate": 2.9387897898468453e-05, "loss": 3.5168, "step": 1259008 }, { "epoch": 0.01, "learning_rate": 2.9379511950957932e-05, "loss": 3.5132, "step": 1259520 }, { "epoch": 0.01, "learning_rate": 2.9371126003447412e-05, "loss": 3.5113, "step": 1260032 }, { "epoch": 0.01, "learning_rate": 2.9362756434740625e-05, "loss": 3.5139, "step": 1260544 }, { "epoch": 0.01, "learning_rate": 2.9354370487230105e-05, "loss": 3.5097, "step": 1261056 }, { "epoch": 0.01, "learning_rate": 2.9345984539719585e-05, "loss": 3.5165, "step": 1261568 }, { "epoch": 0.01, "learning_rate": 2.9337598592209065e-05, "loss": 3.5098, "step": 1262080 }, { "epoch": 0.01, "learning_rate": 2.9329212644698545e-05, "loss": 3.5149, "step": 1262592 }, { "epoch": 0.01, "learning_rate": 2.9320843075991754e-05, "loss": 3.5194, "step": 1263104 }, { "epoch": 0.01, "learning_rate": 2.9312457128481237e-05, "loss": 3.5093, "step": 1263616 }, { "epoch": 0.01, "learning_rate": 2.9304071180970717e-05, "loss": 3.4952, "step": 1264128 }, { "epoch": 0.01, "learning_rate": 2.9295685233460197e-05, "loss": 3.5089, "step": 1264640 }, { "epoch": 0.01, "learning_rate": 2.9287299285949677e-05, "loss": 3.5158, "step": 1265152 }, { "epoch": 0.01, "learning_rate": 2.927891333843915e-05, "loss": 3.5126, "step": 1265664 }, { "epoch": 0.01, "learning_rate": 2.927052739092863e-05, "loss": 3.5115, "step": 1266176 }, { "epoch": 0.01, "learning_rate": 2.926214144341811e-05, "loss": 3.5037, "step": 1266688 }, { "epoch": 0.02, "learning_rate": 2.9253771874711326e-05, "loss": 3.5126, "step": 1267200 }, { "epoch": 0.02, "learning_rate": 2.924540230600454e-05, "loss": 3.5047, "step": 1267712 }, { "epoch": 0.02, "learning_rate": 2.923701635849402e-05, "loss": 3.5074, "step": 1268224 }, { "epoch": 0.02, "learning_rate": 2.92286304109835e-05, "loss": 3.5067, "step": 1268736 }, { "epoch": 0.02, "learning_rate": 2.9220244463472975e-05, "loss": 3.5059, "step": 1269248 }, { "epoch": 0.02, "learning_rate": 2.9211858515962455e-05, "loss": 3.5248, "step": 1269760 }, { "epoch": 0.02, "learning_rate": 2.9203472568451935e-05, "loss": 3.4932, "step": 1270272 }, { "epoch": 0.02, "learning_rate": 2.919510299974515e-05, "loss": 3.497, "step": 1270784 }, { "epoch": 0.02, "learning_rate": 2.9186717052234624e-05, "loss": 3.5145, "step": 1271296 }, { "epoch": 0.02, "learning_rate": 2.9178331104724104e-05, "loss": 3.5135, "step": 1271808 }, { "epoch": 0.02, "learning_rate": 2.9169945157213584e-05, "loss": 3.5126, "step": 1272320 }, { "epoch": 0.02, "learning_rate": 2.9161559209703064e-05, "loss": 3.5098, "step": 1272832 }, { "epoch": 0.02, "learning_rate": 2.9153173262192547e-05, "loss": 3.4969, "step": 1273344 }, { "epoch": 0.02, "learning_rate": 2.9144787314682027e-05, "loss": 3.5042, "step": 1273856 }, { "epoch": 0.02, "learning_rate": 2.9136417745975236e-05, "loss": 3.5121, "step": 1274368 }, { "epoch": 0.02, "learning_rate": 2.9128031798464716e-05, "loss": 3.4983, "step": 1274880 }, { "epoch": 0.02, "learning_rate": 2.9119645850954196e-05, "loss": 3.4981, "step": 1275392 }, { "epoch": 0.02, "learning_rate": 2.9111259903443676e-05, "loss": 3.5111, "step": 1275904 }, { "epoch": 0.02, "learning_rate": 2.910289033473689e-05, "loss": 3.5126, "step": 1276416 }, { "epoch": 0.02, "learning_rate": 2.909450438722637e-05, "loss": 3.4925, "step": 1276928 }, { "epoch": 0.02, "learning_rate": 2.908611843971585e-05, "loss": 3.4997, "step": 1277440 }, { "epoch": 0.02, "learning_rate": 2.907773249220533e-05, "loss": 3.4979, "step": 1277952 }, { "epoch": 0.02, "learning_rate": 2.9069362923498538e-05, "loss": 3.5125, "step": 1278464 }, { "epoch": 0.02, "learning_rate": 2.9060976975988017e-05, "loss": 3.5033, "step": 1278976 }, { "epoch": 0.02, "learning_rate": 2.90525910284775e-05, "loss": 3.506, "step": 1279488 }, { "epoch": 0.02, "learning_rate": 2.904420508096698e-05, "loss": 3.5061, "step": 1280000 }, { "epoch": 0.02, "learning_rate": 2.903583551226019e-05, "loss": 3.5131, "step": 1280512 }, { "epoch": 0.02, "learning_rate": 2.90274659435534e-05, "loss": 3.5008, "step": 1281024 }, { "epoch": 0.02, "learning_rate": 2.901907999604288e-05, "loss": 3.511, "step": 1281536 }, { "epoch": 0.02, "learning_rate": 2.9010694048532362e-05, "loss": 3.5103, "step": 1282048 }, { "epoch": 0.02, "learning_rate": 2.9002308101021842e-05, "loss": 3.5025, "step": 1282560 }, { "epoch": 0.02, "learning_rate": 2.8993922153511322e-05, "loss": 3.4907, "step": 1283072 }, { "epoch": 0.02, "learning_rate": 2.898555258480453e-05, "loss": 3.5058, "step": 1283584 }, { "epoch": 0.02, "learning_rate": 2.897716663729401e-05, "loss": 3.507, "step": 1284096 }, { "epoch": 0.02, "learning_rate": 2.896878068978349e-05, "loss": 3.5111, "step": 1284608 }, { "epoch": 0.02, "learning_rate": 2.896039474227297e-05, "loss": 3.498, "step": 1285120 }, { "epoch": 0.02, "learning_rate": 2.8952025173566184e-05, "loss": 3.5075, "step": 1285632 }, { "epoch": 0.02, "learning_rate": 2.8943639226055664e-05, "loss": 3.5028, "step": 1286144 }, { "epoch": 0.02, "learning_rate": 2.8935253278545144e-05, "loss": 3.5001, "step": 1286656 }, { "epoch": 0.02, "learning_rate": 2.8926867331034623e-05, "loss": 3.491, "step": 1287168 }, { "epoch": 0.02, "learning_rate": 2.8918481383524103e-05, "loss": 3.5165, "step": 1287680 }, { "epoch": 0.02, "learning_rate": 2.8910095436013583e-05, "loss": 3.5177, "step": 1288192 }, { "epoch": 0.02, "learning_rate": 2.8901709488503063e-05, "loss": 3.5054, "step": 1288704 }, { "epoch": 0.02, "learning_rate": 2.8893339919796276e-05, "loss": 3.4975, "step": 1289216 }, { "epoch": 0.02, "learning_rate": 2.8884953972285756e-05, "loss": 3.5165, "step": 1289728 }, { "epoch": 0.02, "learning_rate": 2.8876568024775236e-05, "loss": 3.5023, "step": 1290240 }, { "epoch": 0.02, "learning_rate": 2.8868182077264716e-05, "loss": 3.5033, "step": 1290752 }, { "epoch": 0.02, "learning_rate": 2.8859796129754196e-05, "loss": 3.5061, "step": 1291264 }, { "epoch": 0.02, "learning_rate": 2.8851410182243676e-05, "loss": 3.5145, "step": 1291776 }, { "epoch": 0.02, "learning_rate": 2.8843024234733156e-05, "loss": 3.5076, "step": 1292288 }, { "epoch": 0.02, "learning_rate": 2.883463828722264e-05, "loss": 3.5113, "step": 1292800 }, { "epoch": 0.02, "learning_rate": 2.8826268718515848e-05, "loss": 3.4981, "step": 1293312 }, { "epoch": 0.02, "learning_rate": 2.8817882771005328e-05, "loss": 3.5117, "step": 1293824 }, { "epoch": 0.02, "learning_rate": 2.8809496823494808e-05, "loss": 3.5078, "step": 1294336 }, { "epoch": 0.02, "learning_rate": 2.8801110875984284e-05, "loss": 3.5015, "step": 1294848 }, { "epoch": 0.02, "learning_rate": 2.87927413072775e-05, "loss": 3.5239, "step": 1295360 }, { "epoch": 0.02, "learning_rate": 2.878435535976698e-05, "loss": 3.5012, "step": 1295872 }, { "epoch": 0.02, "learning_rate": 2.877598579106019e-05, "loss": 3.5095, "step": 1296384 }, { "epoch": 0.02, "learning_rate": 2.876759984354967e-05, "loss": 3.5083, "step": 1296896 }, { "epoch": 0.02, "learning_rate": 2.875921389603915e-05, "loss": 3.5033, "step": 1297408 }, { "epoch": 0.03, "eval_loss": 3.9013924598693848, "eval_runtime": 303.538, "eval_samples_per_second": 1257.144, "eval_steps_per_second": 39.287, "step": 1297440 }, { "epoch": 1.0, "learning_rate": 2.875082794852863e-05, "loss": 3.4961, "step": 1297920 }, { "epoch": 1.0, "learning_rate": 2.874244200101811e-05, "loss": 3.5053, "step": 1298432 }, { "epoch": 1.0, "learning_rate": 2.8734072432311322e-05, "loss": 3.5139, "step": 1298944 }, { "epoch": 1.0, "learning_rate": 2.87256864848008e-05, "loss": 3.5087, "step": 1299456 }, { "epoch": 1.0, "learning_rate": 2.871730053729028e-05, "loss": 3.5143, "step": 1299968 }, { "epoch": 1.0, "learning_rate": 2.8708914589779755e-05, "loss": 3.4982, "step": 1300480 }, { "epoch": 1.0, "learning_rate": 2.8700528642269238e-05, "loss": 3.5028, "step": 1300992 }, { "epoch": 1.0, "learning_rate": 2.8692142694758718e-05, "loss": 3.5016, "step": 1301504 }, { "epoch": 1.0, "learning_rate": 2.8683756747248198e-05, "loss": 3.5109, "step": 1302016 }, { "epoch": 1.0, "learning_rate": 2.8675370799737678e-05, "loss": 3.5007, "step": 1302528 }, { "epoch": 1.0, "learning_rate": 2.8667001231030887e-05, "loss": 3.5107, "step": 1303040 }, { "epoch": 1.0, "learning_rate": 2.8658615283520367e-05, "loss": 3.5116, "step": 1303552 }, { "epoch": 1.0, "learning_rate": 2.8650229336009847e-05, "loss": 3.4949, "step": 1304064 }, { "epoch": 1.0, "learning_rate": 2.864184338849933e-05, "loss": 3.4997, "step": 1304576 }, { "epoch": 1.0, "learning_rate": 2.863347381979254e-05, "loss": 3.491, "step": 1305088 }, { "epoch": 1.0, "learning_rate": 2.862508787228202e-05, "loss": 3.4956, "step": 1305600 }, { "epoch": 1.0, "learning_rate": 2.86167019247715e-05, "loss": 3.4971, "step": 1306112 }, { "epoch": 1.0, "learning_rate": 2.860833235606471e-05, "loss": 3.4974, "step": 1306624 }, { "epoch": 1.0, "learning_rate": 2.8599946408554192e-05, "loss": 3.5017, "step": 1307136 }, { "epoch": 1.0, "learning_rate": 2.8591560461043672e-05, "loss": 3.5196, "step": 1307648 }, { "epoch": 1.0, "learning_rate": 2.8583174513533152e-05, "loss": 3.5001, "step": 1308160 }, { "epoch": 1.0, "learning_rate": 2.857478856602263e-05, "loss": 3.4999, "step": 1308672 }, { "epoch": 1.0, "learning_rate": 2.856640261851211e-05, "loss": 3.5077, "step": 1309184 }, { "epoch": 1.0, "learning_rate": 2.855801667100159e-05, "loss": 3.5014, "step": 1309696 }, { "epoch": 1.0, "learning_rate": 2.854963072349107e-05, "loss": 3.5012, "step": 1310208 }, { "epoch": 1.0, "learning_rate": 2.854126115478428e-05, "loss": 3.4937, "step": 1310720 }, { "epoch": 1.0, "learning_rate": 2.8532875207273764e-05, "loss": 3.4991, "step": 1311232 }, { "epoch": 1.0, "learning_rate": 2.8524505638566973e-05, "loss": 3.4965, "step": 1311744 }, { "epoch": 1.0, "learning_rate": 2.8516119691056453e-05, "loss": 3.4836, "step": 1312256 }, { "epoch": 1.01, "learning_rate": 2.8507733743545933e-05, "loss": 3.5033, "step": 1312768 }, { "epoch": 1.01, "learning_rate": 2.8499347796035413e-05, "loss": 3.4942, "step": 1313280 }, { "epoch": 1.01, "learning_rate": 2.8490961848524893e-05, "loss": 3.5068, "step": 1313792 }, { "epoch": 1.01, "learning_rate": 2.8482575901014373e-05, "loss": 3.5024, "step": 1314304 }, { "epoch": 1.01, "learning_rate": 2.8474189953503856e-05, "loss": 3.4897, "step": 1314816 }, { "epoch": 1.01, "learning_rate": 2.8465804005993336e-05, "loss": 3.5042, "step": 1315328 }, { "epoch": 1.01, "learning_rate": 2.8457434437286545e-05, "loss": 3.513, "step": 1315840 }, { "epoch": 1.01, "learning_rate": 2.8449048489776025e-05, "loss": 3.4906, "step": 1316352 }, { "epoch": 1.01, "learning_rate": 2.8440662542265505e-05, "loss": 3.5005, "step": 1316864 }, { "epoch": 1.01, "learning_rate": 2.8432276594754985e-05, "loss": 3.4964, "step": 1317376 }, { "epoch": 1.01, "learning_rate": 2.8423907026048198e-05, "loss": 3.4898, "step": 1317888 }, { "epoch": 1.01, "learning_rate": 2.8415537457341407e-05, "loss": 3.4992, "step": 1318400 }, { "epoch": 1.01, "learning_rate": 2.8407151509830887e-05, "loss": 3.5122, "step": 1318912 }, { "epoch": 1.01, "learning_rate": 2.8398765562320367e-05, "loss": 3.5045, "step": 1319424 }, { "epoch": 1.01, "learning_rate": 2.8390379614809847e-05, "loss": 3.5001, "step": 1319936 }, { "epoch": 1.01, "learning_rate": 2.8381993667299327e-05, "loss": 3.5076, "step": 1320448 }, { "epoch": 1.01, "learning_rate": 2.837360771978881e-05, "loss": 3.4962, "step": 1320960 }, { "epoch": 1.01, "learning_rate": 2.836522177227829e-05, "loss": 3.5042, "step": 1321472 }, { "epoch": 1.01, "learning_rate": 2.835683582476777e-05, "loss": 3.4803, "step": 1321984 }, { "epoch": 1.01, "learning_rate": 2.834846625606098e-05, "loss": 3.4952, "step": 1322496 }, { "epoch": 1.01, "learning_rate": 2.8340096687354188e-05, "loss": 3.5054, "step": 1323008 }, { "epoch": 1.01, "learning_rate": 2.833171073984367e-05, "loss": 3.5061, "step": 1323520 }, { "epoch": 1.01, "learning_rate": 2.832332479233315e-05, "loss": 3.4954, "step": 1324032 }, { "epoch": 1.01, "learning_rate": 2.831493884482263e-05, "loss": 3.488, "step": 1324544 }, { "epoch": 1.01, "learning_rate": 2.830656927611584e-05, "loss": 3.5035, "step": 1325056 }, { "epoch": 1.01, "learning_rate": 2.829818332860532e-05, "loss": 3.4848, "step": 1325568 }, { "epoch": 1.01, "learning_rate": 2.82897973810948e-05, "loss": 3.5104, "step": 1326080 }, { "epoch": 1.01, "learning_rate": 2.828141143358428e-05, "loss": 3.4989, "step": 1326592 }, { "epoch": 1.01, "learning_rate": 2.8273025486073764e-05, "loss": 3.5115, "step": 1327104 }, { "epoch": 1.01, "learning_rate": 2.8264639538563243e-05, "loss": 3.496, "step": 1327616 }, { "epoch": 1.01, "learning_rate": 2.8256253591052717e-05, "loss": 3.491, "step": 1328128 }, { "epoch": 1.01, "learning_rate": 2.8247867643542197e-05, "loss": 3.4968, "step": 1328640 }, { "epoch": 1.01, "learning_rate": 2.8239498074835413e-05, "loss": 3.5012, "step": 1329152 }, { "epoch": 1.01, "learning_rate": 2.823111212732489e-05, "loss": 3.4897, "step": 1329664 }, { "epoch": 1.01, "learning_rate": 2.822272617981437e-05, "loss": 3.4883, "step": 1330176 }, { "epoch": 1.01, "learning_rate": 2.821434023230385e-05, "loss": 3.5042, "step": 1330688 }, { "epoch": 1.01, "learning_rate": 2.820595428479333e-05, "loss": 3.4924, "step": 1331200 }, { "epoch": 1.01, "learning_rate": 2.819756833728281e-05, "loss": 3.4844, "step": 1331712 }, { "epoch": 1.01, "learning_rate": 2.818918238977229e-05, "loss": 3.4871, "step": 1332224 }, { "epoch": 1.01, "learning_rate": 2.818079644226177e-05, "loss": 3.4883, "step": 1332736 }, { "epoch": 1.01, "learning_rate": 2.8172443252358717e-05, "loss": 3.5033, "step": 1333248 }, { "epoch": 1.01, "learning_rate": 2.816405730484819e-05, "loss": 3.5037, "step": 1333760 }, { "epoch": 1.01, "learning_rate": 2.815567135733767e-05, "loss": 3.4925, "step": 1334272 }, { "epoch": 1.01, "learning_rate": 2.814728540982715e-05, "loss": 3.4946, "step": 1334784 }, { "epoch": 1.01, "learning_rate": 2.813889946231663e-05, "loss": 3.5026, "step": 1335296 }, { "epoch": 1.01, "learning_rate": 2.813051351480611e-05, "loss": 3.4973, "step": 1335808 }, { "epoch": 1.01, "learning_rate": 2.8122127567295594e-05, "loss": 3.4967, "step": 1336320 }, { "epoch": 1.01, "learning_rate": 2.8113757998588803e-05, "loss": 3.5037, "step": 1336832 }, { "epoch": 1.01, "learning_rate": 2.8105372051078283e-05, "loss": 3.4971, "step": 1337344 }, { "epoch": 1.01, "learning_rate": 2.8096986103567763e-05, "loss": 3.5041, "step": 1337856 }, { "epoch": 1.01, "learning_rate": 2.8088600156057243e-05, "loss": 3.4956, "step": 1338368 }, { "epoch": 1.01, "learning_rate": 2.8080214208546722e-05, "loss": 3.5005, "step": 1338880 }, { "epoch": 1.01, "learning_rate": 2.8071844639839935e-05, "loss": 3.4998, "step": 1339392 }, { "epoch": 1.01, "learning_rate": 2.8063458692329415e-05, "loss": 3.4986, "step": 1339904 }, { "epoch": 1.01, "learning_rate": 2.8055072744818895e-05, "loss": 3.4843, "step": 1340416 }, { "epoch": 1.01, "learning_rate": 2.8046686797308375e-05, "loss": 3.4932, "step": 1340928 }, { "epoch": 1.01, "learning_rate": 2.8038300849797855e-05, "loss": 3.499, "step": 1341440 }, { "epoch": 1.01, "learning_rate": 2.8029914902287335e-05, "loss": 3.4987, "step": 1341952 }, { "epoch": 1.01, "learning_rate": 2.8021545333580547e-05, "loss": 3.4964, "step": 1342464 }, { "epoch": 1.01, "learning_rate": 2.8013159386070027e-05, "loss": 3.4877, "step": 1342976 }, { "epoch": 1.02, "learning_rate": 2.8004773438559507e-05, "loss": 3.4957, "step": 1343488 }, { "epoch": 1.02, "learning_rate": 2.7996387491048987e-05, "loss": 3.4916, "step": 1344000 }, { "epoch": 1.02, "learning_rate": 2.7988001543538467e-05, "loss": 3.4975, "step": 1344512 }, { "epoch": 1.02, "learning_rate": 2.7979631974831676e-05, "loss": 3.4872, "step": 1345024 }, { "epoch": 1.02, "learning_rate": 2.7971246027321156e-05, "loss": 3.4953, "step": 1345536 }, { "epoch": 1.02, "learning_rate": 2.7962860079810636e-05, "loss": 3.5059, "step": 1346048 }, { "epoch": 1.02, "learning_rate": 2.795447413230012e-05, "loss": 3.4939, "step": 1346560 }, { "epoch": 1.02, "learning_rate": 2.794610456359333e-05, "loss": 3.4789, "step": 1347072 }, { "epoch": 1.02, "learning_rate": 2.793771861608281e-05, "loss": 3.4976, "step": 1347584 }, { "epoch": 1.02, "learning_rate": 2.792933266857229e-05, "loss": 3.4993, "step": 1348096 }, { "epoch": 1.02, "learning_rate": 2.792094672106177e-05, "loss": 3.4984, "step": 1348608 }, { "epoch": 1.02, "learning_rate": 2.791256077355125e-05, "loss": 3.4975, "step": 1349120 }, { "epoch": 1.02, "learning_rate": 2.7904174826040725e-05, "loss": 3.486, "step": 1349632 }, { "epoch": 1.02, "learning_rate": 2.7895788878530205e-05, "loss": 3.4865, "step": 1350144 }, { "epoch": 1.02, "learning_rate": 2.788741930982342e-05, "loss": 3.5017, "step": 1350656 }, { "epoch": 1.02, "learning_rate": 2.78790333623129e-05, "loss": 3.4831, "step": 1351168 }, { "epoch": 1.02, "learning_rate": 2.7870647414802374e-05, "loss": 3.4878, "step": 1351680 }, { "epoch": 1.02, "learning_rate": 2.7862261467291857e-05, "loss": 3.4965, "step": 1352192 }, { "epoch": 1.02, "learning_rate": 2.7853891898585073e-05, "loss": 3.4994, "step": 1352704 }, { "epoch": 1.02, "learning_rate": 2.7845505951074546e-05, "loss": 3.4729, "step": 1353216 }, { "epoch": 1.02, "learning_rate": 2.7837120003564026e-05, "loss": 3.4907, "step": 1353728 }, { "epoch": 1.02, "learning_rate": 2.7828734056053506e-05, "loss": 3.4788, "step": 1354240 }, { "epoch": 1.02, "learning_rate": 2.7820364487346722e-05, "loss": 3.4992, "step": 1354752 }, { "epoch": 1.02, "learning_rate": 2.78119785398362e-05, "loss": 3.4888, "step": 1355264 }, { "epoch": 1.02, "learning_rate": 2.780359259232568e-05, "loss": 3.4843, "step": 1355776 }, { "epoch": 1.02, "learning_rate": 2.779520664481516e-05, "loss": 3.5007, "step": 1356288 }, { "epoch": 1.02, "learning_rate": 2.7786837076108374e-05, "loss": 3.4973, "step": 1356800 }, { "epoch": 1.02, "learning_rate": 2.7778467507401583e-05, "loss": 3.4872, "step": 1357312 }, { "epoch": 1.02, "learning_rate": 2.7770081559891063e-05, "loss": 3.4991, "step": 1357824 }, { "epoch": 1.02, "learning_rate": 2.7761695612380543e-05, "loss": 3.4948, "step": 1358336 }, { "epoch": 1.02, "learning_rate": 2.775330966487002e-05, "loss": 3.4905, "step": 1358848 }, { "epoch": 1.02, "learning_rate": 2.77449237173595e-05, "loss": 3.4754, "step": 1359360 }, { "epoch": 1.02, "learning_rate": 2.7736554148652716e-05, "loss": 3.4972, "step": 1359872 }, { "epoch": 1.02, "learning_rate": 2.7728168201142196e-05, "loss": 3.4899, "step": 1360384 }, { "epoch": 1.02, "learning_rate": 2.7719782253631672e-05, "loss": 3.4971, "step": 1360896 }, { "epoch": 1.02, "learning_rate": 2.7711396306121152e-05, "loss": 3.4871, "step": 1361408 }, { "epoch": 1.02, "learning_rate": 2.7703026737414368e-05, "loss": 3.4921, "step": 1361920 }, { "epoch": 1.02, "learning_rate": 2.7694640789903848e-05, "loss": 3.4908, "step": 1362432 }, { "epoch": 1.02, "learning_rate": 2.768625484239332e-05, "loss": 3.4852, "step": 1362944 }, { "epoch": 1.02, "learning_rate": 2.76778688948828e-05, "loss": 3.4758, "step": 1363456 }, { "epoch": 1.02, "learning_rate": 2.766948294737228e-05, "loss": 3.5033, "step": 1363968 }, { "epoch": 1.02, "learning_rate": 2.7661096999861765e-05, "loss": 3.5002, "step": 1364480 }, { "epoch": 1.02, "learning_rate": 2.7652711052351244e-05, "loss": 3.4933, "step": 1364992 }, { "epoch": 1.02, "learning_rate": 2.7644341483644454e-05, "loss": 3.4882, "step": 1365504 }, { "epoch": 1.02, "learning_rate": 2.7635955536133934e-05, "loss": 3.4991, "step": 1366016 }, { "epoch": 1.02, "learning_rate": 2.7627569588623413e-05, "loss": 3.494, "step": 1366528 }, { "epoch": 1.02, "learning_rate": 2.7619183641112893e-05, "loss": 3.4883, "step": 1367040 }, { "epoch": 1.02, "learning_rate": 2.7610814072406106e-05, "loss": 3.4903, "step": 1367552 }, { "epoch": 1.02, "learning_rate": 2.7602428124895586e-05, "loss": 3.4997, "step": 1368064 }, { "epoch": 1.02, "learning_rate": 2.7594042177385066e-05, "loss": 3.4935, "step": 1368576 }, { "epoch": 1.02, "learning_rate": 2.7585656229874546e-05, "loss": 3.5056, "step": 1369088 }, { "epoch": 1.02, "learning_rate": 2.7577270282364026e-05, "loss": 3.4841, "step": 1369600 }, { "epoch": 1.02, "learning_rate": 2.7568884334853506e-05, "loss": 3.4953, "step": 1370112 }, { "epoch": 1.02, "learning_rate": 2.7560498387342986e-05, "loss": 3.4951, "step": 1370624 }, { "epoch": 1.02, "learning_rate": 2.7552112439832466e-05, "loss": 3.4875, "step": 1371136 }, { "epoch": 1.02, "learning_rate": 2.7543742871125678e-05, "loss": 3.5091, "step": 1371648 }, { "epoch": 1.02, "learning_rate": 2.7535356923615158e-05, "loss": 3.4911, "step": 1372160 }, { "epoch": 1.02, "learning_rate": 2.7526987354908367e-05, "loss": 3.496, "step": 1372672 }, { "epoch": 1.02, "learning_rate": 2.7518601407397847e-05, "loss": 3.4886, "step": 1373184 }, { "epoch": 1.02, "learning_rate": 2.7510215459887327e-05, "loss": 3.4932, "step": 1373696 }, { "epoch": 1.03, "eval_loss": 3.902557373046875, "eval_runtime": 303.1946, "eval_samples_per_second": 1258.568, "eval_steps_per_second": 39.331, "step": 1373760 }, { "epoch": 0.0, "learning_rate": 2.750182951237681e-05, "loss": 3.4817, "step": 1374208 }, { "epoch": 0.0, "learning_rate": 2.749344356486629e-05, "loss": 3.4927, "step": 1374720 }, { "epoch": 0.0, "learning_rate": 2.748505761735577e-05, "loss": 3.4984, "step": 1375232 }, { "epoch": 0.0, "learning_rate": 2.747667166984525e-05, "loss": 3.4933, "step": 1375744 }, { "epoch": 0.0, "learning_rate": 2.746830210113846e-05, "loss": 3.5044, "step": 1376256 }, { "epoch": 0.0, "learning_rate": 2.7459932532431672e-05, "loss": 3.4798, "step": 1376768 }, { "epoch": 0.0, "learning_rate": 2.7451546584921152e-05, "loss": 3.4905, "step": 1377280 }, { "epoch": 0.0, "learning_rate": 2.7443160637410632e-05, "loss": 3.4886, "step": 1377792 }, { "epoch": 0.0, "learning_rate": 2.7434774689900112e-05, "loss": 3.4958, "step": 1378304 }, { "epoch": 0.0, "learning_rate": 2.742638874238959e-05, "loss": 3.4876, "step": 1378816 }, { "epoch": 0.0, "learning_rate": 2.741800279487907e-05, "loss": 3.495, "step": 1379328 }, { "epoch": 0.0, "learning_rate": 2.740961684736855e-05, "loss": 3.4967, "step": 1379840 }, { "epoch": 0.0, "learning_rate": 2.740123089985803e-05, "loss": 3.4815, "step": 1380352 }, { "epoch": 0.0, "learning_rate": 2.7392861331151244e-05, "loss": 3.4874, "step": 1380864 }, { "epoch": 0.0, "learning_rate": 2.7384475383640724e-05, "loss": 3.475, "step": 1381376 }, { "epoch": 0.0, "learning_rate": 2.7376089436130204e-05, "loss": 3.4814, "step": 1381888 }, { "epoch": 0.0, "learning_rate": 2.7367703488619677e-05, "loss": 3.4844, "step": 1382400 }, { "epoch": 0.0, "learning_rate": 2.7359333919912893e-05, "loss": 3.4853, "step": 1382912 }, { "epoch": 0.0, "learning_rate": 2.7350947972402373e-05, "loss": 3.4857, "step": 1383424 }, { "epoch": 0.0, "learning_rate": 2.7342562024891853e-05, "loss": 3.5048, "step": 1383936 }, { "epoch": 0.0, "learning_rate": 2.733417607738133e-05, "loss": 3.4854, "step": 1384448 }, { "epoch": 0.0, "learning_rate": 2.7325806508674545e-05, "loss": 3.486, "step": 1384960 }, { "epoch": 0.0, "learning_rate": 2.7317420561164025e-05, "loss": 3.4934, "step": 1385472 }, { "epoch": 0.0, "learning_rate": 2.7309034613653505e-05, "loss": 3.493, "step": 1385984 }, { "epoch": 0.0, "learning_rate": 2.7300648666142982e-05, "loss": 3.485, "step": 1386496 }, { "epoch": 0.0, "learning_rate": 2.7292262718632462e-05, "loss": 3.48, "step": 1387008 }, { "epoch": 0.0, "learning_rate": 2.7283876771121942e-05, "loss": 3.489, "step": 1387520 }, { "epoch": 0.0, "learning_rate": 2.727550720241515e-05, "loss": 3.4788, "step": 1388032 }, { "epoch": 0.0, "learning_rate": 2.726712125490463e-05, "loss": 3.4728, "step": 1388544 }, { "epoch": 0.01, "learning_rate": 2.725873530739411e-05, "loss": 3.4907, "step": 1389056 }, { "epoch": 0.01, "learning_rate": 2.7250349359883594e-05, "loss": 3.4827, "step": 1389568 }, { "epoch": 0.01, "learning_rate": 2.7241963412373074e-05, "loss": 3.4919, "step": 1390080 }, { "epoch": 0.01, "learning_rate": 2.7233577464862554e-05, "loss": 3.4881, "step": 1390592 }, { "epoch": 0.01, "learning_rate": 2.7225191517352034e-05, "loss": 3.4783, "step": 1391104 }, { "epoch": 0.01, "learning_rate": 2.7216805569841514e-05, "loss": 3.4898, "step": 1391616 }, { "epoch": 0.01, "learning_rate": 2.7208436001134723e-05, "loss": 3.5024, "step": 1392128 }, { "epoch": 0.01, "learning_rate": 2.7200050053624203e-05, "loss": 3.4737, "step": 1392640 }, { "epoch": 0.01, "learning_rate": 2.7191664106113683e-05, "loss": 3.4894, "step": 1393152 }, { "epoch": 0.01, "learning_rate": 2.7183278158603166e-05, "loss": 3.4808, "step": 1393664 }, { "epoch": 0.01, "learning_rate": 2.7174908589896375e-05, "loss": 3.4813, "step": 1394176 }, { "epoch": 0.01, "learning_rate": 2.7166539021189584e-05, "loss": 3.4827, "step": 1394688 }, { "epoch": 0.01, "learning_rate": 2.7158153073679064e-05, "loss": 3.4999, "step": 1395200 }, { "epoch": 0.01, "learning_rate": 2.7149767126168544e-05, "loss": 3.4913, "step": 1395712 }, { "epoch": 0.01, "learning_rate": 2.7141381178658028e-05, "loss": 3.4874, "step": 1396224 }, { "epoch": 0.01, "learning_rate": 2.7133011609951237e-05, "loss": 3.4918, "step": 1396736 }, { "epoch": 0.01, "learning_rate": 2.7124625662440717e-05, "loss": 3.4796, "step": 1397248 }, { "epoch": 0.01, "learning_rate": 2.7116239714930197e-05, "loss": 3.4931, "step": 1397760 }, { "epoch": 0.01, "learning_rate": 2.7107853767419677e-05, "loss": 3.4723, "step": 1398272 }, { "epoch": 0.01, "learning_rate": 2.7099467819909157e-05, "loss": 3.4813, "step": 1398784 }, { "epoch": 0.01, "learning_rate": 2.709109825120237e-05, "loss": 3.4909, "step": 1399296 }, { "epoch": 0.01, "learning_rate": 2.708271230369185e-05, "loss": 3.489, "step": 1399808 }, { "epoch": 0.01, "learning_rate": 2.707432635618133e-05, "loss": 3.4824, "step": 1400320 }, { "epoch": 0.01, "learning_rate": 2.706594040867081e-05, "loss": 3.478, "step": 1400832 }, { "epoch": 0.01, "learning_rate": 2.7057570839964018e-05, "loss": 3.4886, "step": 1401344 }, { "epoch": 0.01, "learning_rate": 2.7049184892453498e-05, "loss": 3.471, "step": 1401856 }, { "epoch": 0.01, "learning_rate": 2.704079894494298e-05, "loss": 3.4938, "step": 1402368 }, { "epoch": 0.01, "learning_rate": 2.703241299743246e-05, "loss": 3.4859, "step": 1402880 }, { "epoch": 0.01, "learning_rate": 2.702402704992194e-05, "loss": 3.4951, "step": 1403392 }, { "epoch": 0.01, "learning_rate": 2.701564110241142e-05, "loss": 3.4875, "step": 1403904 }, { "epoch": 0.01, "learning_rate": 2.70072551549009e-05, "loss": 3.477, "step": 1404416 }, { "epoch": 0.01, "learning_rate": 2.699886920739038e-05, "loss": 3.4839, "step": 1404928 }, { "epoch": 0.01, "learning_rate": 2.699049963868359e-05, "loss": 3.4879, "step": 1405440 }, { "epoch": 0.01, "learning_rate": 2.6982113691173074e-05, "loss": 3.4749, "step": 1405952 }, { "epoch": 0.01, "learning_rate": 2.6973727743662554e-05, "loss": 3.4783, "step": 1406464 }, { "epoch": 0.01, "learning_rate": 2.6965341796152033e-05, "loss": 3.4882, "step": 1406976 }, { "epoch": 0.01, "learning_rate": 2.6956955848641513e-05, "loss": 3.4841, "step": 1407488 }, { "epoch": 0.01, "learning_rate": 2.6948586279934723e-05, "loss": 3.4689, "step": 1408000 }, { "epoch": 0.01, "learning_rate": 2.6940200332424203e-05, "loss": 3.4769, "step": 1408512 }, { "epoch": 0.01, "learning_rate": 2.6931814384913682e-05, "loss": 3.4756, "step": 1409024 }, { "epoch": 0.01, "learning_rate": 2.6923428437403166e-05, "loss": 3.4894, "step": 1409536 }, { "epoch": 0.01, "learning_rate": 2.691504248989264e-05, "loss": 3.4879, "step": 1410048 }, { "epoch": 0.01, "learning_rate": 2.690665654238212e-05, "loss": 3.4788, "step": 1410560 }, { "epoch": 0.01, "learning_rate": 2.68982705948716e-05, "loss": 3.4863, "step": 1411072 }, { "epoch": 0.01, "learning_rate": 2.6889901026164815e-05, "loss": 3.4848, "step": 1411584 }, { "epoch": 0.01, "learning_rate": 2.688151507865429e-05, "loss": 3.4887, "step": 1412096 }, { "epoch": 0.01, "learning_rate": 2.687312913114377e-05, "loss": 3.4797, "step": 1412608 }, { "epoch": 0.01, "learning_rate": 2.686474318363325e-05, "loss": 3.4924, "step": 1413120 }, { "epoch": 0.01, "learning_rate": 2.685637361492646e-05, "loss": 3.486, "step": 1413632 }, { "epoch": 0.01, "learning_rate": 2.684798766741594e-05, "loss": 3.4872, "step": 1414144 }, { "epoch": 0.01, "learning_rate": 2.683960171990542e-05, "loss": 3.4829, "step": 1414656 }, { "epoch": 0.01, "learning_rate": 2.6831215772394904e-05, "loss": 3.487, "step": 1415168 }, { "epoch": 0.01, "learning_rate": 2.6822846203688113e-05, "loss": 3.4877, "step": 1415680 }, { "epoch": 0.01, "learning_rate": 2.6814460256177593e-05, "loss": 3.4854, "step": 1416192 }, { "epoch": 0.01, "learning_rate": 2.6806074308667073e-05, "loss": 3.4739, "step": 1416704 }, { "epoch": 0.01, "learning_rate": 2.6797688361156553e-05, "loss": 3.4799, "step": 1417216 }, { "epoch": 0.01, "learning_rate": 2.6789302413646033e-05, "loss": 3.4859, "step": 1417728 }, { "epoch": 0.01, "learning_rate": 2.6780916466135512e-05, "loss": 3.485, "step": 1418240 }, { "epoch": 0.01, "learning_rate": 2.6772546897428725e-05, "loss": 3.4878, "step": 1418752 }, { "epoch": 0.01, "learning_rate": 2.6764160949918205e-05, "loss": 3.4729, "step": 1419264 }, { "epoch": 0.02, "learning_rate": 2.6755775002407685e-05, "loss": 3.4815, "step": 1419776 }, { "epoch": 0.02, "learning_rate": 2.6747389054897165e-05, "loss": 3.4809, "step": 1420288 }, { "epoch": 0.02, "learning_rate": 2.6739003107386645e-05, "loss": 3.4858, "step": 1420800 }, { "epoch": 0.02, "learning_rate": 2.6730617159876125e-05, "loss": 3.4708, "step": 1421312 }, { "epoch": 0.02, "learning_rate": 2.6722247591169337e-05, "loss": 3.4822, "step": 1421824 }, { "epoch": 0.02, "learning_rate": 2.6713861643658817e-05, "loss": 3.495, "step": 1422336 }, { "epoch": 0.02, "learning_rate": 2.6705475696148297e-05, "loss": 3.4789, "step": 1422848 }, { "epoch": 0.02, "learning_rate": 2.6697089748637777e-05, "loss": 3.4663, "step": 1423360 }, { "epoch": 0.02, "learning_rate": 2.6688703801127257e-05, "loss": 3.4838, "step": 1423872 }, { "epoch": 0.02, "learning_rate": 2.6680334232420466e-05, "loss": 3.4858, "step": 1424384 }, { "epoch": 0.02, "learning_rate": 2.667194828490995e-05, "loss": 3.4841, "step": 1424896 }, { "epoch": 0.02, "learning_rate": 2.666356233739943e-05, "loss": 3.4859, "step": 1425408 }, { "epoch": 0.02, "learning_rate": 2.665517638988891e-05, "loss": 3.4719, "step": 1425920 }, { "epoch": 0.02, "learning_rate": 2.664679044237839e-05, "loss": 3.4759, "step": 1426432 }, { "epoch": 0.02, "learning_rate": 2.663840449486787e-05, "loss": 3.485, "step": 1426944 }, { "epoch": 0.02, "learning_rate": 2.663001854735735e-05, "loss": 3.4715, "step": 1427456 }, { "epoch": 0.02, "learning_rate": 2.6621632599846822e-05, "loss": 3.4765, "step": 1427968 }, { "epoch": 0.02, "learning_rate": 2.661326303114004e-05, "loss": 3.4811, "step": 1428480 }, { "epoch": 0.02, "learning_rate": 2.660487708362952e-05, "loss": 3.488, "step": 1428992 }, { "epoch": 0.02, "learning_rate": 2.6596491136119e-05, "loss": 3.458, "step": 1429504 }, { "epoch": 0.02, "learning_rate": 2.6588105188608475e-05, "loss": 3.4794, "step": 1430016 }, { "epoch": 0.02, "learning_rate": 2.657973561990169e-05, "loss": 3.4666, "step": 1430528 }, { "epoch": 0.02, "learning_rate": 2.657134967239117e-05, "loss": 3.483, "step": 1431040 }, { "epoch": 0.02, "learning_rate": 2.6562963724880647e-05, "loss": 3.4806, "step": 1431552 }, { "epoch": 0.02, "learning_rate": 2.6554577777370127e-05, "loss": 3.4705, "step": 1432064 }, { "epoch": 0.02, "learning_rate": 2.6546208208663343e-05, "loss": 3.4888, "step": 1432576 }, { "epoch": 0.02, "learning_rate": 2.6537822261152823e-05, "loss": 3.4867, "step": 1433088 }, { "epoch": 0.02, "learning_rate": 2.6529452692446032e-05, "loss": 3.4724, "step": 1433600 }, { "epoch": 0.02, "learning_rate": 2.6521066744935512e-05, "loss": 3.4849, "step": 1434112 }, { "epoch": 0.02, "learning_rate": 2.6512680797424992e-05, "loss": 3.4837, "step": 1434624 }, { "epoch": 0.02, "learning_rate": 2.6504294849914475e-05, "loss": 3.4773, "step": 1435136 }, { "epoch": 0.02, "learning_rate": 2.649590890240395e-05, "loss": 3.4666, "step": 1435648 }, { "epoch": 0.02, "learning_rate": 2.6487539333697164e-05, "loss": 3.4801, "step": 1436160 }, { "epoch": 0.02, "learning_rate": 2.6479153386186644e-05, "loss": 3.4775, "step": 1436672 }, { "epoch": 0.02, "learning_rate": 2.647076743867612e-05, "loss": 3.4826, "step": 1437184 }, { "epoch": 0.02, "learning_rate": 2.64623814911656e-05, "loss": 3.477, "step": 1437696 }, { "epoch": 0.02, "learning_rate": 2.6454011922458817e-05, "loss": 3.4839, "step": 1438208 }, { "epoch": 0.02, "learning_rate": 2.6445625974948297e-05, "loss": 3.4714, "step": 1438720 }, { "epoch": 0.02, "learning_rate": 2.643724002743777e-05, "loss": 3.4708, "step": 1439232 }, { "epoch": 0.02, "learning_rate": 2.642885407992725e-05, "loss": 3.4667, "step": 1439744 }, { "epoch": 0.02, "learning_rate": 2.642046813241673e-05, "loss": 3.4901, "step": 1440256 }, { "epoch": 0.02, "learning_rate": 2.6412082184906213e-05, "loss": 3.4825, "step": 1440768 }, { "epoch": 0.02, "learning_rate": 2.6403696237395693e-05, "loss": 3.4828, "step": 1441280 }, { "epoch": 0.02, "learning_rate": 2.6395326668688902e-05, "loss": 3.4746, "step": 1441792 }, { "epoch": 0.02, "learning_rate": 2.6386940721178382e-05, "loss": 3.4881, "step": 1442304 }, { "epoch": 0.02, "learning_rate": 2.6378554773667862e-05, "loss": 3.4808, "step": 1442816 }, { "epoch": 0.02, "learning_rate": 2.6370168826157342e-05, "loss": 3.4741, "step": 1443328 }, { "epoch": 0.02, "learning_rate": 2.6361782878646822e-05, "loss": 3.4784, "step": 1443840 }, { "epoch": 0.02, "learning_rate": 2.6353396931136305e-05, "loss": 3.4839, "step": 1444352 }, { "epoch": 0.02, "learning_rate": 2.6345010983625785e-05, "loss": 3.4809, "step": 1444864 }, { "epoch": 0.02, "learning_rate": 2.6336641414918994e-05, "loss": 3.4937, "step": 1445376 }, { "epoch": 0.02, "learning_rate": 2.6328255467408474e-05, "loss": 3.4729, "step": 1445888 }, { "epoch": 0.02, "learning_rate": 2.6319869519897954e-05, "loss": 3.484, "step": 1446400 }, { "epoch": 0.02, "learning_rate": 2.6311483572387434e-05, "loss": 3.479, "step": 1446912 }, { "epoch": 0.02, "learning_rate": 2.6303097624876914e-05, "loss": 3.4719, "step": 1447424 }, { "epoch": 0.02, "learning_rate": 2.6294711677366398e-05, "loss": 3.4954, "step": 1447936 }, { "epoch": 0.02, "learning_rate": 2.6286325729855878e-05, "loss": 3.4767, "step": 1448448 }, { "epoch": 0.02, "learning_rate": 2.6277956161149087e-05, "loss": 3.4823, "step": 1448960 }, { "epoch": 0.02, "learning_rate": 2.6269570213638567e-05, "loss": 3.4767, "step": 1449472 }, { "epoch": 0.02, "learning_rate": 2.6261184266128047e-05, "loss": 3.4776, "step": 1449984 }, { "epoch": 0.03, "eval_loss": 3.904287815093994, "eval_runtime": 302.5883, "eval_samples_per_second": 1261.09, "eval_steps_per_second": 39.41, "step": 1450080 }, { "epoch": 1.0, "learning_rate": 2.6252798318617526e-05, "loss": 3.476, "step": 1450496 }, { "epoch": 1.0, "learning_rate": 2.6244412371107006e-05, "loss": 3.4762, "step": 1451008 }, { "epoch": 1.0, "learning_rate": 2.6236026423596483e-05, "loss": 3.4863, "step": 1451520 }, { "epoch": 1.0, "learning_rate": 2.6227640476085963e-05, "loss": 3.4817, "step": 1452032 }, { "epoch": 1.0, "learning_rate": 2.6219254528575443e-05, "loss": 3.4901, "step": 1452544 }, { "epoch": 1.0, "learning_rate": 2.621088495986866e-05, "loss": 3.4723, "step": 1453056 }, { "epoch": 1.0, "learning_rate": 2.6202499012358135e-05, "loss": 3.4787, "step": 1453568 }, { "epoch": 1.0, "learning_rate": 2.6194113064847615e-05, "loss": 3.4695, "step": 1454080 }, { "epoch": 1.0, "learning_rate": 2.6185727117337095e-05, "loss": 3.4884, "step": 1454592 }, { "epoch": 1.0, "learning_rate": 2.6177357548630304e-05, "loss": 3.4714, "step": 1455104 }, { "epoch": 1.0, "learning_rate": 2.6168971601119784e-05, "loss": 3.4819, "step": 1455616 }, { "epoch": 1.0, "learning_rate": 2.6160585653609264e-05, "loss": 3.4829, "step": 1456128 }, { "epoch": 1.0, "learning_rate": 2.6152199706098744e-05, "loss": 3.4744, "step": 1456640 }, { "epoch": 1.0, "learning_rate": 2.6143830137391957e-05, "loss": 3.4653, "step": 1457152 }, { "epoch": 1.0, "learning_rate": 2.6135444189881437e-05, "loss": 3.471, "step": 1457664 }, { "epoch": 1.0, "learning_rate": 2.6127058242370917e-05, "loss": 3.4657, "step": 1458176 }, { "epoch": 1.0, "learning_rate": 2.6118672294860397e-05, "loss": 3.4732, "step": 1458688 }, { "epoch": 1.0, "learning_rate": 2.611031910495734e-05, "loss": 3.4731, "step": 1459200 }, { "epoch": 1.0, "learning_rate": 2.610193315744682e-05, "loss": 3.4724, "step": 1459712 }, { "epoch": 1.0, "learning_rate": 2.6093547209936305e-05, "loss": 3.4896, "step": 1460224 }, { "epoch": 1.0, "learning_rate": 2.6085161262425778e-05, "loss": 3.4762, "step": 1460736 }, { "epoch": 1.0, "learning_rate": 2.6076775314915258e-05, "loss": 3.472, "step": 1461248 }, { "epoch": 1.0, "learning_rate": 2.6068389367404738e-05, "loss": 3.4806, "step": 1461760 }, { "epoch": 1.0, "learning_rate": 2.6060003419894218e-05, "loss": 3.4793, "step": 1462272 }, { "epoch": 1.0, "learning_rate": 2.6051617472383698e-05, "loss": 3.473, "step": 1462784 }, { "epoch": 1.0, "learning_rate": 2.604324790367691e-05, "loss": 3.4685, "step": 1463296 }, { "epoch": 1.0, "learning_rate": 2.603486195616639e-05, "loss": 3.4794, "step": 1463808 }, { "epoch": 1.0, "learning_rate": 2.6026492387459606e-05, "loss": 3.4623, "step": 1464320 }, { "epoch": 1.0, "learning_rate": 2.601810643994908e-05, "loss": 3.4651, "step": 1464832 }, { "epoch": 1.01, "learning_rate": 2.600972049243856e-05, "loss": 3.4747, "step": 1465344 }, { "epoch": 1.01, "learning_rate": 2.6001334544928043e-05, "loss": 3.4703, "step": 1465856 }, { "epoch": 1.01, "learning_rate": 2.5992948597417523e-05, "loss": 3.4809, "step": 1466368 }, { "epoch": 1.01, "learning_rate": 2.5984562649907003e-05, "loss": 3.4733, "step": 1466880 }, { "epoch": 1.01, "learning_rate": 2.5976176702396483e-05, "loss": 3.467, "step": 1467392 }, { "epoch": 1.01, "learning_rate": 2.5967790754885963e-05, "loss": 3.4784, "step": 1467904 }, { "epoch": 1.01, "learning_rate": 2.595942118617917e-05, "loss": 3.4875, "step": 1468416 }, { "epoch": 1.01, "learning_rate": 2.595103523866865e-05, "loss": 3.4653, "step": 1468928 }, { "epoch": 1.01, "learning_rate": 2.594264929115813e-05, "loss": 3.4755, "step": 1469440 }, { "epoch": 1.01, "learning_rate": 2.5934263343647615e-05, "loss": 3.4627, "step": 1469952 }, { "epoch": 1.01, "learning_rate": 2.5925893774940824e-05, "loss": 3.4765, "step": 1470464 }, { "epoch": 1.01, "learning_rate": 2.5917524206234033e-05, "loss": 3.4646, "step": 1470976 }, { "epoch": 1.01, "learning_rate": 2.5909138258723513e-05, "loss": 3.488, "step": 1471488 }, { "epoch": 1.01, "learning_rate": 2.5900752311212993e-05, "loss": 3.4773, "step": 1472000 }, { "epoch": 1.01, "learning_rate": 2.5892366363702476e-05, "loss": 3.4737, "step": 1472512 }, { "epoch": 1.01, "learning_rate": 2.5883980416191956e-05, "loss": 3.4815, "step": 1473024 }, { "epoch": 1.01, "learning_rate": 2.5875594468681436e-05, "loss": 3.4695, "step": 1473536 }, { "epoch": 1.01, "learning_rate": 2.5867208521170916e-05, "loss": 3.4776, "step": 1474048 }, { "epoch": 1.01, "learning_rate": 2.5858822573660396e-05, "loss": 3.463, "step": 1474560 }, { "epoch": 1.01, "learning_rate": 2.5850453004953605e-05, "loss": 3.4628, "step": 1475072 }, { "epoch": 1.01, "learning_rate": 2.5842067057443085e-05, "loss": 3.48, "step": 1475584 }, { "epoch": 1.01, "learning_rate": 2.583368110993257e-05, "loss": 3.4737, "step": 1476096 }, { "epoch": 1.01, "learning_rate": 2.582529516242205e-05, "loss": 3.4744, "step": 1476608 }, { "epoch": 1.01, "learning_rate": 2.581690921491153e-05, "loss": 3.4634, "step": 1477120 }, { "epoch": 1.01, "learning_rate": 2.580852326740101e-05, "loss": 3.4728, "step": 1477632 }, { "epoch": 1.01, "learning_rate": 2.5800153698694217e-05, "loss": 3.4608, "step": 1478144 }, { "epoch": 1.01, "learning_rate": 2.5791767751183697e-05, "loss": 3.4809, "step": 1478656 }, { "epoch": 1.01, "learning_rate": 2.5783381803673177e-05, "loss": 3.4732, "step": 1479168 }, { "epoch": 1.01, "learning_rate": 2.577499585616266e-05, "loss": 3.4842, "step": 1479680 }, { "epoch": 1.01, "learning_rate": 2.576660990865214e-05, "loss": 3.4732, "step": 1480192 }, { "epoch": 1.01, "learning_rate": 2.5758223961141614e-05, "loss": 3.4669, "step": 1480704 }, { "epoch": 1.01, "learning_rate": 2.5749838013631094e-05, "loss": 3.4684, "step": 1481216 }, { "epoch": 1.01, "learning_rate": 2.574146844492431e-05, "loss": 3.4743, "step": 1481728 }, { "epoch": 1.01, "learning_rate": 2.573308249741379e-05, "loss": 3.4662, "step": 1482240 }, { "epoch": 1.01, "learning_rate": 2.5724696549903266e-05, "loss": 3.4635, "step": 1482752 }, { "epoch": 1.01, "learning_rate": 2.5716310602392746e-05, "loss": 3.4727, "step": 1483264 }, { "epoch": 1.01, "learning_rate": 2.5707924654882226e-05, "loss": 3.4735, "step": 1483776 }, { "epoch": 1.01, "learning_rate": 2.5699538707371706e-05, "loss": 3.4554, "step": 1484288 }, { "epoch": 1.01, "learning_rate": 2.5691152759861186e-05, "loss": 3.4628, "step": 1484800 }, { "epoch": 1.01, "learning_rate": 2.5682766812350666e-05, "loss": 3.46, "step": 1485312 }, { "epoch": 1.01, "learning_rate": 2.5674413622447614e-05, "loss": 3.482, "step": 1485824 }, { "epoch": 1.01, "learning_rate": 2.5666027674937088e-05, "loss": 3.4731, "step": 1486336 }, { "epoch": 1.01, "learning_rate": 2.5657641727426568e-05, "loss": 3.4666, "step": 1486848 }, { "epoch": 1.01, "learning_rate": 2.5649255779916047e-05, "loss": 3.4736, "step": 1487360 }, { "epoch": 1.01, "learning_rate": 2.5640869832405527e-05, "loss": 3.4701, "step": 1487872 }, { "epoch": 1.01, "learning_rate": 2.5632483884895007e-05, "loss": 3.4797, "step": 1488384 }, { "epoch": 1.01, "learning_rate": 2.562409793738449e-05, "loss": 3.4626, "step": 1488896 }, { "epoch": 1.01, "learning_rate": 2.56157283686777e-05, "loss": 3.4845, "step": 1489408 }, { "epoch": 1.01, "learning_rate": 2.560734242116718e-05, "loss": 3.4674, "step": 1489920 }, { "epoch": 1.01, "learning_rate": 2.559895647365666e-05, "loss": 3.4753, "step": 1490432 }, { "epoch": 1.01, "learning_rate": 2.559057052614614e-05, "loss": 3.475, "step": 1490944 }, { "epoch": 1.01, "learning_rate": 2.558218457863562e-05, "loss": 3.4696, "step": 1491456 }, { "epoch": 1.01, "learning_rate": 2.55737986311251e-05, "loss": 3.4769, "step": 1491968 }, { "epoch": 1.01, "learning_rate": 2.5565412683614583e-05, "loss": 3.4709, "step": 1492480 }, { "epoch": 1.01, "learning_rate": 2.5557026736104063e-05, "loss": 3.4608, "step": 1492992 }, { "epoch": 1.01, "learning_rate": 2.5548657167397272e-05, "loss": 3.47, "step": 1493504 }, { "epoch": 1.01, "learning_rate": 2.5540271219886752e-05, "loss": 3.4677, "step": 1494016 }, { "epoch": 1.01, "learning_rate": 2.5531885272376232e-05, "loss": 3.4767, "step": 1494528 }, { "epoch": 1.01, "learning_rate": 2.5523515703669444e-05, "loss": 3.4725, "step": 1495040 }, { "epoch": 1.01, "learning_rate": 2.5515129756158924e-05, "loss": 3.4622, "step": 1495552 }, { "epoch": 1.02, "learning_rate": 2.5506743808648404e-05, "loss": 3.4728, "step": 1496064 }, { "epoch": 1.02, "learning_rate": 2.5498357861137884e-05, "loss": 3.4641, "step": 1496576 }, { "epoch": 1.02, "learning_rate": 2.5489971913627364e-05, "loss": 3.4714, "step": 1497088 }, { "epoch": 1.02, "learning_rate": 2.5481585966116844e-05, "loss": 3.4616, "step": 1497600 }, { "epoch": 1.02, "learning_rate": 2.5473200018606324e-05, "loss": 3.4715, "step": 1498112 }, { "epoch": 1.02, "learning_rate": 2.54648140710958e-05, "loss": 3.4809, "step": 1498624 }, { "epoch": 1.02, "learning_rate": 2.5456444502389017e-05, "loss": 3.4648, "step": 1499136 }, { "epoch": 1.02, "learning_rate": 2.5448074933682226e-05, "loss": 3.457, "step": 1499648 }, { "epoch": 1.02, "learning_rate": 2.5439688986171706e-05, "loss": 3.4716, "step": 1500160 }, { "epoch": 1.02, "learning_rate": 2.5431303038661186e-05, "loss": 3.4662, "step": 1500672 }, { "epoch": 1.02, "learning_rate": 2.5422917091150666e-05, "loss": 3.4772, "step": 1501184 }, { "epoch": 1.02, "learning_rate": 2.5414531143640146e-05, "loss": 3.4704, "step": 1501696 }, { "epoch": 1.02, "learning_rate": 2.5406145196129625e-05, "loss": 3.4612, "step": 1502208 }, { "epoch": 1.02, "learning_rate": 2.5397759248619102e-05, "loss": 3.4655, "step": 1502720 }, { "epoch": 1.02, "learning_rate": 2.5389373301108582e-05, "loss": 3.4729, "step": 1503232 }, { "epoch": 1.02, "learning_rate": 2.5381003732401798e-05, "loss": 3.4568, "step": 1503744 }, { "epoch": 1.02, "learning_rate": 2.537261778489127e-05, "loss": 3.4657, "step": 1504256 }, { "epoch": 1.02, "learning_rate": 2.5364231837380754e-05, "loss": 3.4657, "step": 1504768 }, { "epoch": 1.02, "learning_rate": 2.535586226867397e-05, "loss": 3.4755, "step": 1505280 }, { "epoch": 1.02, "learning_rate": 2.534747632116345e-05, "loss": 3.4448, "step": 1505792 }, { "epoch": 1.02, "learning_rate": 2.5339090373652923e-05, "loss": 3.4656, "step": 1506304 }, { "epoch": 1.02, "learning_rate": 2.5330704426142403e-05, "loss": 3.4613, "step": 1506816 }, { "epoch": 1.02, "learning_rate": 2.532233485743562e-05, "loss": 3.4648, "step": 1507328 }, { "epoch": 1.02, "learning_rate": 2.53139489099251e-05, "loss": 3.4709, "step": 1507840 }, { "epoch": 1.02, "learning_rate": 2.5305562962414576e-05, "loss": 3.4583, "step": 1508352 }, { "epoch": 1.02, "learning_rate": 2.5297177014904056e-05, "loss": 3.4763, "step": 1508864 }, { "epoch": 1.02, "learning_rate": 2.528880744619727e-05, "loss": 3.4698, "step": 1509376 }, { "epoch": 1.02, "learning_rate": 2.528043787749048e-05, "loss": 3.4613, "step": 1509888 }, { "epoch": 1.02, "learning_rate": 2.527205192997996e-05, "loss": 3.4729, "step": 1510400 }, { "epoch": 1.02, "learning_rate": 2.526366598246944e-05, "loss": 3.4708, "step": 1510912 }, { "epoch": 1.02, "learning_rate": 2.5255280034958924e-05, "loss": 3.4672, "step": 1511424 }, { "epoch": 1.02, "learning_rate": 2.5246894087448397e-05, "loss": 3.4487, "step": 1511936 }, { "epoch": 1.02, "learning_rate": 2.5238524518741613e-05, "loss": 3.4728, "step": 1512448 }, { "epoch": 1.02, "learning_rate": 2.5230138571231093e-05, "loss": 3.4618, "step": 1512960 }, { "epoch": 1.02, "learning_rate": 2.5221752623720573e-05, "loss": 3.4694, "step": 1513472 }, { "epoch": 1.02, "learning_rate": 2.521336667621005e-05, "loss": 3.4668, "step": 1513984 }, { "epoch": 1.02, "learning_rate": 2.5204997107503265e-05, "loss": 3.4729, "step": 1514496 }, { "epoch": 1.02, "learning_rate": 2.5196611159992745e-05, "loss": 3.4646, "step": 1515008 }, { "epoch": 1.02, "learning_rate": 2.518822521248222e-05, "loss": 3.4558, "step": 1515520 }, { "epoch": 1.02, "learning_rate": 2.51798392649717e-05, "loss": 3.4555, "step": 1516032 }, { "epoch": 1.02, "learning_rate": 2.517145331746118e-05, "loss": 3.4728, "step": 1516544 }, { "epoch": 1.02, "learning_rate": 2.5163067369950662e-05, "loss": 3.4711, "step": 1517056 }, { "epoch": 1.02, "learning_rate": 2.515468142244014e-05, "loss": 3.4713, "step": 1517568 }, { "epoch": 1.02, "learning_rate": 2.514631185373335e-05, "loss": 3.461, "step": 1518080 }, { "epoch": 1.02, "learning_rate": 2.513792590622283e-05, "loss": 3.4732, "step": 1518592 }, { "epoch": 1.02, "learning_rate": 2.512953995871231e-05, "loss": 3.4688, "step": 1519104 }, { "epoch": 1.02, "learning_rate": 2.512115401120179e-05, "loss": 3.4618, "step": 1519616 }, { "epoch": 1.02, "learning_rate": 2.511276806369127e-05, "loss": 3.4671, "step": 1520128 }, { "epoch": 1.02, "learning_rate": 2.5104382116180754e-05, "loss": 3.4679, "step": 1520640 }, { "epoch": 1.02, "learning_rate": 2.5096012547473963e-05, "loss": 3.4732, "step": 1521152 }, { "epoch": 1.02, "learning_rate": 2.5087626599963443e-05, "loss": 3.479, "step": 1521664 }, { "epoch": 1.02, "learning_rate": 2.5079240652452923e-05, "loss": 3.4603, "step": 1522176 }, { "epoch": 1.02, "learning_rate": 2.5070854704942403e-05, "loss": 3.4717, "step": 1522688 }, { "epoch": 1.02, "learning_rate": 2.5062468757431883e-05, "loss": 3.4662, "step": 1523200 }, { "epoch": 1.02, "learning_rate": 2.5054082809921363e-05, "loss": 3.4649, "step": 1523712 }, { "epoch": 1.02, "learning_rate": 2.5045696862410846e-05, "loss": 3.4765, "step": 1524224 }, { "epoch": 1.02, "learning_rate": 2.5037310914900326e-05, "loss": 3.4675, "step": 1524736 }, { "epoch": 1.02, "learning_rate": 2.5028941346193535e-05, "loss": 3.4691, "step": 1525248 }, { "epoch": 1.02, "learning_rate": 2.5020571777486744e-05, "loss": 3.4618, "step": 1525760 }, { "epoch": 1.02, "learning_rate": 2.5012185829976224e-05, "loss": 3.4675, "step": 1526272 }, { "epoch": 1.03, "eval_loss": 3.906632661819458, "eval_runtime": 302.585, "eval_samples_per_second": 1261.103, "eval_steps_per_second": 39.41, "step": 1526400 }, { "epoch": 0.0, "learning_rate": 2.5003799882465708e-05, "loss": 3.4566, "step": 1526784 }, { "epoch": 0.0, "learning_rate": 2.4995413934955188e-05, "loss": 3.4663, "step": 1527296 }, { "epoch": 0.0, "learning_rate": 2.4987027987444668e-05, "loss": 3.4721, "step": 1527808 }, { "epoch": 0.0, "learning_rate": 2.4978642039934144e-05, "loss": 3.4686, "step": 1528320 }, { "epoch": 0.0, "learning_rate": 2.4970272471227357e-05, "loss": 3.4797, "step": 1528832 }, { "epoch": 0.0, "learning_rate": 2.4961886523716837e-05, "loss": 3.4572, "step": 1529344 }, { "epoch": 0.0, "learning_rate": 2.4953500576206316e-05, "loss": 3.4655, "step": 1529856 }, { "epoch": 0.0, "learning_rate": 2.4945114628695796e-05, "loss": 3.4595, "step": 1530368 }, { "epoch": 0.0, "learning_rate": 2.493674505998901e-05, "loss": 3.4745, "step": 1530880 }, { "epoch": 0.0, "learning_rate": 2.492835911247849e-05, "loss": 3.466, "step": 1531392 }, { "epoch": 0.0, "learning_rate": 2.4919973164967965e-05, "loss": 3.468, "step": 1531904 }, { "epoch": 0.0, "learning_rate": 2.4911587217457445e-05, "loss": 3.4652, "step": 1532416 }, { "epoch": 0.0, "learning_rate": 2.490321764875066e-05, "loss": 3.4641, "step": 1532928 }, { "epoch": 0.0, "learning_rate": 2.489483170124014e-05, "loss": 3.4542, "step": 1533440 }, { "epoch": 0.0, "learning_rate": 2.4886445753729618e-05, "loss": 3.4625, "step": 1533952 }, { "epoch": 0.0, "learning_rate": 2.487807618502283e-05, "loss": 3.4477, "step": 1534464 }, { "epoch": 0.0, "learning_rate": 2.486969023751231e-05, "loss": 3.4625, "step": 1534976 }, { "epoch": 0.0, "learning_rate": 2.4861304290001787e-05, "loss": 3.461, "step": 1535488 }, { "epoch": 0.0, "learning_rate": 2.485291834249127e-05, "loss": 3.4576, "step": 1536000 }, { "epoch": 0.0, "learning_rate": 2.4844548773784483e-05, "loss": 3.4819, "step": 1536512 }, { "epoch": 0.0, "learning_rate": 2.4836162826273963e-05, "loss": 3.4606, "step": 1537024 }, { "epoch": 0.0, "learning_rate": 2.482779325756717e-05, "loss": 3.4626, "step": 1537536 }, { "epoch": 0.0, "learning_rate": 2.481940731005665e-05, "loss": 3.468, "step": 1538048 }, { "epoch": 0.0, "learning_rate": 2.481102136254613e-05, "loss": 3.4657, "step": 1538560 }, { "epoch": 0.0, "learning_rate": 2.4802635415035615e-05, "loss": 3.4614, "step": 1539072 }, { "epoch": 0.0, "learning_rate": 2.479424946752509e-05, "loss": 3.4565, "step": 1539584 }, { "epoch": 0.0, "learning_rate": 2.478586352001457e-05, "loss": 3.4679, "step": 1540096 }, { "epoch": 0.0, "learning_rate": 2.4777493951307784e-05, "loss": 3.4462, "step": 1540608 }, { "epoch": 0.0, "learning_rate": 2.476910800379726e-05, "loss": 3.4565, "step": 1541120 }, { "epoch": 0.0, "learning_rate": 2.476072205628674e-05, "loss": 3.4577, "step": 1541632 }, { "epoch": 0.01, "learning_rate": 2.4752336108776224e-05, "loss": 3.4594, "step": 1542144 }, { "epoch": 0.01, "learning_rate": 2.4743950161265704e-05, "loss": 3.4673, "step": 1542656 }, { "epoch": 0.01, "learning_rate": 2.4735564213755184e-05, "loss": 3.4623, "step": 1543168 }, { "epoch": 0.01, "learning_rate": 2.4727178266244664e-05, "loss": 3.4581, "step": 1543680 }, { "epoch": 0.01, "learning_rate": 2.4718792318734144e-05, "loss": 3.4632, "step": 1544192 }, { "epoch": 0.01, "learning_rate": 2.4710422750027353e-05, "loss": 3.4705, "step": 1544704 }, { "epoch": 0.01, "learning_rate": 2.4702036802516833e-05, "loss": 3.4563, "step": 1545216 }, { "epoch": 0.01, "learning_rate": 2.4693650855006316e-05, "loss": 3.4643, "step": 1545728 }, { "epoch": 0.01, "learning_rate": 2.4685264907495796e-05, "loss": 3.4519, "step": 1546240 }, { "epoch": 0.01, "learning_rate": 2.4676895338789005e-05, "loss": 3.4631, "step": 1546752 }, { "epoch": 0.01, "learning_rate": 2.4668525770082214e-05, "loss": 3.4509, "step": 1547264 }, { "epoch": 0.01, "learning_rate": 2.4660139822571694e-05, "loss": 3.4773, "step": 1547776 }, { "epoch": 0.01, "learning_rate": 2.4651753875061177e-05, "loss": 3.4642, "step": 1548288 }, { "epoch": 0.01, "learning_rate": 2.4643367927550657e-05, "loss": 3.4602, "step": 1548800 }, { "epoch": 0.01, "learning_rate": 2.4634981980040137e-05, "loss": 3.468, "step": 1549312 }, { "epoch": 0.01, "learning_rate": 2.4626596032529617e-05, "loss": 3.4562, "step": 1549824 }, { "epoch": 0.01, "learning_rate": 2.4618210085019094e-05, "loss": 3.465, "step": 1550336 }, { "epoch": 0.01, "learning_rate": 2.4609824137508574e-05, "loss": 3.451, "step": 1550848 }, { "epoch": 0.01, "learning_rate": 2.4601454568801786e-05, "loss": 3.4491, "step": 1551360 }, { "epoch": 0.01, "learning_rate": 2.4593085000095e-05, "loss": 3.4704, "step": 1551872 }, { "epoch": 0.01, "learning_rate": 2.458469905258448e-05, "loss": 3.4604, "step": 1552384 }, { "epoch": 0.01, "learning_rate": 2.457631310507396e-05, "loss": 3.4606, "step": 1552896 }, { "epoch": 0.01, "learning_rate": 2.456792715756344e-05, "loss": 3.4509, "step": 1553408 }, { "epoch": 0.01, "learning_rate": 2.4559541210052915e-05, "loss": 3.4612, "step": 1553920 }, { "epoch": 0.01, "learning_rate": 2.455117164134613e-05, "loss": 3.4499, "step": 1554432 }, { "epoch": 0.01, "learning_rate": 2.454278569383561e-05, "loss": 3.4643, "step": 1554944 }, { "epoch": 0.01, "learning_rate": 2.453439974632509e-05, "loss": 3.4576, "step": 1555456 }, { "epoch": 0.01, "learning_rate": 2.4526013798814568e-05, "loss": 3.4732, "step": 1555968 }, { "epoch": 0.01, "learning_rate": 2.4517627851304048e-05, "loss": 3.4618, "step": 1556480 }, { "epoch": 0.01, "learning_rate": 2.4509241903793528e-05, "loss": 3.4517, "step": 1556992 }, { "epoch": 0.01, "learning_rate": 2.4500855956283007e-05, "loss": 3.4582, "step": 1557504 }, { "epoch": 0.01, "learning_rate": 2.449248638757622e-05, "loss": 3.461, "step": 1558016 }, { "epoch": 0.01, "learning_rate": 2.44841004400657e-05, "loss": 3.4516, "step": 1558528 }, { "epoch": 0.01, "learning_rate": 2.447571449255518e-05, "loss": 3.4545, "step": 1559040 }, { "epoch": 0.01, "learning_rate": 2.446732854504466e-05, "loss": 3.4583, "step": 1559552 }, { "epoch": 0.01, "learning_rate": 2.445894259753414e-05, "loss": 3.4643, "step": 1560064 }, { "epoch": 0.01, "learning_rate": 2.445055665002362e-05, "loss": 3.4408, "step": 1560576 }, { "epoch": 0.01, "learning_rate": 2.44421707025131e-05, "loss": 3.4525, "step": 1561088 }, { "epoch": 0.01, "learning_rate": 2.443378475500258e-05, "loss": 3.4481, "step": 1561600 }, { "epoch": 0.01, "learning_rate": 2.442543156509952e-05, "loss": 3.4648, "step": 1562112 }, { "epoch": 0.01, "learning_rate": 2.4417045617589e-05, "loss": 3.4592, "step": 1562624 }, { "epoch": 0.01, "learning_rate": 2.440865967007848e-05, "loss": 3.4578, "step": 1563136 }, { "epoch": 0.01, "learning_rate": 2.440027372256796e-05, "loss": 3.4606, "step": 1563648 }, { "epoch": 0.01, "learning_rate": 2.439188777505744e-05, "loss": 3.4587, "step": 1564160 }, { "epoch": 0.01, "learning_rate": 2.438350182754692e-05, "loss": 3.4716, "step": 1564672 }, { "epoch": 0.01, "learning_rate": 2.43751158800364e-05, "loss": 3.4503, "step": 1565184 }, { "epoch": 0.01, "learning_rate": 2.436672993252588e-05, "loss": 3.4687, "step": 1565696 }, { "epoch": 0.01, "learning_rate": 2.4358360363819093e-05, "loss": 3.4588, "step": 1566208 }, { "epoch": 0.01, "learning_rate": 2.4349990795112303e-05, "loss": 3.4588, "step": 1566720 }, { "epoch": 0.01, "learning_rate": 2.4341604847601786e-05, "loss": 3.4636, "step": 1567232 }, { "epoch": 0.01, "learning_rate": 2.4333218900091266e-05, "loss": 3.4601, "step": 1567744 }, { "epoch": 0.01, "learning_rate": 2.4324832952580746e-05, "loss": 3.464, "step": 1568256 }, { "epoch": 0.01, "learning_rate": 2.4316447005070222e-05, "loss": 3.4608, "step": 1568768 }, { "epoch": 0.01, "learning_rate": 2.4308061057559702e-05, "loss": 3.4446, "step": 1569280 }, { "epoch": 0.01, "learning_rate": 2.4299675110049182e-05, "loss": 3.458, "step": 1569792 }, { "epoch": 0.01, "learning_rate": 2.4291289162538662e-05, "loss": 3.4549, "step": 1570304 }, { "epoch": 0.01, "learning_rate": 2.4282919593831875e-05, "loss": 3.4636, "step": 1570816 }, { "epoch": 0.01, "learning_rate": 2.4274550025125087e-05, "loss": 3.4597, "step": 1571328 }, { "epoch": 0.01, "learning_rate": 2.4266164077614567e-05, "loss": 3.4497, "step": 1571840 }, { "epoch": 0.02, "learning_rate": 2.4257778130104044e-05, "loss": 3.4593, "step": 1572352 }, { "epoch": 0.02, "learning_rate": 2.4249392182593524e-05, "loss": 3.455, "step": 1572864 }, { "epoch": 0.02, "learning_rate": 2.4241006235083004e-05, "loss": 3.4611, "step": 1573376 }, { "epoch": 0.02, "learning_rate": 2.4232620287572487e-05, "loss": 3.4441, "step": 1573888 }, { "epoch": 0.02, "learning_rate": 2.4224234340061967e-05, "loss": 3.461, "step": 1574400 }, { "epoch": 0.02, "learning_rate": 2.4215848392551447e-05, "loss": 3.4747, "step": 1574912 }, { "epoch": 0.02, "learning_rate": 2.4207478823844656e-05, "loss": 3.451, "step": 1575424 }, { "epoch": 0.02, "learning_rate": 2.4199109255137865e-05, "loss": 3.4395, "step": 1575936 }, { "epoch": 0.02, "learning_rate": 2.419072330762735e-05, "loss": 3.4584, "step": 1576448 }, { "epoch": 0.02, "learning_rate": 2.418233736011683e-05, "loss": 3.4572, "step": 1576960 }, { "epoch": 0.02, "learning_rate": 2.417395141260631e-05, "loss": 3.4627, "step": 1577472 }, { "epoch": 0.02, "learning_rate": 2.416556546509579e-05, "loss": 3.4609, "step": 1577984 }, { "epoch": 0.02, "learning_rate": 2.4157179517585268e-05, "loss": 3.4499, "step": 1578496 }, { "epoch": 0.02, "learning_rate": 2.4148793570074748e-05, "loss": 3.4524, "step": 1579008 }, { "epoch": 0.02, "learning_rate": 2.4140424001367957e-05, "loss": 3.4619, "step": 1579520 }, { "epoch": 0.02, "learning_rate": 2.413203805385744e-05, "loss": 3.4439, "step": 1580032 }, { "epoch": 0.02, "learning_rate": 2.412365210634692e-05, "loss": 3.4524, "step": 1580544 }, { "epoch": 0.02, "learning_rate": 2.41152661588364e-05, "loss": 3.4523, "step": 1581056 }, { "epoch": 0.02, "learning_rate": 2.410689659012961e-05, "loss": 3.4631, "step": 1581568 }, { "epoch": 0.02, "learning_rate": 2.409851064261909e-05, "loss": 3.4333, "step": 1582080 }, { "epoch": 0.02, "learning_rate": 2.409012469510857e-05, "loss": 3.454, "step": 1582592 }, { "epoch": 0.02, "learning_rate": 2.408173874759805e-05, "loss": 3.4474, "step": 1583104 }, { "epoch": 0.02, "learning_rate": 2.4073369178891262e-05, "loss": 3.4549, "step": 1583616 }, { "epoch": 0.02, "learning_rate": 2.4064983231380742e-05, "loss": 3.453, "step": 1584128 }, { "epoch": 0.02, "learning_rate": 2.4056597283870222e-05, "loss": 3.4491, "step": 1584640 }, { "epoch": 0.02, "learning_rate": 2.40482113363597e-05, "loss": 3.4585, "step": 1585152 }, { "epoch": 0.02, "learning_rate": 2.403984176765291e-05, "loss": 3.461, "step": 1585664 }, { "epoch": 0.02, "learning_rate": 2.4031472198946123e-05, "loss": 3.4495, "step": 1586176 }, { "epoch": 0.02, "learning_rate": 2.4023086251435603e-05, "loss": 3.4631, "step": 1586688 }, { "epoch": 0.02, "learning_rate": 2.4014700303925083e-05, "loss": 3.4549, "step": 1587200 }, { "epoch": 0.02, "learning_rate": 2.4006314356414563e-05, "loss": 3.4599, "step": 1587712 }, { "epoch": 0.02, "learning_rate": 2.3997928408904043e-05, "loss": 3.4381, "step": 1588224 }, { "epoch": 0.02, "learning_rate": 2.3989558840197256e-05, "loss": 3.4615, "step": 1588736 }, { "epoch": 0.02, "learning_rate": 2.3981172892686736e-05, "loss": 3.4439, "step": 1589248 }, { "epoch": 0.02, "learning_rate": 2.3972786945176216e-05, "loss": 3.4578, "step": 1589760 }, { "epoch": 0.02, "learning_rate": 2.3964400997665696e-05, "loss": 3.4485, "step": 1590272 }, { "epoch": 0.02, "learning_rate": 2.3956031428958905e-05, "loss": 3.4631, "step": 1590784 }, { "epoch": 0.02, "learning_rate": 2.3947645481448385e-05, "loss": 3.4539, "step": 1591296 }, { "epoch": 0.02, "learning_rate": 2.3939259533937865e-05, "loss": 3.4464, "step": 1591808 }, { "epoch": 0.02, "learning_rate": 2.3930873586427348e-05, "loss": 3.4407, "step": 1592320 }, { "epoch": 0.02, "learning_rate": 2.3922487638916825e-05, "loss": 3.4658, "step": 1592832 }, { "epoch": 0.02, "learning_rate": 2.3914101691406305e-05, "loss": 3.4521, "step": 1593344 }, { "epoch": 0.02, "learning_rate": 2.3905715743895784e-05, "loss": 3.4593, "step": 1593856 }, { "epoch": 0.02, "learning_rate": 2.3897346175188994e-05, "loss": 3.4506, "step": 1594368 }, { "epoch": 0.02, "learning_rate": 2.3888960227678474e-05, "loss": 3.4603, "step": 1594880 }, { "epoch": 0.02, "learning_rate": 2.3880574280167957e-05, "loss": 3.4608, "step": 1595392 }, { "epoch": 0.02, "learning_rate": 2.3872188332657437e-05, "loss": 3.4481, "step": 1595904 }, { "epoch": 0.02, "learning_rate": 2.3863802385146917e-05, "loss": 3.4533, "step": 1596416 }, { "epoch": 0.02, "learning_rate": 2.3855416437636397e-05, "loss": 3.4587, "step": 1596928 }, { "epoch": 0.02, "learning_rate": 2.3847030490125877e-05, "loss": 3.462, "step": 1597440 }, { "epoch": 0.02, "learning_rate": 2.3838660921419086e-05, "loss": 3.4683, "step": 1597952 }, { "epoch": 0.02, "learning_rate": 2.3830274973908566e-05, "loss": 3.4455, "step": 1598464 }, { "epoch": 0.02, "learning_rate": 2.382188902639805e-05, "loss": 3.4577, "step": 1598976 }, { "epoch": 0.02, "learning_rate": 2.381350307888753e-05, "loss": 3.4533, "step": 1599488 }, { "epoch": 0.02, "learning_rate": 2.3805117131377006e-05, "loss": 3.4566, "step": 1600000 }, { "epoch": 0.02, "learning_rate": 2.3796731183866486e-05, "loss": 3.4622, "step": 1600512 }, { "epoch": 0.02, "learning_rate": 2.3788345236355966e-05, "loss": 3.4517, "step": 1601024 }, { "epoch": 0.02, "learning_rate": 2.3779959288845445e-05, "loss": 3.4626, "step": 1601536 }, { "epoch": 0.02, "learning_rate": 2.3771589720138658e-05, "loss": 3.4482, "step": 1602048 }, { "epoch": 0.02, "learning_rate": 2.3763203772628138e-05, "loss": 3.463, "step": 1602560 }, { "epoch": 0.03, "eval_loss": 3.9080088138580322, "eval_runtime": 304.7239, "eval_samples_per_second": 1252.252, "eval_steps_per_second": 39.134, "step": 1602720 }, { "epoch": 1.0, "learning_rate": 2.3754817825117618e-05, "loss": 3.4462, "step": 1603072 }, { "epoch": 1.0, "learning_rate": 2.3746431877607098e-05, "loss": 3.4564, "step": 1603584 }, { "epoch": 1.0, "learning_rate": 2.3738045930096578e-05, "loss": 3.4586, "step": 1604096 }, { "epoch": 1.0, "learning_rate": 2.3729659982586058e-05, "loss": 3.4566, "step": 1604608 }, { "epoch": 1.0, "learning_rate": 2.3721274035075534e-05, "loss": 3.4676, "step": 1605120 }, { "epoch": 1.0, "learning_rate": 2.371290446636875e-05, "loss": 3.4488, "step": 1605632 }, { "epoch": 1.0, "learning_rate": 2.370451851885823e-05, "loss": 3.4516, "step": 1606144 }, { "epoch": 1.0, "learning_rate": 2.3696132571347707e-05, "loss": 3.4459, "step": 1606656 }, { "epoch": 1.0, "learning_rate": 2.3687746623837187e-05, "loss": 3.4615, "step": 1607168 }, { "epoch": 1.0, "learning_rate": 2.36793770551304e-05, "loss": 3.4589, "step": 1607680 }, { "epoch": 1.0, "learning_rate": 2.367099110761988e-05, "loss": 3.4523, "step": 1608192 }, { "epoch": 1.0, "learning_rate": 2.366260516010936e-05, "loss": 3.4566, "step": 1608704 }, { "epoch": 1.0, "learning_rate": 2.365421921259884e-05, "loss": 3.448, "step": 1609216 }, { "epoch": 1.0, "learning_rate": 2.364584964389205e-05, "loss": 3.4445, "step": 1609728 }, { "epoch": 1.0, "learning_rate": 2.363746369638153e-05, "loss": 3.4502, "step": 1610240 }, { "epoch": 1.0, "learning_rate": 2.3629077748871008e-05, "loss": 3.4368, "step": 1610752 }, { "epoch": 1.0, "learning_rate": 2.3620691801360488e-05, "loss": 3.4479, "step": 1611264 }, { "epoch": 1.0, "learning_rate": 2.3612322232653704e-05, "loss": 3.4462, "step": 1611776 }, { "epoch": 1.0, "learning_rate": 2.360393628514318e-05, "loss": 3.446, "step": 1612288 }, { "epoch": 1.0, "learning_rate": 2.359555033763266e-05, "loss": 3.4769, "step": 1612800 }, { "epoch": 1.0, "learning_rate": 2.358716439012214e-05, "loss": 3.446, "step": 1613312 }, { "epoch": 1.0, "learning_rate": 2.3578794821415353e-05, "loss": 3.4524, "step": 1613824 }, { "epoch": 1.0, "learning_rate": 2.3570408873904833e-05, "loss": 3.4529, "step": 1614336 }, { "epoch": 1.0, "learning_rate": 2.3562022926394313e-05, "loss": 3.4536, "step": 1614848 }, { "epoch": 1.0, "learning_rate": 2.3553636978883793e-05, "loss": 3.4464, "step": 1615360 }, { "epoch": 1.0, "learning_rate": 2.3545251031373273e-05, "loss": 3.449, "step": 1615872 }, { "epoch": 1.0, "learning_rate": 2.3536865083862753e-05, "loss": 3.4534, "step": 1616384 }, { "epoch": 1.0, "learning_rate": 2.352849551515596e-05, "loss": 3.435, "step": 1616896 }, { "epoch": 1.0, "learning_rate": 2.352010956764544e-05, "loss": 3.443, "step": 1617408 }, { "epoch": 1.0, "learning_rate": 2.3511723620134925e-05, "loss": 3.4427, "step": 1617920 }, { "epoch": 1.01, "learning_rate": 2.3503337672624405e-05, "loss": 3.4494, "step": 1618432 }, { "epoch": 1.01, "learning_rate": 2.3494951725113885e-05, "loss": 3.4518, "step": 1618944 }, { "epoch": 1.01, "learning_rate": 2.348656577760336e-05, "loss": 3.45, "step": 1619456 }, { "epoch": 1.01, "learning_rate": 2.347817983009284e-05, "loss": 3.4499, "step": 1619968 }, { "epoch": 1.01, "learning_rate": 2.346979388258232e-05, "loss": 3.4494, "step": 1620480 }, { "epoch": 1.01, "learning_rate": 2.3461424313875534e-05, "loss": 3.4542, "step": 1620992 }, { "epoch": 1.01, "learning_rate": 2.3453038366365014e-05, "loss": 3.4439, "step": 1621504 }, { "epoch": 1.01, "learning_rate": 2.3444652418854494e-05, "loss": 3.4531, "step": 1622016 }, { "epoch": 1.01, "learning_rate": 2.3436266471343974e-05, "loss": 3.4389, "step": 1622528 }, { "epoch": 1.01, "learning_rate": 2.3427896902637186e-05, "loss": 3.4536, "step": 1623040 }, { "epoch": 1.01, "learning_rate": 2.3419527333930395e-05, "loss": 3.4345, "step": 1623552 }, { "epoch": 1.01, "learning_rate": 2.341114138641988e-05, "loss": 3.4678, "step": 1624064 }, { "epoch": 1.01, "learning_rate": 2.340275543890936e-05, "loss": 3.4527, "step": 1624576 }, { "epoch": 1.01, "learning_rate": 2.3394369491398835e-05, "loss": 3.4491, "step": 1625088 }, { "epoch": 1.01, "learning_rate": 2.3385983543888315e-05, "loss": 3.4542, "step": 1625600 }, { "epoch": 1.01, "learning_rate": 2.3377597596377795e-05, "loss": 3.4508, "step": 1626112 }, { "epoch": 1.01, "learning_rate": 2.3369211648867275e-05, "loss": 3.4498, "step": 1626624 }, { "epoch": 1.01, "learning_rate": 2.3360825701356755e-05, "loss": 3.4375, "step": 1627136 }, { "epoch": 1.01, "learning_rate": 2.3352456132649967e-05, "loss": 3.4317, "step": 1627648 }, { "epoch": 1.01, "learning_rate": 2.334408656394318e-05, "loss": 3.4631, "step": 1628160 }, { "epoch": 1.01, "learning_rate": 2.333570061643266e-05, "loss": 3.4479, "step": 1628672 }, { "epoch": 1.01, "learning_rate": 2.3327314668922136e-05, "loss": 3.453, "step": 1629184 }, { "epoch": 1.01, "learning_rate": 2.3318928721411616e-05, "loss": 3.4419, "step": 1629696 }, { "epoch": 1.01, "learning_rate": 2.3310542773901096e-05, "loss": 3.4473, "step": 1630208 }, { "epoch": 1.01, "learning_rate": 2.330217320519431e-05, "loss": 3.4391, "step": 1630720 }, { "epoch": 1.01, "learning_rate": 2.329378725768379e-05, "loss": 3.4524, "step": 1631232 }, { "epoch": 1.01, "learning_rate": 2.328540131017327e-05, "loss": 3.4451, "step": 1631744 }, { "epoch": 1.01, "learning_rate": 2.327701536266275e-05, "loss": 3.4591, "step": 1632256 }, { "epoch": 1.01, "learning_rate": 2.326862941515223e-05, "loss": 3.4567, "step": 1632768 }, { "epoch": 1.01, "learning_rate": 2.326024346764171e-05, "loss": 3.4385, "step": 1633280 }, { "epoch": 1.01, "learning_rate": 2.325185752013119e-05, "loss": 3.4464, "step": 1633792 }, { "epoch": 1.01, "learning_rate": 2.32434879514244e-05, "loss": 3.4518, "step": 1634304 }, { "epoch": 1.01, "learning_rate": 2.323510200391388e-05, "loss": 3.4375, "step": 1634816 }, { "epoch": 1.01, "learning_rate": 2.322671605640336e-05, "loss": 3.4417, "step": 1635328 }, { "epoch": 1.01, "learning_rate": 2.321833010889284e-05, "loss": 3.4478, "step": 1635840 }, { "epoch": 1.01, "learning_rate": 2.3209944161382318e-05, "loss": 3.449, "step": 1636352 }, { "epoch": 1.01, "learning_rate": 2.3201574592675533e-05, "loss": 3.4316, "step": 1636864 }, { "epoch": 1.01, "learning_rate": 2.3193188645165013e-05, "loss": 3.4415, "step": 1637376 }, { "epoch": 1.01, "learning_rate": 2.318480269765449e-05, "loss": 3.4356, "step": 1637888 }, { "epoch": 1.01, "learning_rate": 2.317641675014397e-05, "loss": 3.4544, "step": 1638400 }, { "epoch": 1.01, "learning_rate": 2.316803080263345e-05, "loss": 3.4489, "step": 1638912 }, { "epoch": 1.01, "learning_rate": 2.315964485512293e-05, "loss": 3.4453, "step": 1639424 }, { "epoch": 1.01, "learning_rate": 2.315125890761241e-05, "loss": 3.4517, "step": 1639936 }, { "epoch": 1.01, "learning_rate": 2.3142889338905622e-05, "loss": 3.4438, "step": 1640448 }, { "epoch": 1.01, "learning_rate": 2.3134503391395102e-05, "loss": 3.4616, "step": 1640960 }, { "epoch": 1.01, "learning_rate": 2.3126117443884582e-05, "loss": 3.4369, "step": 1641472 }, { "epoch": 1.01, "learning_rate": 2.3117731496374062e-05, "loss": 3.4568, "step": 1641984 }, { "epoch": 1.01, "learning_rate": 2.3109345548863542e-05, "loss": 3.4459, "step": 1642496 }, { "epoch": 1.01, "learning_rate": 2.310097598015675e-05, "loss": 3.4477, "step": 1643008 }, { "epoch": 1.01, "learning_rate": 2.3092590032646235e-05, "loss": 3.4545, "step": 1643520 }, { "epoch": 1.01, "learning_rate": 2.3084204085135714e-05, "loss": 3.447, "step": 1644032 }, { "epoch": 1.01, "learning_rate": 2.3075818137625194e-05, "loss": 3.4483, "step": 1644544 }, { "epoch": 1.01, "learning_rate": 2.306743219011467e-05, "loss": 3.4515, "step": 1645056 }, { "epoch": 1.01, "learning_rate": 2.305904624260415e-05, "loss": 3.4351, "step": 1645568 }, { "epoch": 1.01, "learning_rate": 2.305066029509363e-05, "loss": 3.4465, "step": 1646080 }, { "epoch": 1.01, "learning_rate": 2.304227434758311e-05, "loss": 3.445, "step": 1646592 }, { "epoch": 1.01, "learning_rate": 2.3033904778876323e-05, "loss": 3.4537, "step": 1647104 }, { "epoch": 1.01, "learning_rate": 2.3025535210169536e-05, "loss": 3.4444, "step": 1647616 }, { "epoch": 1.01, "learning_rate": 2.3017149262659016e-05, "loss": 3.4388, "step": 1648128 }, { "epoch": 1.02, "learning_rate": 2.3008763315148492e-05, "loss": 3.4452, "step": 1648640 }, { "epoch": 1.02, "learning_rate": 2.3000377367637972e-05, "loss": 3.4464, "step": 1649152 }, { "epoch": 1.02, "learning_rate": 2.2991991420127452e-05, "loss": 3.4481, "step": 1649664 }, { "epoch": 1.02, "learning_rate": 2.2983605472616936e-05, "loss": 3.4335, "step": 1650176 }, { "epoch": 1.02, "learning_rate": 2.2975219525106416e-05, "loss": 3.4485, "step": 1650688 }, { "epoch": 1.02, "learning_rate": 2.2966833577595896e-05, "loss": 3.4592, "step": 1651200 }, { "epoch": 1.02, "learning_rate": 2.2958464008889105e-05, "loss": 3.4419, "step": 1651712 }, { "epoch": 1.02, "learning_rate": 2.2950094440182317e-05, "loss": 3.4278, "step": 1652224 }, { "epoch": 1.02, "learning_rate": 2.2941708492671797e-05, "loss": 3.4478, "step": 1652736 }, { "epoch": 1.02, "learning_rate": 2.2933322545161277e-05, "loss": 3.4467, "step": 1653248 }, { "epoch": 1.02, "learning_rate": 2.2924936597650757e-05, "loss": 3.4487, "step": 1653760 }, { "epoch": 1.02, "learning_rate": 2.2916550650140237e-05, "loss": 3.45, "step": 1654272 }, { "epoch": 1.02, "learning_rate": 2.2908164702629717e-05, "loss": 3.4382, "step": 1654784 }, { "epoch": 1.02, "learning_rate": 2.2899778755119197e-05, "loss": 3.4391, "step": 1655296 }, { "epoch": 1.02, "learning_rate": 2.2891392807608673e-05, "loss": 3.4474, "step": 1655808 }, { "epoch": 1.02, "learning_rate": 2.288302323890189e-05, "loss": 3.434, "step": 1656320 }, { "epoch": 1.02, "learning_rate": 2.287463729139137e-05, "loss": 3.4398, "step": 1656832 }, { "epoch": 1.02, "learning_rate": 2.286625134388085e-05, "loss": 3.4392, "step": 1657344 }, { "epoch": 1.02, "learning_rate": 2.2857865396370326e-05, "loss": 3.4485, "step": 1657856 }, { "epoch": 1.02, "learning_rate": 2.2849495827663538e-05, "loss": 3.4265, "step": 1658368 }, { "epoch": 1.02, "learning_rate": 2.2841109880153018e-05, "loss": 3.4393, "step": 1658880 }, { "epoch": 1.02, "learning_rate": 2.2832723932642498e-05, "loss": 3.4387, "step": 1659392 }, { "epoch": 1.02, "learning_rate": 2.2824337985131978e-05, "loss": 3.4404, "step": 1659904 }, { "epoch": 1.02, "learning_rate": 2.281596841642519e-05, "loss": 3.4456, "step": 1660416 }, { "epoch": 1.02, "learning_rate": 2.280758246891467e-05, "loss": 3.4328, "step": 1660928 }, { "epoch": 1.02, "learning_rate": 2.2799196521404147e-05, "loss": 3.4493, "step": 1661440 }, { "epoch": 1.02, "learning_rate": 2.279082695269736e-05, "loss": 3.4493, "step": 1661952 }, { "epoch": 1.02, "learning_rate": 2.2782441005186843e-05, "loss": 3.4353, "step": 1662464 }, { "epoch": 1.02, "learning_rate": 2.2774071436480052e-05, "loss": 3.4526, "step": 1662976 }, { "epoch": 1.02, "learning_rate": 2.2765685488969532e-05, "loss": 3.4389, "step": 1663488 }, { "epoch": 1.02, "learning_rate": 2.2757299541459012e-05, "loss": 3.449, "step": 1664000 }, { "epoch": 1.02, "learning_rate": 2.2748913593948492e-05, "loss": 3.4329, "step": 1664512 }, { "epoch": 1.02, "learning_rate": 2.2740544025241704e-05, "loss": 3.4437, "step": 1665024 }, { "epoch": 1.02, "learning_rate": 2.2732158077731184e-05, "loss": 3.4328, "step": 1665536 }, { "epoch": 1.02, "learning_rate": 2.2723772130220664e-05, "loss": 3.4473, "step": 1666048 }, { "epoch": 1.02, "learning_rate": 2.2715386182710144e-05, "loss": 3.4406, "step": 1666560 }, { "epoch": 1.02, "learning_rate": 2.270700023519962e-05, "loss": 3.4472, "step": 1667072 }, { "epoch": 1.02, "learning_rate": 2.26986142876891e-05, "loss": 3.4409, "step": 1667584 }, { "epoch": 1.02, "learning_rate": 2.269022834017858e-05, "loss": 3.4381, "step": 1668096 }, { "epoch": 1.02, "learning_rate": 2.2681858771471797e-05, "loss": 3.4249, "step": 1668608 }, { "epoch": 1.02, "learning_rate": 2.2673472823961273e-05, "loss": 3.456, "step": 1669120 }, { "epoch": 1.02, "learning_rate": 2.2665086876450753e-05, "loss": 3.4372, "step": 1669632 }, { "epoch": 1.02, "learning_rate": 2.2656700928940233e-05, "loss": 3.4501, "step": 1670144 }, { "epoch": 1.02, "learning_rate": 2.2648331360233446e-05, "loss": 3.4387, "step": 1670656 }, { "epoch": 1.02, "learning_rate": 2.2639945412722922e-05, "loss": 3.449, "step": 1671168 }, { "epoch": 1.02, "learning_rate": 2.2631559465212405e-05, "loss": 3.4478, "step": 1671680 }, { "epoch": 1.02, "learning_rate": 2.2623173517701885e-05, "loss": 3.4349, "step": 1672192 }, { "epoch": 1.02, "learning_rate": 2.2614787570191365e-05, "loss": 3.4456, "step": 1672704 }, { "epoch": 1.02, "learning_rate": 2.2606401622680845e-05, "loss": 3.4448, "step": 1673216 }, { "epoch": 1.02, "learning_rate": 2.2598015675170325e-05, "loss": 3.4469, "step": 1673728 }, { "epoch": 1.02, "learning_rate": 2.2589629727659802e-05, "loss": 3.462, "step": 1674240 }, { "epoch": 1.02, "learning_rate": 2.2581260158953014e-05, "loss": 3.4314, "step": 1674752 }, { "epoch": 1.02, "learning_rate": 2.2572874211442498e-05, "loss": 3.4512, "step": 1675264 }, { "epoch": 1.02, "learning_rate": 2.2564488263931978e-05, "loss": 3.4391, "step": 1675776 }, { "epoch": 1.02, "learning_rate": 2.2556102316421454e-05, "loss": 3.4479, "step": 1676288 }, { "epoch": 1.02, "learning_rate": 2.2547732747714667e-05, "loss": 3.4483, "step": 1676800 }, { "epoch": 1.02, "learning_rate": 2.2539346800204147e-05, "loss": 3.4382, "step": 1677312 }, { "epoch": 1.02, "learning_rate": 2.2530960852693627e-05, "loss": 3.4504, "step": 1677824 }, { "epoch": 1.02, "learning_rate": 2.252259128398684e-05, "loss": 3.4399, "step": 1678336 }, { "epoch": 1.02, "learning_rate": 2.251420533647632e-05, "loss": 3.4455, "step": 1678848 }, { "epoch": 1.03, "eval_loss": 3.9104843139648438, "eval_runtime": 304.8514, "eval_samples_per_second": 1251.728, "eval_steps_per_second": 39.117, "step": 1679040 }, { "epoch": 0.0, "learning_rate": 2.25058193889658e-05, "loss": 3.4366, "step": 1679360 }, { "epoch": 0.0, "learning_rate": 2.2497433441455276e-05, "loss": 3.4418, "step": 1679872 }, { "epoch": 0.0, "learning_rate": 2.2489047493944756e-05, "loss": 3.4483, "step": 1680384 }, { "epoch": 0.0, "learning_rate": 2.2480661546434235e-05, "loss": 3.4464, "step": 1680896 }, { "epoch": 0.0, "learning_rate": 2.247229197772745e-05, "loss": 3.4536, "step": 1681408 }, { "epoch": 0.0, "learning_rate": 2.2463906030216928e-05, "loss": 3.4434, "step": 1681920 }, { "epoch": 0.0, "learning_rate": 2.2455520082706408e-05, "loss": 3.4338, "step": 1682432 }, { "epoch": 0.0, "learning_rate": 2.2447134135195888e-05, "loss": 3.439, "step": 1682944 }, { "epoch": 0.0, "learning_rate": 2.2438764566489097e-05, "loss": 3.4445, "step": 1683456 }, { "epoch": 0.0, "learning_rate": 2.243037861897858e-05, "loss": 3.448, "step": 1683968 }, { "epoch": 0.0, "learning_rate": 2.242199267146806e-05, "loss": 3.4385, "step": 1684480 }, { "epoch": 0.0, "learning_rate": 2.241360672395754e-05, "loss": 3.4452, "step": 1684992 }, { "epoch": 0.0, "learning_rate": 2.240523715525075e-05, "loss": 3.4303, "step": 1685504 }, { "epoch": 0.0, "learning_rate": 2.239685120774023e-05, "loss": 3.4375, "step": 1686016 }, { "epoch": 0.0, "learning_rate": 2.238846526022971e-05, "loss": 3.4388, "step": 1686528 }, { "epoch": 0.0, "learning_rate": 2.238007931271919e-05, "loss": 3.4252, "step": 1687040 }, { "epoch": 0.0, "learning_rate": 2.23717097440124e-05, "loss": 3.4384, "step": 1687552 }, { "epoch": 0.0, "learning_rate": 2.236332379650188e-05, "loss": 3.4294, "step": 1688064 }, { "epoch": 0.0, "learning_rate": 2.235493784899136e-05, "loss": 3.434, "step": 1688576 }, { "epoch": 0.0, "learning_rate": 2.234656828028457e-05, "loss": 3.4641, "step": 1689088 }, { "epoch": 0.0, "learning_rate": 2.233818233277405e-05, "loss": 3.436, "step": 1689600 }, { "epoch": 0.0, "learning_rate": 2.2329812764067266e-05, "loss": 3.4369, "step": 1690112 }, { "epoch": 0.0, "learning_rate": 2.2321426816556746e-05, "loss": 3.4414, "step": 1690624 }, { "epoch": 0.0, "learning_rate": 2.2313040869046223e-05, "loss": 3.4463, "step": 1691136 }, { "epoch": 0.0, "learning_rate": 2.2304654921535703e-05, "loss": 3.4276, "step": 1691648 }, { "epoch": 0.0, "learning_rate": 2.2296268974025183e-05, "loss": 3.4368, "step": 1692160 }, { "epoch": 0.0, "learning_rate": 2.2287883026514663e-05, "loss": 3.4392, "step": 1692672 }, { "epoch": 0.0, "learning_rate": 2.2279497079004143e-05, "loss": 3.4277, "step": 1693184 }, { "epoch": 0.0, "learning_rate": 2.2271111131493623e-05, "loss": 3.432, "step": 1693696 }, { "epoch": 0.0, "learning_rate": 2.2262741562786835e-05, "loss": 3.4298, "step": 1694208 }, { "epoch": 0.01, "learning_rate": 2.2254355615276315e-05, "loss": 3.4394, "step": 1694720 }, { "epoch": 0.01, "learning_rate": 2.2245969667765795e-05, "loss": 3.4427, "step": 1695232 }, { "epoch": 0.01, "learning_rate": 2.2237600099059004e-05, "loss": 3.4368, "step": 1695744 }, { "epoch": 0.01, "learning_rate": 2.2229214151548484e-05, "loss": 3.4377, "step": 1696256 }, { "epoch": 0.01, "learning_rate": 2.2220828204037968e-05, "loss": 3.4371, "step": 1696768 }, { "epoch": 0.01, "learning_rate": 2.2212442256527448e-05, "loss": 3.4429, "step": 1697280 }, { "epoch": 0.01, "learning_rate": 2.2204072687820657e-05, "loss": 3.4304, "step": 1697792 }, { "epoch": 0.01, "learning_rate": 2.2195686740310137e-05, "loss": 3.4448, "step": 1698304 }, { "epoch": 0.01, "learning_rate": 2.2187300792799617e-05, "loss": 3.4241, "step": 1698816 }, { "epoch": 0.01, "learning_rate": 2.2178914845289096e-05, "loss": 3.4413, "step": 1699328 }, { "epoch": 0.01, "learning_rate": 2.217054527658231e-05, "loss": 3.4248, "step": 1699840 }, { "epoch": 0.01, "learning_rate": 2.216215932907179e-05, "loss": 3.4571, "step": 1700352 }, { "epoch": 0.01, "learning_rate": 2.215377338156127e-05, "loss": 3.4383, "step": 1700864 }, { "epoch": 0.01, "learning_rate": 2.214538743405075e-05, "loss": 3.4393, "step": 1701376 }, { "epoch": 0.01, "learning_rate": 2.2137001486540225e-05, "loss": 3.4421, "step": 1701888 }, { "epoch": 0.01, "learning_rate": 2.2128615539029705e-05, "loss": 3.4394, "step": 1702400 }, { "epoch": 0.01, "learning_rate": 2.212022959151919e-05, "loss": 3.4408, "step": 1702912 }, { "epoch": 0.01, "learning_rate": 2.211184364400867e-05, "loss": 3.4298, "step": 1703424 }, { "epoch": 0.01, "learning_rate": 2.2103474075301878e-05, "loss": 3.4173, "step": 1703936 }, { "epoch": 0.01, "learning_rate": 2.209510450659509e-05, "loss": 3.452, "step": 1704448 }, { "epoch": 0.01, "learning_rate": 2.208671855908457e-05, "loss": 3.433, "step": 1704960 }, { "epoch": 0.01, "learning_rate": 2.207833261157405e-05, "loss": 3.4457, "step": 1705472 }, { "epoch": 0.01, "learning_rate": 2.206994666406353e-05, "loss": 3.429, "step": 1705984 }, { "epoch": 0.01, "learning_rate": 2.206156071655301e-05, "loss": 3.4338, "step": 1706496 }, { "epoch": 0.01, "learning_rate": 2.2053191147846223e-05, "loss": 3.4248, "step": 1707008 }, { "epoch": 0.01, "learning_rate": 2.20448052003357e-05, "loss": 3.4418, "step": 1707520 }, { "epoch": 0.01, "learning_rate": 2.203641925282518e-05, "loss": 3.4397, "step": 1708032 }, { "epoch": 0.01, "learning_rate": 2.202803330531466e-05, "loss": 3.4448, "step": 1708544 }, { "epoch": 0.01, "learning_rate": 2.201964735780414e-05, "loss": 3.4447, "step": 1709056 }, { "epoch": 0.01, "learning_rate": 2.2011261410293622e-05, "loss": 3.4261, "step": 1709568 }, { "epoch": 0.01, "learning_rate": 2.2002875462783102e-05, "loss": 3.4323, "step": 1710080 }, { "epoch": 0.01, "learning_rate": 2.199450589407631e-05, "loss": 3.4462, "step": 1710592 }, { "epoch": 0.01, "learning_rate": 2.198611994656579e-05, "loss": 3.4241, "step": 1711104 }, { "epoch": 0.01, "learning_rate": 2.197773399905527e-05, "loss": 3.43, "step": 1711616 }, { "epoch": 0.01, "learning_rate": 2.196934805154475e-05, "loss": 3.435, "step": 1712128 }, { "epoch": 0.01, "learning_rate": 2.196096210403423e-05, "loss": 3.4424, "step": 1712640 }, { "epoch": 0.01, "learning_rate": 2.1952592535327444e-05, "loss": 3.4185, "step": 1713152 }, { "epoch": 0.01, "learning_rate": 2.1944206587816924e-05, "loss": 3.428, "step": 1713664 }, { "epoch": 0.01, "learning_rate": 2.1935820640306404e-05, "loss": 3.4286, "step": 1714176 }, { "epoch": 0.01, "learning_rate": 2.192743469279588e-05, "loss": 3.4333, "step": 1714688 }, { "epoch": 0.01, "learning_rate": 2.191904874528536e-05, "loss": 3.4382, "step": 1715200 }, { "epoch": 0.01, "learning_rate": 2.1910662797774843e-05, "loss": 3.4353, "step": 1715712 }, { "epoch": 0.01, "learning_rate": 2.1902276850264323e-05, "loss": 3.4395, "step": 1716224 }, { "epoch": 0.01, "learning_rate": 2.1893907281557533e-05, "loss": 3.4299, "step": 1716736 }, { "epoch": 0.01, "learning_rate": 2.1885521334047012e-05, "loss": 3.4507, "step": 1717248 }, { "epoch": 0.01, "learning_rate": 2.1877135386536492e-05, "loss": 3.4265, "step": 1717760 }, { "epoch": 0.01, "learning_rate": 2.1868749439025972e-05, "loss": 3.4438, "step": 1718272 }, { "epoch": 0.01, "learning_rate": 2.1860363491515452e-05, "loss": 3.4351, "step": 1718784 }, { "epoch": 0.01, "learning_rate": 2.1851977544004936e-05, "loss": 3.4342, "step": 1719296 }, { "epoch": 0.01, "learning_rate": 2.1843607975298145e-05, "loss": 3.444, "step": 1719808 }, { "epoch": 0.01, "learning_rate": 2.1835222027787625e-05, "loss": 3.4374, "step": 1720320 }, { "epoch": 0.01, "learning_rate": 2.1826836080277105e-05, "loss": 3.4336, "step": 1720832 }, { "epoch": 0.01, "learning_rate": 2.1818450132766585e-05, "loss": 3.4385, "step": 1721344 }, { "epoch": 0.01, "learning_rate": 2.181006418525606e-05, "loss": 3.4237, "step": 1721856 }, { "epoch": 0.01, "learning_rate": 2.1801678237745545e-05, "loss": 3.4314, "step": 1722368 }, { "epoch": 0.01, "learning_rate": 2.1793292290235025e-05, "loss": 3.4355, "step": 1722880 }, { "epoch": 0.01, "learning_rate": 2.1784922721528237e-05, "loss": 3.4423, "step": 1723392 }, { "epoch": 0.01, "learning_rate": 2.1776553152821446e-05, "loss": 3.4324, "step": 1723904 }, { "epoch": 0.01, "learning_rate": 2.1768167205310926e-05, "loss": 3.4281, "step": 1724416 }, { "epoch": 0.02, "learning_rate": 2.1759781257800406e-05, "loss": 3.4321, "step": 1724928 }, { "epoch": 0.02, "learning_rate": 2.1751395310289886e-05, "loss": 3.4384, "step": 1725440 }, { "epoch": 0.02, "learning_rate": 2.1743009362779366e-05, "loss": 3.4364, "step": 1725952 }, { "epoch": 0.02, "learning_rate": 2.1734623415268846e-05, "loss": 3.4215, "step": 1726464 }, { "epoch": 0.02, "learning_rate": 2.1726237467758326e-05, "loss": 3.4378, "step": 1726976 }, { "epoch": 0.02, "learning_rate": 2.1717851520247806e-05, "loss": 3.4476, "step": 1727488 }, { "epoch": 0.02, "learning_rate": 2.1709481951541015e-05, "loss": 3.4341, "step": 1728000 }, { "epoch": 0.02, "learning_rate": 2.170111238283423e-05, "loss": 3.4163, "step": 1728512 }, { "epoch": 0.02, "learning_rate": 2.169272643532371e-05, "loss": 3.4355, "step": 1729024 }, { "epoch": 0.02, "learning_rate": 2.1684340487813187e-05, "loss": 3.4287, "step": 1729536 }, { "epoch": 0.02, "learning_rate": 2.1675954540302667e-05, "loss": 3.4417, "step": 1730048 }, { "epoch": 0.02, "learning_rate": 2.1667568592792147e-05, "loss": 3.4377, "step": 1730560 }, { "epoch": 0.02, "learning_rate": 2.1659182645281627e-05, "loss": 3.4279, "step": 1731072 }, { "epoch": 0.02, "learning_rate": 2.1650796697771107e-05, "loss": 3.4266, "step": 1731584 }, { "epoch": 0.02, "learning_rate": 2.164241075026059e-05, "loss": 3.4355, "step": 1732096 }, { "epoch": 0.02, "learning_rate": 2.16340411815538e-05, "loss": 3.4232, "step": 1732608 }, { "epoch": 0.02, "learning_rate": 2.162565523404328e-05, "loss": 3.4304, "step": 1733120 }, { "epoch": 0.02, "learning_rate": 2.161726928653276e-05, "loss": 3.4268, "step": 1733632 }, { "epoch": 0.02, "learning_rate": 2.160889971782597e-05, "loss": 3.4411, "step": 1734144 }, { "epoch": 0.02, "learning_rate": 2.1600513770315452e-05, "loss": 3.4152, "step": 1734656 }, { "epoch": 0.02, "learning_rate": 2.1592127822804932e-05, "loss": 3.4244, "step": 1735168 }, { "epoch": 0.02, "learning_rate": 2.1583741875294412e-05, "loss": 3.4279, "step": 1735680 }, { "epoch": 0.02, "learning_rate": 2.157537230658762e-05, "loss": 3.4345, "step": 1736192 }, { "epoch": 0.02, "learning_rate": 2.15669863590771e-05, "loss": 3.4307, "step": 1736704 }, { "epoch": 0.02, "learning_rate": 2.155860041156658e-05, "loss": 3.4244, "step": 1737216 }, { "epoch": 0.02, "learning_rate": 2.155021446405606e-05, "loss": 3.4355, "step": 1737728 }, { "epoch": 0.02, "learning_rate": 2.1541844895349273e-05, "loss": 3.4382, "step": 1738240 }, { "epoch": 0.02, "learning_rate": 2.1533458947838753e-05, "loss": 3.4239, "step": 1738752 }, { "epoch": 0.02, "learning_rate": 2.1525089379131962e-05, "loss": 3.4444, "step": 1739264 }, { "epoch": 0.02, "learning_rate": 2.1516703431621442e-05, "loss": 3.4267, "step": 1739776 }, { "epoch": 0.02, "learning_rate": 2.1508317484110922e-05, "loss": 3.4337, "step": 1740288 }, { "epoch": 0.02, "learning_rate": 2.1499931536600406e-05, "loss": 3.4221, "step": 1740800 }, { "epoch": 0.02, "learning_rate": 2.1491561967893615e-05, "loss": 3.4308, "step": 1741312 }, { "epoch": 0.02, "learning_rate": 2.1483176020383095e-05, "loss": 3.422, "step": 1741824 }, { "epoch": 0.02, "learning_rate": 2.1474790072872575e-05, "loss": 3.4344, "step": 1742336 }, { "epoch": 0.02, "learning_rate": 2.1466404125362055e-05, "loss": 3.433, "step": 1742848 }, { "epoch": 0.02, "learning_rate": 2.1458034556655267e-05, "loss": 3.4312, "step": 1743360 }, { "epoch": 0.02, "learning_rate": 2.1449648609144747e-05, "loss": 3.4283, "step": 1743872 }, { "epoch": 0.02, "learning_rate": 2.1441262661634227e-05, "loss": 3.4295, "step": 1744384 }, { "epoch": 0.02, "learning_rate": 2.1432876714123707e-05, "loss": 3.4159, "step": 1744896 }, { "epoch": 0.02, "learning_rate": 2.1424490766613187e-05, "loss": 3.4418, "step": 1745408 }, { "epoch": 0.02, "learning_rate": 2.1416104819102663e-05, "loss": 3.4287, "step": 1745920 }, { "epoch": 0.02, "learning_rate": 2.1407718871592143e-05, "loss": 3.4362, "step": 1746432 }, { "epoch": 0.02, "learning_rate": 2.1399332924081623e-05, "loss": 3.4275, "step": 1746944 }, { "epoch": 0.02, "learning_rate": 2.139096335537484e-05, "loss": 3.4429, "step": 1747456 }, { "epoch": 0.02, "learning_rate": 2.1382577407864316e-05, "loss": 3.4325, "step": 1747968 }, { "epoch": 0.02, "learning_rate": 2.1374191460353796e-05, "loss": 3.4248, "step": 1748480 }, { "epoch": 0.02, "learning_rate": 2.1365805512843276e-05, "loss": 3.4308, "step": 1748992 }, { "epoch": 0.02, "learning_rate": 2.1357419565332756e-05, "loss": 3.4311, "step": 1749504 }, { "epoch": 0.02, "learning_rate": 2.1349033617822236e-05, "loss": 3.4353, "step": 1750016 }, { "epoch": 0.02, "learning_rate": 2.1340647670311716e-05, "loss": 3.4498, "step": 1750528 }, { "epoch": 0.02, "learning_rate": 2.1332278101604928e-05, "loss": 3.4203, "step": 1751040 }, { "epoch": 0.02, "learning_rate": 2.1323892154094408e-05, "loss": 3.4364, "step": 1751552 }, { "epoch": 0.02, "learning_rate": 2.1315506206583888e-05, "loss": 3.4281, "step": 1752064 }, { "epoch": 0.02, "learning_rate": 2.1307120259073368e-05, "loss": 3.4368, "step": 1752576 }, { "epoch": 0.02, "learning_rate": 2.1298750690366577e-05, "loss": 3.4339, "step": 1753088 }, { "epoch": 0.02, "learning_rate": 2.129036474285606e-05, "loss": 3.4279, "step": 1753600 }, { "epoch": 0.02, "learning_rate": 2.128197879534554e-05, "loss": 3.4382, "step": 1754112 }, { "epoch": 0.02, "learning_rate": 2.127360922663875e-05, "loss": 3.4279, "step": 1754624 }, { "epoch": 0.02, "learning_rate": 2.126522327912823e-05, "loss": 3.4337, "step": 1755136 }, { "epoch": 0.03, "eval_loss": 3.912721872329712, "eval_runtime": 302.5978, "eval_samples_per_second": 1261.05, "eval_steps_per_second": 39.409, "step": 1755360 }, { "epoch": 0.0, "learning_rate": 2.125683733161771e-05, "loss": 3.4297, "step": 1755648 }, { "epoch": 0.0, "learning_rate": 2.124845138410719e-05, "loss": 3.4253, "step": 1756160 }, { "epoch": 0.0, "learning_rate": 2.1240081815400402e-05, "loss": 3.4339, "step": 1756672 }, { "epoch": 0.0, "learning_rate": 2.123169586788988e-05, "loss": 3.4349, "step": 1757184 }, { "epoch": 0.0, "learning_rate": 2.122330992037936e-05, "loss": 3.4433, "step": 1757696 }, { "epoch": 0.0, "learning_rate": 2.121492397286884e-05, "loss": 3.4279, "step": 1758208 }, { "epoch": 0.0, "learning_rate": 2.1206538025358318e-05, "loss": 3.4227, "step": 1758720 }, { "epoch": 0.0, "learning_rate": 2.1198152077847798e-05, "loss": 3.4234, "step": 1759232 }, { "epoch": 0.0, "learning_rate": 2.1189766130337278e-05, "loss": 3.4378, "step": 1759744 }, { "epoch": 0.0, "learning_rate": 2.118138018282676e-05, "loss": 3.4377, "step": 1760256 }, { "epoch": 0.0, "learning_rate": 2.117301061411997e-05, "loss": 3.4248, "step": 1760768 }, { "epoch": 0.0, "learning_rate": 2.116462466660945e-05, "loss": 3.4328, "step": 1761280 }, { "epoch": 0.0, "learning_rate": 2.115623871909893e-05, "loss": 3.4233, "step": 1761792 }, { "epoch": 0.0, "learning_rate": 2.114785277158841e-05, "loss": 3.4257, "step": 1762304 }, { "epoch": 0.0, "learning_rate": 2.1139483202881623e-05, "loss": 3.4238, "step": 1762816 }, { "epoch": 0.0, "learning_rate": 2.1131097255371103e-05, "loss": 3.4168, "step": 1763328 }, { "epoch": 0.0, "learning_rate": 2.1122711307860583e-05, "loss": 3.425, "step": 1763840 }, { "epoch": 0.0, "learning_rate": 2.1114325360350063e-05, "loss": 3.422, "step": 1764352 }, { "epoch": 0.0, "learning_rate": 2.1105955791643272e-05, "loss": 3.4234, "step": 1764864 }, { "epoch": 0.0, "learning_rate": 2.1097569844132752e-05, "loss": 3.4501, "step": 1765376 }, { "epoch": 0.0, "learning_rate": 2.1089183896622232e-05, "loss": 3.4287, "step": 1765888 }, { "epoch": 0.0, "learning_rate": 2.1080814327915444e-05, "loss": 3.4236, "step": 1766400 }, { "epoch": 0.0, "learning_rate": 2.1072428380404924e-05, "loss": 3.4272, "step": 1766912 }, { "epoch": 0.0, "learning_rate": 2.1064042432894404e-05, "loss": 3.4337, "step": 1767424 }, { "epoch": 0.0, "learning_rate": 2.1055656485383884e-05, "loss": 3.4185, "step": 1767936 }, { "epoch": 0.0, "learning_rate": 2.1047270537873364e-05, "loss": 3.4286, "step": 1768448 }, { "epoch": 0.0, "learning_rate": 2.1038884590362844e-05, "loss": 3.4282, "step": 1768960 }, { "epoch": 0.0, "learning_rate": 2.1030515021656056e-05, "loss": 3.419, "step": 1769472 }, { "epoch": 0.0, "learning_rate": 2.1022129074145536e-05, "loss": 3.4174, "step": 1769984 }, { "epoch": 0.0, "learning_rate": 2.1013743126635016e-05, "loss": 3.4193, "step": 1770496 }, { "epoch": 0.01, "learning_rate": 2.1005357179124496e-05, "loss": 3.4279, "step": 1771008 }, { "epoch": 0.01, "learning_rate": 2.0996971231613973e-05, "loss": 3.4309, "step": 1771520 }, { "epoch": 0.01, "learning_rate": 2.0988585284103453e-05, "loss": 3.4262, "step": 1772032 }, { "epoch": 0.01, "learning_rate": 2.0980199336592933e-05, "loss": 3.4246, "step": 1772544 }, { "epoch": 0.01, "learning_rate": 2.0971813389082416e-05, "loss": 3.4262, "step": 1773056 }, { "epoch": 0.01, "learning_rate": 2.0963443820375625e-05, "loss": 3.4303, "step": 1773568 }, { "epoch": 0.01, "learning_rate": 2.0955057872865105e-05, "loss": 3.4257, "step": 1774080 }, { "epoch": 0.01, "learning_rate": 2.0946671925354585e-05, "loss": 3.4304, "step": 1774592 }, { "epoch": 0.01, "learning_rate": 2.0938285977844065e-05, "loss": 3.4158, "step": 1775104 }, { "epoch": 0.01, "learning_rate": 2.0929916409137278e-05, "loss": 3.4271, "step": 1775616 }, { "epoch": 0.01, "learning_rate": 2.092154684043049e-05, "loss": 3.4152, "step": 1776128 }, { "epoch": 0.01, "learning_rate": 2.091316089291997e-05, "loss": 3.44, "step": 1776640 }, { "epoch": 0.01, "learning_rate": 2.0904774945409447e-05, "loss": 3.4302, "step": 1777152 }, { "epoch": 0.01, "learning_rate": 2.0896388997898927e-05, "loss": 3.4267, "step": 1777664 }, { "epoch": 0.01, "learning_rate": 2.0888003050388407e-05, "loss": 3.4337, "step": 1778176 }, { "epoch": 0.01, "learning_rate": 2.0879617102877886e-05, "loss": 3.4251, "step": 1778688 }, { "epoch": 0.01, "learning_rate": 2.087123115536737e-05, "loss": 3.4281, "step": 1779200 }, { "epoch": 0.01, "learning_rate": 2.086284520785685e-05, "loss": 3.4181, "step": 1779712 }, { "epoch": 0.01, "learning_rate": 2.085447563915006e-05, "loss": 3.4005, "step": 1780224 }, { "epoch": 0.01, "learning_rate": 2.084608969163954e-05, "loss": 3.4428, "step": 1780736 }, { "epoch": 0.01, "learning_rate": 2.083770374412902e-05, "loss": 3.4229, "step": 1781248 }, { "epoch": 0.01, "learning_rate": 2.08293177966185e-05, "loss": 3.4352, "step": 1781760 }, { "epoch": 0.01, "learning_rate": 2.082094822791171e-05, "loss": 3.4198, "step": 1782272 }, { "epoch": 0.01, "learning_rate": 2.081256228040119e-05, "loss": 3.4238, "step": 1782784 }, { "epoch": 0.01, "learning_rate": 2.08041927116944e-05, "loss": 3.4088, "step": 1783296 }, { "epoch": 0.01, "learning_rate": 2.079580676418388e-05, "loss": 3.4306, "step": 1783808 }, { "epoch": 0.01, "learning_rate": 2.078742081667336e-05, "loss": 3.4281, "step": 1784320 }, { "epoch": 0.01, "learning_rate": 2.077903486916284e-05, "loss": 3.4283, "step": 1784832 }, { "epoch": 0.01, "learning_rate": 2.0770648921652324e-05, "loss": 3.4368, "step": 1785344 }, { "epoch": 0.01, "learning_rate": 2.07622629741418e-05, "loss": 3.4155, "step": 1785856 }, { "epoch": 0.01, "learning_rate": 2.075387702663128e-05, "loss": 3.4206, "step": 1786368 }, { "epoch": 0.01, "learning_rate": 2.0745507457924493e-05, "loss": 3.4353, "step": 1786880 }, { "epoch": 0.01, "learning_rate": 2.0737121510413972e-05, "loss": 3.4143, "step": 1787392 }, { "epoch": 0.01, "learning_rate": 2.0728735562903452e-05, "loss": 3.4168, "step": 1787904 }, { "epoch": 0.01, "learning_rate": 2.0720349615392932e-05, "loss": 3.4246, "step": 1788416 }, { "epoch": 0.01, "learning_rate": 2.0711963667882412e-05, "loss": 3.4284, "step": 1788928 }, { "epoch": 0.01, "learning_rate": 2.0703577720371892e-05, "loss": 3.4119, "step": 1789440 }, { "epoch": 0.01, "learning_rate": 2.0695191772861372e-05, "loss": 3.4164, "step": 1789952 }, { "epoch": 0.01, "learning_rate": 2.068682220415458e-05, "loss": 3.4114, "step": 1790464 }, { "epoch": 0.01, "learning_rate": 2.067843625664406e-05, "loss": 3.4206, "step": 1790976 }, { "epoch": 0.01, "learning_rate": 2.067005030913354e-05, "loss": 3.4275, "step": 1791488 }, { "epoch": 0.01, "learning_rate": 2.0661664361623025e-05, "loss": 3.4241, "step": 1792000 }, { "epoch": 0.01, "learning_rate": 2.0653278414112505e-05, "loss": 3.4229, "step": 1792512 }, { "epoch": 0.01, "learning_rate": 2.0644908845405714e-05, "loss": 3.4244, "step": 1793024 }, { "epoch": 0.01, "learning_rate": 2.0636522897895194e-05, "loss": 3.4379, "step": 1793536 }, { "epoch": 0.01, "learning_rate": 2.0628136950384674e-05, "loss": 3.4145, "step": 1794048 }, { "epoch": 0.01, "learning_rate": 2.0619751002874154e-05, "loss": 3.4344, "step": 1794560 }, { "epoch": 0.01, "learning_rate": 2.0611365055363633e-05, "loss": 3.4222, "step": 1795072 }, { "epoch": 0.01, "learning_rate": 2.0602979107853113e-05, "loss": 3.4209, "step": 1795584 }, { "epoch": 0.01, "learning_rate": 2.0594609539146326e-05, "loss": 3.4347, "step": 1796096 }, { "epoch": 0.01, "learning_rate": 2.0586223591635802e-05, "loss": 3.427, "step": 1796608 }, { "epoch": 0.01, "learning_rate": 2.0577837644125282e-05, "loss": 3.4219, "step": 1797120 }, { "epoch": 0.01, "learning_rate": 2.0569451696614762e-05, "loss": 3.4268, "step": 1797632 }, { "epoch": 0.01, "learning_rate": 2.0561065749104246e-05, "loss": 3.4147, "step": 1798144 }, { "epoch": 0.01, "learning_rate": 2.0552679801593726e-05, "loss": 3.4191, "step": 1798656 }, { "epoch": 0.01, "learning_rate": 2.0544293854083206e-05, "loss": 3.4254, "step": 1799168 }, { "epoch": 0.01, "learning_rate": 2.0535924285376415e-05, "loss": 3.4339, "step": 1799680 }, { "epoch": 0.01, "learning_rate": 2.0527554716669627e-05, "loss": 3.4168, "step": 1800192 }, { "epoch": 0.01, "learning_rate": 2.0519168769159107e-05, "loss": 3.4207, "step": 1800704 }, { "epoch": 0.02, "learning_rate": 2.0510782821648587e-05, "loss": 3.4163, "step": 1801216 }, { "epoch": 0.02, "learning_rate": 2.0502396874138067e-05, "loss": 3.4286, "step": 1801728 }, { "epoch": 0.02, "learning_rate": 2.0494010926627547e-05, "loss": 3.4272, "step": 1802240 }, { "epoch": 0.02, "learning_rate": 2.0485641357920756e-05, "loss": 3.4101, "step": 1802752 }, { "epoch": 0.02, "learning_rate": 2.0477255410410236e-05, "loss": 3.4265, "step": 1803264 }, { "epoch": 0.02, "learning_rate": 2.0468869462899716e-05, "loss": 3.4331, "step": 1803776 }, { "epoch": 0.02, "learning_rate": 2.04604835153892e-05, "loss": 3.423, "step": 1804288 }, { "epoch": 0.02, "learning_rate": 2.045211394668241e-05, "loss": 3.4062, "step": 1804800 }, { "epoch": 0.02, "learning_rate": 2.044372799917189e-05, "loss": 3.4246, "step": 1805312 }, { "epoch": 0.02, "learning_rate": 2.043534205166137e-05, "loss": 3.4165, "step": 1805824 }, { "epoch": 0.02, "learning_rate": 2.042695610415085e-05, "loss": 3.4323, "step": 1806336 }, { "epoch": 0.02, "learning_rate": 2.041857015664033e-05, "loss": 3.4285, "step": 1806848 }, { "epoch": 0.02, "learning_rate": 2.0410184209129808e-05, "loss": 3.4155, "step": 1807360 }, { "epoch": 0.02, "learning_rate": 2.0401798261619288e-05, "loss": 3.4188, "step": 1807872 }, { "epoch": 0.02, "learning_rate": 2.0393412314108768e-05, "loss": 3.4189, "step": 1808384 }, { "epoch": 0.02, "learning_rate": 2.038504274540198e-05, "loss": 3.4154, "step": 1808896 }, { "epoch": 0.02, "learning_rate": 2.0376656797891457e-05, "loss": 3.4196, "step": 1809408 }, { "epoch": 0.02, "learning_rate": 2.0368270850380937e-05, "loss": 3.4112, "step": 1809920 }, { "epoch": 0.02, "learning_rate": 2.0359884902870417e-05, "loss": 3.4315, "step": 1810432 }, { "epoch": 0.02, "learning_rate": 2.0351515334163633e-05, "loss": 3.404, "step": 1810944 }, { "epoch": 0.02, "learning_rate": 2.034312938665311e-05, "loss": 3.4127, "step": 1811456 }, { "epoch": 0.02, "learning_rate": 2.033474343914259e-05, "loss": 3.4147, "step": 1811968 }, { "epoch": 0.02, "learning_rate": 2.032635749163207e-05, "loss": 3.424, "step": 1812480 }, { "epoch": 0.02, "learning_rate": 2.0317987922925282e-05, "loss": 3.4174, "step": 1812992 }, { "epoch": 0.02, "learning_rate": 2.0309601975414762e-05, "loss": 3.4152, "step": 1813504 }, { "epoch": 0.02, "learning_rate": 2.0301216027904242e-05, "loss": 3.424, "step": 1814016 }, { "epoch": 0.02, "learning_rate": 2.0292830080393722e-05, "loss": 3.4273, "step": 1814528 }, { "epoch": 0.02, "learning_rate": 2.028446051168693e-05, "loss": 3.4119, "step": 1815040 }, { "epoch": 0.02, "learning_rate": 2.0276090942980143e-05, "loss": 3.4298, "step": 1815552 }, { "epoch": 0.02, "learning_rate": 2.0267704995469623e-05, "loss": 3.4196, "step": 1816064 }, { "epoch": 0.02, "learning_rate": 2.0259319047959103e-05, "loss": 3.4234, "step": 1816576 }, { "epoch": 0.02, "learning_rate": 2.0250933100448583e-05, "loss": 3.4113, "step": 1817088 }, { "epoch": 0.02, "learning_rate": 2.0242563531741796e-05, "loss": 3.4166, "step": 1817600 }, { "epoch": 0.02, "learning_rate": 2.0234177584231276e-05, "loss": 3.4135, "step": 1818112 }, { "epoch": 0.02, "learning_rate": 2.0225791636720756e-05, "loss": 3.4235, "step": 1818624 }, { "epoch": 0.02, "learning_rate": 2.0217405689210232e-05, "loss": 3.4249, "step": 1819136 }, { "epoch": 0.02, "learning_rate": 2.0209036120503448e-05, "loss": 3.4199, "step": 1819648 }, { "epoch": 0.02, "learning_rate": 2.0200650172992928e-05, "loss": 3.4175, "step": 1820160 }, { "epoch": 0.02, "learning_rate": 2.0192264225482405e-05, "loss": 3.4165, "step": 1820672 }, { "epoch": 0.02, "learning_rate": 2.0183878277971885e-05, "loss": 3.4026, "step": 1821184 }, { "epoch": 0.02, "learning_rate": 2.0175492330461365e-05, "loss": 3.4327, "step": 1821696 }, { "epoch": 0.02, "learning_rate": 2.0167106382950845e-05, "loss": 3.414, "step": 1822208 }, { "epoch": 0.02, "learning_rate": 2.0158720435440324e-05, "loss": 3.4253, "step": 1822720 }, { "epoch": 0.02, "learning_rate": 2.0150334487929808e-05, "loss": 3.4147, "step": 1823232 }, { "epoch": 0.02, "learning_rate": 2.0141964919223017e-05, "loss": 3.4302, "step": 1823744 }, { "epoch": 0.02, "learning_rate": 2.0133578971712497e-05, "loss": 3.4203, "step": 1824256 }, { "epoch": 0.02, "learning_rate": 2.0125193024201977e-05, "loss": 3.4131, "step": 1824768 }, { "epoch": 0.02, "learning_rate": 2.0116807076691457e-05, "loss": 3.4221, "step": 1825280 }, { "epoch": 0.02, "learning_rate": 2.0108421129180937e-05, "loss": 3.4176, "step": 1825792 }, { "epoch": 0.02, "learning_rate": 2.0100035181670417e-05, "loss": 3.4236, "step": 1826304 }, { "epoch": 0.02, "learning_rate": 2.0091649234159897e-05, "loss": 3.4449, "step": 1826816 }, { "epoch": 0.02, "learning_rate": 2.008327966545311e-05, "loss": 3.4048, "step": 1827328 }, { "epoch": 0.02, "learning_rate": 2.0074893717942586e-05, "loss": 3.4286, "step": 1827840 }, { "epoch": 0.02, "learning_rate": 2.0066507770432066e-05, "loss": 3.4155, "step": 1828352 }, { "epoch": 0.02, "learning_rate": 2.0058121822921546e-05, "loss": 3.4256, "step": 1828864 }, { "epoch": 0.02, "learning_rate": 2.0049752254214758e-05, "loss": 3.4172, "step": 1829376 }, { "epoch": 0.02, "learning_rate": 2.0041366306704238e-05, "loss": 3.4219, "step": 1829888 }, { "epoch": 0.02, "learning_rate": 2.0032980359193718e-05, "loss": 3.4261, "step": 1830400 }, { "epoch": 0.02, "learning_rate": 2.002461079048693e-05, "loss": 3.4176, "step": 1830912 }, { "epoch": 0.02, "learning_rate": 2.0016224842976407e-05, "loss": 3.4207, "step": 1831424 }, { "epoch": 0.03, "eval_loss": 3.9143993854522705, "eval_runtime": 302.9986, "eval_samples_per_second": 1259.382, "eval_steps_per_second": 39.357, "step": 1831680 }, { "epoch": 1.0, "learning_rate": 2.0007838895465887e-05, "loss": 3.42, "step": 1831936 }, { "epoch": 1.0, "learning_rate": 1.999945294795537e-05, "loss": 3.416, "step": 1832448 }, { "epoch": 1.0, "learning_rate": 1.999106700044485e-05, "loss": 3.4223, "step": 1832960 }, { "epoch": 1.0, "learning_rate": 1.998268105293433e-05, "loss": 3.4226, "step": 1833472 }, { "epoch": 1.0, "learning_rate": 1.997429510542381e-05, "loss": 3.4331, "step": 1833984 }, { "epoch": 1.0, "learning_rate": 1.996590915791329e-05, "loss": 3.417, "step": 1834496 }, { "epoch": 1.0, "learning_rate": 1.99575395892065e-05, "loss": 3.4141, "step": 1835008 }, { "epoch": 1.0, "learning_rate": 1.994915364169598e-05, "loss": 3.4188, "step": 1835520 }, { "epoch": 1.0, "learning_rate": 1.9940767694185463e-05, "loss": 3.422, "step": 1836032 }, { "epoch": 1.0, "learning_rate": 1.9932381746674943e-05, "loss": 3.4246, "step": 1836544 }, { "epoch": 1.0, "learning_rate": 1.992401217796815e-05, "loss": 3.4126, "step": 1837056 }, { "epoch": 1.0, "learning_rate": 1.991562623045763e-05, "loss": 3.4213, "step": 1837568 }, { "epoch": 1.0, "learning_rate": 1.990724028294711e-05, "loss": 3.4145, "step": 1838080 }, { "epoch": 1.0, "learning_rate": 1.9898870714240324e-05, "loss": 3.4118, "step": 1838592 }, { "epoch": 1.0, "learning_rate": 1.9890484766729804e-05, "loss": 3.4183, "step": 1839104 }, { "epoch": 1.0, "learning_rate": 1.9882098819219284e-05, "loss": 3.4041, "step": 1839616 }, { "epoch": 1.0, "learning_rate": 1.9873712871708764e-05, "loss": 3.4141, "step": 1840128 }, { "epoch": 1.0, "learning_rate": 1.9865343303001973e-05, "loss": 3.408, "step": 1840640 }, { "epoch": 1.0, "learning_rate": 1.9856957355491453e-05, "loss": 3.4131, "step": 1841152 }, { "epoch": 1.0, "learning_rate": 1.9848571407980933e-05, "loss": 3.4356, "step": 1841664 }, { "epoch": 1.0, "learning_rate": 1.9840185460470416e-05, "loss": 3.4214, "step": 1842176 }, { "epoch": 1.0, "learning_rate": 1.9831815891763625e-05, "loss": 3.4144, "step": 1842688 }, { "epoch": 1.0, "learning_rate": 1.9823429944253105e-05, "loss": 3.4182, "step": 1843200 }, { "epoch": 1.0, "learning_rate": 1.9815043996742585e-05, "loss": 3.4216, "step": 1843712 }, { "epoch": 1.0, "learning_rate": 1.9806658049232062e-05, "loss": 3.4026, "step": 1844224 }, { "epoch": 1.0, "learning_rate": 1.9798288480525278e-05, "loss": 3.4202, "step": 1844736 }, { "epoch": 1.0, "learning_rate": 1.9789902533014758e-05, "loss": 3.4175, "step": 1845248 }, { "epoch": 1.0, "learning_rate": 1.9781516585504238e-05, "loss": 3.4064, "step": 1845760 }, { "epoch": 1.0, "learning_rate": 1.9773130637993714e-05, "loss": 3.4038, "step": 1846272 }, { "epoch": 1.0, "learning_rate": 1.9764761069286927e-05, "loss": 3.4086, "step": 1846784 }, { "epoch": 1.01, "learning_rate": 1.9756375121776407e-05, "loss": 3.4162, "step": 1847296 }, { "epoch": 1.01, "learning_rate": 1.9747989174265887e-05, "loss": 3.4224, "step": 1847808 }, { "epoch": 1.01, "learning_rate": 1.9739603226755367e-05, "loss": 3.4135, "step": 1848320 }, { "epoch": 1.01, "learning_rate": 1.973123365804858e-05, "loss": 3.4155, "step": 1848832 }, { "epoch": 1.01, "learning_rate": 1.972284771053806e-05, "loss": 3.4156, "step": 1849344 }, { "epoch": 1.01, "learning_rate": 1.9714461763027536e-05, "loss": 3.4175, "step": 1849856 }, { "epoch": 1.01, "learning_rate": 1.9706075815517015e-05, "loss": 3.4165, "step": 1850368 }, { "epoch": 1.01, "learning_rate": 1.969770624681023e-05, "loss": 3.4171, "step": 1850880 }, { "epoch": 1.01, "learning_rate": 1.968932029929971e-05, "loss": 3.4028, "step": 1851392 }, { "epoch": 1.01, "learning_rate": 1.9680934351789188e-05, "loss": 3.4154, "step": 1851904 }, { "epoch": 1.01, "learning_rate": 1.96725647830824e-05, "loss": 3.4066, "step": 1852416 }, { "epoch": 1.01, "learning_rate": 1.966417883557188e-05, "loss": 3.4271, "step": 1852928 }, { "epoch": 1.01, "learning_rate": 1.965579288806136e-05, "loss": 3.4198, "step": 1853440 }, { "epoch": 1.01, "learning_rate": 1.964740694055084e-05, "loss": 3.4144, "step": 1853952 }, { "epoch": 1.01, "learning_rate": 1.963902099304032e-05, "loss": 3.4231, "step": 1854464 }, { "epoch": 1.01, "learning_rate": 1.96306350455298e-05, "loss": 3.4133, "step": 1854976 }, { "epoch": 1.01, "learning_rate": 1.962224909801928e-05, "loss": 3.42, "step": 1855488 }, { "epoch": 1.01, "learning_rate": 1.961386315050876e-05, "loss": 3.4105, "step": 1856000 }, { "epoch": 1.01, "learning_rate": 1.960549358180197e-05, "loss": 3.388, "step": 1856512 }, { "epoch": 1.01, "learning_rate": 1.959710763429145e-05, "loss": 3.429, "step": 1857024 }, { "epoch": 1.01, "learning_rate": 1.9588721686780932e-05, "loss": 3.4121, "step": 1857536 }, { "epoch": 1.01, "learning_rate": 1.9580335739270412e-05, "loss": 3.427, "step": 1858048 }, { "epoch": 1.01, "learning_rate": 1.957196617056362e-05, "loss": 3.4079, "step": 1858560 }, { "epoch": 1.01, "learning_rate": 1.95635802230531e-05, "loss": 3.4101, "step": 1859072 }, { "epoch": 1.01, "learning_rate": 1.955521065434631e-05, "loss": 3.3998, "step": 1859584 }, { "epoch": 1.01, "learning_rate": 1.9546824706835794e-05, "loss": 3.4175, "step": 1860096 }, { "epoch": 1.01, "learning_rate": 1.9538438759325274e-05, "loss": 3.4198, "step": 1860608 }, { "epoch": 1.01, "learning_rate": 1.9530052811814754e-05, "loss": 3.4172, "step": 1861120 }, { "epoch": 1.01, "learning_rate": 1.9521666864304234e-05, "loss": 3.4268, "step": 1861632 }, { "epoch": 1.01, "learning_rate": 1.9513280916793714e-05, "loss": 3.4061, "step": 1862144 }, { "epoch": 1.01, "learning_rate": 1.950489496928319e-05, "loss": 3.4066, "step": 1862656 }, { "epoch": 1.01, "learning_rate": 1.9496525400576403e-05, "loss": 3.4266, "step": 1863168 }, { "epoch": 1.01, "learning_rate": 1.9488139453065886e-05, "loss": 3.4031, "step": 1863680 }, { "epoch": 1.01, "learning_rate": 1.9479753505555366e-05, "loss": 3.405, "step": 1864192 }, { "epoch": 1.01, "learning_rate": 1.9471367558044843e-05, "loss": 3.4119, "step": 1864704 }, { "epoch": 1.01, "learning_rate": 1.9462981610534323e-05, "loss": 3.4188, "step": 1865216 }, { "epoch": 1.01, "learning_rate": 1.9454595663023803e-05, "loss": 3.3981, "step": 1865728 }, { "epoch": 1.01, "learning_rate": 1.9446209715513283e-05, "loss": 3.4075, "step": 1866240 }, { "epoch": 1.01, "learning_rate": 1.9437823768002762e-05, "loss": 3.4027, "step": 1866752 }, { "epoch": 1.01, "learning_rate": 1.9429454199295975e-05, "loss": 3.4072, "step": 1867264 }, { "epoch": 1.01, "learning_rate": 1.9421068251785455e-05, "loss": 3.4189, "step": 1867776 }, { "epoch": 1.01, "learning_rate": 1.9412682304274935e-05, "loss": 3.4093, "step": 1868288 }, { "epoch": 1.01, "learning_rate": 1.9404296356764415e-05, "loss": 3.4134, "step": 1868800 }, { "epoch": 1.01, "learning_rate": 1.9395926788057624e-05, "loss": 3.4113, "step": 1869312 }, { "epoch": 1.01, "learning_rate": 1.9387540840547104e-05, "loss": 3.4299, "step": 1869824 }, { "epoch": 1.01, "learning_rate": 1.9379154893036587e-05, "loss": 3.4026, "step": 1870336 }, { "epoch": 1.01, "learning_rate": 1.9370768945526067e-05, "loss": 3.423, "step": 1870848 }, { "epoch": 1.01, "learning_rate": 1.9362382998015547e-05, "loss": 3.4127, "step": 1871360 }, { "epoch": 1.01, "learning_rate": 1.9353997050505024e-05, "loss": 3.4087, "step": 1871872 }, { "epoch": 1.01, "learning_rate": 1.9345627481798236e-05, "loss": 3.4205, "step": 1872384 }, { "epoch": 1.01, "learning_rate": 1.9337241534287716e-05, "loss": 3.4151, "step": 1872896 }, { "epoch": 1.01, "learning_rate": 1.9328855586777196e-05, "loss": 3.4146, "step": 1873408 }, { "epoch": 1.01, "learning_rate": 1.9320469639266676e-05, "loss": 3.4139, "step": 1873920 }, { "epoch": 1.01, "learning_rate": 1.9312083691756156e-05, "loss": 3.4051, "step": 1874432 }, { "epoch": 1.01, "learning_rate": 1.9303697744245636e-05, "loss": 3.4057, "step": 1874944 }, { "epoch": 1.01, "learning_rate": 1.9295311796735116e-05, "loss": 3.4127, "step": 1875456 }, { "epoch": 1.01, "learning_rate": 1.9286925849224596e-05, "loss": 3.4203, "step": 1875968 }, { "epoch": 1.01, "learning_rate": 1.927857265932154e-05, "loss": 3.4079, "step": 1876480 }, { "epoch": 1.01, "learning_rate": 1.927018671181102e-05, "loss": 3.4102, "step": 1876992 }, { "epoch": 1.02, "learning_rate": 1.9261800764300497e-05, "loss": 3.4039, "step": 1877504 }, { "epoch": 1.02, "learning_rate": 1.9253414816789977e-05, "loss": 3.4195, "step": 1878016 }, { "epoch": 1.02, "learning_rate": 1.9245028869279457e-05, "loss": 3.4134, "step": 1878528 }, { "epoch": 1.02, "learning_rate": 1.9236642921768937e-05, "loss": 3.3992, "step": 1879040 }, { "epoch": 1.02, "learning_rate": 1.9228256974258417e-05, "loss": 3.4139, "step": 1879552 }, { "epoch": 1.02, "learning_rate": 1.9219871026747897e-05, "loss": 3.4206, "step": 1880064 }, { "epoch": 1.02, "learning_rate": 1.921150145804111e-05, "loss": 3.4135, "step": 1880576 }, { "epoch": 1.02, "learning_rate": 1.920311551053059e-05, "loss": 3.3947, "step": 1881088 }, { "epoch": 1.02, "learning_rate": 1.919472956302007e-05, "loss": 3.411, "step": 1881600 }, { "epoch": 1.02, "learning_rate": 1.918634361550955e-05, "loss": 3.4052, "step": 1882112 }, { "epoch": 1.02, "learning_rate": 1.917797404680276e-05, "loss": 3.4209, "step": 1882624 }, { "epoch": 1.02, "learning_rate": 1.9169588099292242e-05, "loss": 3.4137, "step": 1883136 }, { "epoch": 1.02, "learning_rate": 1.9161202151781722e-05, "loss": 3.4126, "step": 1883648 }, { "epoch": 1.02, "learning_rate": 1.9152816204271202e-05, "loss": 3.4062, "step": 1884160 }, { "epoch": 1.02, "learning_rate": 1.914444663556441e-05, "loss": 3.4077, "step": 1884672 }, { "epoch": 1.02, "learning_rate": 1.913606068805389e-05, "loss": 3.4068, "step": 1885184 }, { "epoch": 1.02, "learning_rate": 1.912767474054337e-05, "loss": 3.4057, "step": 1885696 }, { "epoch": 1.02, "learning_rate": 1.911928879303285e-05, "loss": 3.4006, "step": 1886208 }, { "epoch": 1.02, "learning_rate": 1.9110919224326063e-05, "loss": 3.4198, "step": 1886720 }, { "epoch": 1.02, "learning_rate": 1.9102533276815543e-05, "loss": 3.3962, "step": 1887232 }, { "epoch": 1.02, "learning_rate": 1.9094147329305023e-05, "loss": 3.396, "step": 1887744 }, { "epoch": 1.02, "learning_rate": 1.90857613817945e-05, "loss": 3.4058, "step": 1888256 }, { "epoch": 1.02, "learning_rate": 1.9077391813087712e-05, "loss": 3.4058, "step": 1888768 }, { "epoch": 1.02, "learning_rate": 1.9069005865577196e-05, "loss": 3.4094, "step": 1889280 }, { "epoch": 1.02, "learning_rate": 1.9060619918066676e-05, "loss": 3.4022, "step": 1889792 }, { "epoch": 1.02, "learning_rate": 1.9052250349359885e-05, "loss": 3.4106, "step": 1890304 }, { "epoch": 1.02, "learning_rate": 1.9043864401849365e-05, "loss": 3.4186, "step": 1890816 }, { "epoch": 1.02, "learning_rate": 1.9035478454338845e-05, "loss": 3.401, "step": 1891328 }, { "epoch": 1.02, "learning_rate": 1.9027108885632057e-05, "loss": 3.4137, "step": 1891840 }, { "epoch": 1.02, "learning_rate": 1.9018722938121537e-05, "loss": 3.41, "step": 1892352 }, { "epoch": 1.02, "learning_rate": 1.9010336990611017e-05, "loss": 3.4131, "step": 1892864 }, { "epoch": 1.02, "learning_rate": 1.9001951043100497e-05, "loss": 3.4007, "step": 1893376 }, { "epoch": 1.02, "learning_rate": 1.8993581474393706e-05, "loss": 3.4024, "step": 1893888 }, { "epoch": 1.02, "learning_rate": 1.8985195526883186e-05, "loss": 3.4031, "step": 1894400 }, { "epoch": 1.02, "learning_rate": 1.8976809579372666e-05, "loss": 3.4109, "step": 1894912 }, { "epoch": 1.02, "learning_rate": 1.896842363186215e-05, "loss": 3.4133, "step": 1895424 }, { "epoch": 1.02, "learning_rate": 1.896005406315536e-05, "loss": 3.4061, "step": 1895936 }, { "epoch": 1.02, "learning_rate": 1.895166811564484e-05, "loss": 3.4066, "step": 1896448 }, { "epoch": 1.02, "learning_rate": 1.894328216813432e-05, "loss": 3.4062, "step": 1896960 }, { "epoch": 1.02, "learning_rate": 1.8934896220623795e-05, "loss": 3.3927, "step": 1897472 }, { "epoch": 1.02, "learning_rate": 1.8926510273113275e-05, "loss": 3.4198, "step": 1897984 }, { "epoch": 1.02, "learning_rate": 1.8918124325602758e-05, "loss": 3.4011, "step": 1898496 }, { "epoch": 1.02, "learning_rate": 1.8909738378092238e-05, "loss": 3.4175, "step": 1899008 }, { "epoch": 1.02, "learning_rate": 1.8901352430581718e-05, "loss": 3.4023, "step": 1899520 }, { "epoch": 1.02, "learning_rate": 1.8892982861874927e-05, "loss": 3.4191, "step": 1900032 }, { "epoch": 1.02, "learning_rate": 1.8884596914364407e-05, "loss": 3.4109, "step": 1900544 }, { "epoch": 1.02, "learning_rate": 1.8876210966853887e-05, "loss": 3.4031, "step": 1901056 }, { "epoch": 1.02, "learning_rate": 1.8867825019343367e-05, "loss": 3.4094, "step": 1901568 }, { "epoch": 1.02, "learning_rate": 1.885943907183285e-05, "loss": 3.4079, "step": 1902080 }, { "epoch": 1.02, "learning_rate": 1.885105312432233e-05, "loss": 3.4121, "step": 1902592 }, { "epoch": 1.02, "learning_rate": 1.884268355561554e-05, "loss": 3.4318, "step": 1903104 }, { "epoch": 1.02, "learning_rate": 1.883429760810502e-05, "loss": 3.3976, "step": 1903616 }, { "epoch": 1.02, "learning_rate": 1.88259116605945e-05, "loss": 3.4205, "step": 1904128 }, { "epoch": 1.02, "learning_rate": 1.881752571308398e-05, "loss": 3.4022, "step": 1904640 }, { "epoch": 1.02, "learning_rate": 1.880913976557346e-05, "loss": 3.4108, "step": 1905152 }, { "epoch": 1.02, "learning_rate": 1.880075381806294e-05, "loss": 3.4099, "step": 1905664 }, { "epoch": 1.02, "learning_rate": 1.879236787055242e-05, "loss": 3.4089, "step": 1906176 }, { "epoch": 1.02, "learning_rate": 1.87839819230419e-05, "loss": 3.4138, "step": 1906688 }, { "epoch": 1.02, "learning_rate": 1.8775612354335108e-05, "loss": 3.413, "step": 1907200 }, { "epoch": 1.02, "learning_rate": 1.8767226406824588e-05, "loss": 3.4094, "step": 1907712 }, { "epoch": 1.03, "eval_loss": 3.9159352779388428, "eval_runtime": 305.1551, "eval_samples_per_second": 1250.482, "eval_steps_per_second": 39.078, "step": 1908000 }, { "epoch": 0.0, "learning_rate": 1.875884045931407e-05, "loss": 3.4058, "step": 1908224 }, { "epoch": 0.0, "learning_rate": 1.875045451180355e-05, "loss": 3.4063, "step": 1908736 }, { "epoch": 0.0, "learning_rate": 1.874206856429303e-05, "loss": 3.4109, "step": 1909248 }, { "epoch": 0.0, "learning_rate": 1.8733682616782508e-05, "loss": 3.4095, "step": 1909760 }, { "epoch": 0.0, "learning_rate": 1.872531304807572e-05, "loss": 3.4199, "step": 1910272 }, { "epoch": 0.0, "learning_rate": 1.87169271005652e-05, "loss": 3.4066, "step": 1910784 }, { "epoch": 0.0, "learning_rate": 1.870854115305468e-05, "loss": 3.4057, "step": 1911296 }, { "epoch": 0.0, "learning_rate": 1.870015520554416e-05, "loss": 3.4081, "step": 1911808 }, { "epoch": 0.0, "learning_rate": 1.8691785636837373e-05, "loss": 3.4093, "step": 1912320 }, { "epoch": 0.0, "learning_rate": 1.8683399689326853e-05, "loss": 3.4127, "step": 1912832 }, { "epoch": 0.0, "learning_rate": 1.8675013741816333e-05, "loss": 3.4067, "step": 1913344 }, { "epoch": 0.0, "learning_rate": 1.866662779430581e-05, "loss": 3.4067, "step": 1913856 }, { "epoch": 0.0, "learning_rate": 1.8658258225599022e-05, "loss": 3.4074, "step": 1914368 }, { "epoch": 0.0, "learning_rate": 1.8649872278088505e-05, "loss": 3.3953, "step": 1914880 }, { "epoch": 0.0, "learning_rate": 1.8641486330577982e-05, "loss": 3.4074, "step": 1915392 }, { "epoch": 0.0, "learning_rate": 1.863310038306746e-05, "loss": 3.3961, "step": 1915904 }, { "epoch": 0.0, "learning_rate": 1.8624730814360674e-05, "loss": 3.3958, "step": 1916416 }, { "epoch": 0.0, "learning_rate": 1.8616344866850154e-05, "loss": 3.3994, "step": 1916928 }, { "epoch": 0.0, "learning_rate": 1.8607958919339634e-05, "loss": 3.4029, "step": 1917440 }, { "epoch": 0.0, "learning_rate": 1.8599572971829114e-05, "loss": 3.4198, "step": 1917952 }, { "epoch": 0.0, "learning_rate": 1.8591203403122327e-05, "loss": 3.4113, "step": 1918464 }, { "epoch": 0.0, "learning_rate": 1.8582833834415536e-05, "loss": 3.4049, "step": 1918976 }, { "epoch": 0.0, "learning_rate": 1.8574447886905016e-05, "loss": 3.4065, "step": 1919488 }, { "epoch": 0.0, "learning_rate": 1.8566061939394496e-05, "loss": 3.4115, "step": 1920000 }, { "epoch": 0.0, "learning_rate": 1.8557675991883975e-05, "loss": 3.393, "step": 1920512 }, { "epoch": 0.0, "learning_rate": 1.8549290044373455e-05, "loss": 3.4082, "step": 1921024 }, { "epoch": 0.0, "learning_rate": 1.8540904096862935e-05, "loss": 3.4077, "step": 1921536 }, { "epoch": 0.0, "learning_rate": 1.8532534528156148e-05, "loss": 3.3921, "step": 1922048 }, { "epoch": 0.0, "learning_rate": 1.8524148580645628e-05, "loss": 3.3979, "step": 1922560 }, { "epoch": 0.0, "learning_rate": 1.8515762633135104e-05, "loss": 3.398, "step": 1923072 }, { "epoch": 0.01, "learning_rate": 1.8507376685624588e-05, "loss": 3.4066, "step": 1923584 }, { "epoch": 0.01, "learning_rate": 1.8498990738114068e-05, "loss": 3.4047, "step": 1924096 }, { "epoch": 0.01, "learning_rate": 1.8490604790603548e-05, "loss": 3.4047, "step": 1924608 }, { "epoch": 0.01, "learning_rate": 1.8482218843093028e-05, "loss": 3.41, "step": 1925120 }, { "epoch": 0.01, "learning_rate": 1.8473832895582508e-05, "loss": 3.3991, "step": 1925632 }, { "epoch": 0.01, "learning_rate": 1.8465463326875717e-05, "loss": 3.4063, "step": 1926144 }, { "epoch": 0.01, "learning_rate": 1.8457077379365197e-05, "loss": 3.4092, "step": 1926656 }, { "epoch": 0.01, "learning_rate": 1.844869143185468e-05, "loss": 3.4026, "step": 1927168 }, { "epoch": 0.01, "learning_rate": 1.844030548434416e-05, "loss": 3.393, "step": 1927680 }, { "epoch": 0.01, "learning_rate": 1.843193591563737e-05, "loss": 3.4048, "step": 1928192 }, { "epoch": 0.01, "learning_rate": 1.842354996812685e-05, "loss": 3.3956, "step": 1928704 }, { "epoch": 0.01, "learning_rate": 1.8415180399420058e-05, "loss": 3.4166, "step": 1929216 }, { "epoch": 0.01, "learning_rate": 1.840679445190954e-05, "loss": 3.4103, "step": 1929728 }, { "epoch": 0.01, "learning_rate": 1.839840850439902e-05, "loss": 3.4011, "step": 1930240 }, { "epoch": 0.01, "learning_rate": 1.83900225568885e-05, "loss": 3.4125, "step": 1930752 }, { "epoch": 0.01, "learning_rate": 1.838163660937798e-05, "loss": 3.4021, "step": 1931264 }, { "epoch": 0.01, "learning_rate": 1.837325066186746e-05, "loss": 3.4079, "step": 1931776 }, { "epoch": 0.01, "learning_rate": 1.8364864714356938e-05, "loss": 3.4054, "step": 1932288 }, { "epoch": 0.01, "learning_rate": 1.835649514565015e-05, "loss": 3.3712, "step": 1932800 }, { "epoch": 0.01, "learning_rate": 1.834810919813963e-05, "loss": 3.4179, "step": 1933312 }, { "epoch": 0.01, "learning_rate": 1.8339739629432843e-05, "loss": 3.403, "step": 1933824 }, { "epoch": 0.01, "learning_rate": 1.8331353681922323e-05, "loss": 3.4104, "step": 1934336 }, { "epoch": 0.01, "learning_rate": 1.8322967734411803e-05, "loss": 3.4007, "step": 1934848 }, { "epoch": 0.01, "learning_rate": 1.8314581786901283e-05, "loss": 3.4001, "step": 1935360 }, { "epoch": 0.01, "learning_rate": 1.8306212218194492e-05, "loss": 3.3912, "step": 1935872 }, { "epoch": 0.01, "learning_rate": 1.8297826270683975e-05, "loss": 3.4067, "step": 1936384 }, { "epoch": 0.01, "learning_rate": 1.8289440323173455e-05, "loss": 3.408, "step": 1936896 }, { "epoch": 0.01, "learning_rate": 1.8281054375662935e-05, "loss": 3.4052, "step": 1937408 }, { "epoch": 0.01, "learning_rate": 1.827266842815241e-05, "loss": 3.4181, "step": 1937920 }, { "epoch": 0.01, "learning_rate": 1.826428248064189e-05, "loss": 3.3976, "step": 1938432 }, { "epoch": 0.01, "learning_rate": 1.825589653313137e-05, "loss": 3.3918, "step": 1938944 }, { "epoch": 0.01, "learning_rate": 1.8247526964424584e-05, "loss": 3.4178, "step": 1939456 }, { "epoch": 0.01, "learning_rate": 1.8239141016914064e-05, "loss": 3.3932, "step": 1939968 }, { "epoch": 0.01, "learning_rate": 1.8230755069403544e-05, "loss": 3.3895, "step": 1940480 }, { "epoch": 0.01, "learning_rate": 1.8222369121893024e-05, "loss": 3.406, "step": 1940992 }, { "epoch": 0.01, "learning_rate": 1.8213983174382504e-05, "loss": 3.406, "step": 1941504 }, { "epoch": 0.01, "learning_rate": 1.8205597226871984e-05, "loss": 3.3919, "step": 1942016 }, { "epoch": 0.01, "learning_rate": 1.8197211279361464e-05, "loss": 3.3951, "step": 1942528 }, { "epoch": 0.01, "learning_rate": 1.8188825331850944e-05, "loss": 3.392, "step": 1943040 }, { "epoch": 0.01, "learning_rate": 1.8180455763144156e-05, "loss": 3.3974, "step": 1943552 }, { "epoch": 0.01, "learning_rate": 1.8172069815633636e-05, "loss": 3.408, "step": 1944064 }, { "epoch": 0.01, "learning_rate": 1.8163683868123113e-05, "loss": 3.3994, "step": 1944576 }, { "epoch": 0.01, "learning_rate": 1.8155297920612593e-05, "loss": 3.4016, "step": 1945088 }, { "epoch": 0.01, "learning_rate": 1.8146928351905805e-05, "loss": 3.3981, "step": 1945600 }, { "epoch": 0.01, "learning_rate": 1.813854240439529e-05, "loss": 3.4191, "step": 1946112 }, { "epoch": 0.01, "learning_rate": 1.8130156456884765e-05, "loss": 3.394, "step": 1946624 }, { "epoch": 0.01, "learning_rate": 1.8121770509374245e-05, "loss": 3.4128, "step": 1947136 }, { "epoch": 0.01, "learning_rate": 1.8113384561863725e-05, "loss": 3.3982, "step": 1947648 }, { "epoch": 0.01, "learning_rate": 1.8104998614353205e-05, "loss": 3.4001, "step": 1948160 }, { "epoch": 0.01, "learning_rate": 1.8096629045646414e-05, "loss": 3.4091, "step": 1948672 }, { "epoch": 0.01, "learning_rate": 1.8088243098135897e-05, "loss": 3.4092, "step": 1949184 }, { "epoch": 0.01, "learning_rate": 1.8079857150625377e-05, "loss": 3.4002, "step": 1949696 }, { "epoch": 0.01, "learning_rate": 1.8071471203114857e-05, "loss": 3.4063, "step": 1950208 }, { "epoch": 0.01, "learning_rate": 1.8063085255604337e-05, "loss": 3.3954, "step": 1950720 }, { "epoch": 0.01, "learning_rate": 1.8054699308093817e-05, "loss": 3.3931, "step": 1951232 }, { "epoch": 0.01, "learning_rate": 1.8046313360583294e-05, "loss": 3.4031, "step": 1951744 }, { "epoch": 0.01, "learning_rate": 1.8037927413072774e-05, "loss": 3.4088, "step": 1952256 }, { "epoch": 0.01, "learning_rate": 1.802957422316972e-05, "loss": 3.3969, "step": 1952768 }, { "epoch": 0.01, "learning_rate": 1.80211882756592e-05, "loss": 3.4008, "step": 1953280 }, { "epoch": 0.02, "learning_rate": 1.801280232814868e-05, "loss": 3.3966, "step": 1953792 }, { "epoch": 0.02, "learning_rate": 1.800441638063816e-05, "loss": 3.4052, "step": 1954304 }, { "epoch": 0.02, "learning_rate": 1.799603043312764e-05, "loss": 3.4042, "step": 1954816 }, { "epoch": 0.02, "learning_rate": 1.798764448561712e-05, "loss": 3.3896, "step": 1955328 }, { "epoch": 0.02, "learning_rate": 1.79792585381066e-05, "loss": 3.4047, "step": 1955840 }, { "epoch": 0.02, "learning_rate": 1.797087259059608e-05, "loss": 3.403, "step": 1956352 }, { "epoch": 0.02, "learning_rate": 1.796250302188929e-05, "loss": 3.4073, "step": 1956864 }, { "epoch": 0.02, "learning_rate": 1.79541334531825e-05, "loss": 3.3824, "step": 1957376 }, { "epoch": 0.02, "learning_rate": 1.794574750567198e-05, "loss": 3.4004, "step": 1957888 }, { "epoch": 0.02, "learning_rate": 1.793736155816146e-05, "loss": 3.3975, "step": 1958400 }, { "epoch": 0.02, "learning_rate": 1.7928975610650943e-05, "loss": 3.4092, "step": 1958912 }, { "epoch": 0.02, "learning_rate": 1.792058966314042e-05, "loss": 3.4006, "step": 1959424 }, { "epoch": 0.02, "learning_rate": 1.79122037156299e-05, "loss": 3.4028, "step": 1959936 }, { "epoch": 0.02, "learning_rate": 1.790381776811938e-05, "loss": 3.3971, "step": 1960448 }, { "epoch": 0.02, "learning_rate": 1.789543182060886e-05, "loss": 3.3952, "step": 1960960 }, { "epoch": 0.02, "learning_rate": 1.788706225190207e-05, "loss": 3.3928, "step": 1961472 }, { "epoch": 0.02, "learning_rate": 1.7878676304391552e-05, "loss": 3.3984, "step": 1961984 }, { "epoch": 0.02, "learning_rate": 1.7870290356881032e-05, "loss": 3.3945, "step": 1962496 }, { "epoch": 0.02, "learning_rate": 1.7861904409370512e-05, "loss": 3.4023, "step": 1963008 }, { "epoch": 0.02, "learning_rate": 1.785353484066372e-05, "loss": 3.3908, "step": 1963520 }, { "epoch": 0.02, "learning_rate": 1.78451488931532e-05, "loss": 3.3855, "step": 1964032 }, { "epoch": 0.02, "learning_rate": 1.783676294564268e-05, "loss": 3.3944, "step": 1964544 }, { "epoch": 0.02, "learning_rate": 1.782837699813216e-05, "loss": 3.3967, "step": 1965056 }, { "epoch": 0.02, "learning_rate": 1.7820007429425373e-05, "loss": 3.3978, "step": 1965568 }, { "epoch": 0.02, "learning_rate": 1.7811621481914853e-05, "loss": 3.3913, "step": 1966080 }, { "epoch": 0.02, "learning_rate": 1.7803235534404333e-05, "loss": 3.404, "step": 1966592 }, { "epoch": 0.02, "learning_rate": 1.7794865965697542e-05, "loss": 3.4086, "step": 1967104 }, { "epoch": 0.02, "learning_rate": 1.7786480018187022e-05, "loss": 3.392, "step": 1967616 }, { "epoch": 0.02, "learning_rate": 1.7778110449480238e-05, "loss": 3.4004, "step": 1968128 }, { "epoch": 0.02, "learning_rate": 1.7769724501969715e-05, "loss": 3.402, "step": 1968640 }, { "epoch": 0.02, "learning_rate": 1.7761338554459195e-05, "loss": 3.4004, "step": 1969152 }, { "epoch": 0.02, "learning_rate": 1.7752952606948675e-05, "loss": 3.3925, "step": 1969664 }, { "epoch": 0.02, "learning_rate": 1.7744583038241887e-05, "loss": 3.3882, "step": 1970176 }, { "epoch": 0.02, "learning_rate": 1.7736197090731367e-05, "loss": 3.3946, "step": 1970688 }, { "epoch": 0.02, "learning_rate": 1.7727811143220847e-05, "loss": 3.3987, "step": 1971200 }, { "epoch": 0.02, "learning_rate": 1.7719425195710327e-05, "loss": 3.4025, "step": 1971712 }, { "epoch": 0.02, "learning_rate": 1.771105562700354e-05, "loss": 3.4, "step": 1972224 }, { "epoch": 0.02, "learning_rate": 1.7702669679493016e-05, "loss": 3.3934, "step": 1972736 }, { "epoch": 0.02, "learning_rate": 1.7694283731982496e-05, "loss": 3.3967, "step": 1973248 }, { "epoch": 0.02, "learning_rate": 1.7685897784471976e-05, "loss": 3.3824, "step": 1973760 }, { "epoch": 0.02, "learning_rate": 1.767751183696146e-05, "loss": 3.4083, "step": 1974272 }, { "epoch": 0.02, "learning_rate": 1.766912588945094e-05, "loss": 3.391, "step": 1974784 }, { "epoch": 0.02, "learning_rate": 1.766073994194042e-05, "loss": 3.4095, "step": 1975296 }, { "epoch": 0.02, "learning_rate": 1.7652353994429896e-05, "loss": 3.3922, "step": 1975808 }, { "epoch": 0.02, "learning_rate": 1.764398442572311e-05, "loss": 3.4084, "step": 1976320 }, { "epoch": 0.02, "learning_rate": 1.7635598478212588e-05, "loss": 3.4012, "step": 1976832 }, { "epoch": 0.02, "learning_rate": 1.7627212530702068e-05, "loss": 3.3915, "step": 1977344 }, { "epoch": 0.02, "learning_rate": 1.7618826583191548e-05, "loss": 3.399, "step": 1977856 }, { "epoch": 0.02, "learning_rate": 1.7610440635681028e-05, "loss": 3.3936, "step": 1978368 }, { "epoch": 0.02, "learning_rate": 1.7602054688170508e-05, "loss": 3.4051, "step": 1978880 }, { "epoch": 0.02, "learning_rate": 1.7593668740659988e-05, "loss": 3.4171, "step": 1979392 }, { "epoch": 0.02, "learning_rate": 1.7585282793149468e-05, "loss": 3.3875, "step": 1979904 }, { "epoch": 0.02, "learning_rate": 1.7576913224442677e-05, "loss": 3.4048, "step": 1980416 }, { "epoch": 0.02, "learning_rate": 1.756852727693216e-05, "loss": 3.3934, "step": 1980928 }, { "epoch": 0.02, "learning_rate": 1.756014132942164e-05, "loss": 3.4055, "step": 1981440 }, { "epoch": 0.02, "learning_rate": 1.755177176071485e-05, "loss": 3.398, "step": 1981952 }, { "epoch": 0.02, "learning_rate": 1.754338581320433e-05, "loss": 3.4036, "step": 1982464 }, { "epoch": 0.02, "learning_rate": 1.753499986569381e-05, "loss": 3.3994, "step": 1982976 }, { "epoch": 0.02, "learning_rate": 1.7526630296987022e-05, "loss": 3.4013, "step": 1983488 }, { "epoch": 0.02, "learning_rate": 1.7518244349476502e-05, "loss": 3.4, "step": 1984000 }, { "epoch": 0.03, "eval_loss": 3.917753219604492, "eval_runtime": 308.9372, "eval_samples_per_second": 1235.173, "eval_steps_per_second": 38.6, "step": 1984320 }, { "epoch": 1.0, "learning_rate": 1.7509858401965982e-05, "loss": 3.3934, "step": 1984512 }, { "epoch": 1.0, "learning_rate": 1.7501472454455462e-05, "loss": 3.3921, "step": 1985024 }, { "epoch": 1.0, "learning_rate": 1.7493086506944942e-05, "loss": 3.3996, "step": 1985536 }, { "epoch": 1.0, "learning_rate": 1.748470055943442e-05, "loss": 3.4014, "step": 1986048 }, { "epoch": 1.0, "learning_rate": 1.7476314611923898e-05, "loss": 3.4075, "step": 1986560 }, { "epoch": 1.0, "learning_rate": 1.746792866441338e-05, "loss": 3.3969, "step": 1987072 }, { "epoch": 1.0, "learning_rate": 1.7459559095706594e-05, "loss": 3.3952, "step": 1987584 }, { "epoch": 1.0, "learning_rate": 1.7451173148196074e-05, "loss": 3.3971, "step": 1988096 }, { "epoch": 1.0, "learning_rate": 1.744278720068555e-05, "loss": 3.3949, "step": 1988608 }, { "epoch": 1.0, "learning_rate": 1.743440125317503e-05, "loss": 3.4047, "step": 1989120 }, { "epoch": 1.0, "learning_rate": 1.7426031684468243e-05, "loss": 3.3959, "step": 1989632 }, { "epoch": 1.0, "learning_rate": 1.7417645736957723e-05, "loss": 3.3928, "step": 1990144 }, { "epoch": 1.0, "learning_rate": 1.7409259789447203e-05, "loss": 3.3996, "step": 1990656 }, { "epoch": 1.0, "learning_rate": 1.7400873841936683e-05, "loss": 3.3874, "step": 1991168 }, { "epoch": 1.0, "learning_rate": 1.7392504273229895e-05, "loss": 3.396, "step": 1991680 }, { "epoch": 1.0, "learning_rate": 1.7384118325719372e-05, "loss": 3.3839, "step": 1992192 }, { "epoch": 1.0, "learning_rate": 1.7375732378208852e-05, "loss": 3.3854, "step": 1992704 }, { "epoch": 1.0, "learning_rate": 1.7367346430698332e-05, "loss": 3.393, "step": 1993216 }, { "epoch": 1.0, "learning_rate": 1.7358976861991548e-05, "loss": 3.3893, "step": 1993728 }, { "epoch": 1.0, "learning_rate": 1.7350590914481024e-05, "loss": 3.4068, "step": 1994240 }, { "epoch": 1.0, "learning_rate": 1.7342204966970504e-05, "loss": 3.4044, "step": 1994752 }, { "epoch": 1.0, "learning_rate": 1.7333835398263717e-05, "loss": 3.3916, "step": 1995264 }, { "epoch": 1.0, "learning_rate": 1.7325449450753197e-05, "loss": 3.3959, "step": 1995776 }, { "epoch": 1.0, "learning_rate": 1.7317063503242677e-05, "loss": 3.397, "step": 1996288 }, { "epoch": 1.0, "learning_rate": 1.7308677555732157e-05, "loss": 3.388, "step": 1996800 }, { "epoch": 1.0, "learning_rate": 1.730030798702537e-05, "loss": 3.398, "step": 1997312 }, { "epoch": 1.0, "learning_rate": 1.7291922039514846e-05, "loss": 3.3938, "step": 1997824 }, { "epoch": 1.0, "learning_rate": 1.7283536092004326e-05, "loss": 3.383, "step": 1998336 }, { "epoch": 1.0, "learning_rate": 1.7275150144493806e-05, "loss": 3.3868, "step": 1998848 }, { "epoch": 1.0, "learning_rate": 1.726678057578702e-05, "loss": 3.3874, "step": 1999360 }, { "epoch": 1.01, "learning_rate": 1.7258394628276498e-05, "loss": 3.3975, "step": 1999872 }, { "epoch": 1.01, "learning_rate": 1.7250008680765978e-05, "loss": 3.3935, "step": 2000384 }, { "epoch": 1.01, "learning_rate": 1.7241622733255458e-05, "loss": 3.3948, "step": 2000896 }, { "epoch": 1.01, "learning_rate": 1.723325316454867e-05, "loss": 3.3992, "step": 2001408 }, { "epoch": 1.01, "learning_rate": 1.7224867217038147e-05, "loss": 3.3864, "step": 2001920 }, { "epoch": 1.01, "learning_rate": 1.721648126952763e-05, "loss": 3.3991, "step": 2002432 }, { "epoch": 1.01, "learning_rate": 1.720809532201711e-05, "loss": 3.4012, "step": 2002944 }, { "epoch": 1.01, "learning_rate": 1.719972575331032e-05, "loss": 3.3874, "step": 2003456 }, { "epoch": 1.01, "learning_rate": 1.71913398057998e-05, "loss": 3.3889, "step": 2003968 }, { "epoch": 1.01, "learning_rate": 1.718295385828928e-05, "loss": 3.391, "step": 2004480 }, { "epoch": 1.01, "learning_rate": 1.717456791077876e-05, "loss": 3.3868, "step": 2004992 }, { "epoch": 1.01, "learning_rate": 1.7166198342071972e-05, "loss": 3.4025, "step": 2005504 }, { "epoch": 1.01, "learning_rate": 1.7157812394561452e-05, "loss": 3.3984, "step": 2006016 }, { "epoch": 1.01, "learning_rate": 1.714942644705093e-05, "loss": 3.3921, "step": 2006528 }, { "epoch": 1.01, "learning_rate": 1.714104049954041e-05, "loss": 3.4006, "step": 2007040 }, { "epoch": 1.01, "learning_rate": 1.713265455202989e-05, "loss": 3.3948, "step": 2007552 }, { "epoch": 1.01, "learning_rate": 1.712426860451937e-05, "loss": 3.3946, "step": 2008064 }, { "epoch": 1.01, "learning_rate": 1.711588265700885e-05, "loss": 3.3965, "step": 2008576 }, { "epoch": 1.01, "learning_rate": 1.7107513088302064e-05, "loss": 3.3646, "step": 2009088 }, { "epoch": 1.01, "learning_rate": 1.7099127140791544e-05, "loss": 3.4026, "step": 2009600 }, { "epoch": 1.01, "learning_rate": 1.7090757572084753e-05, "loss": 3.3893, "step": 2010112 }, { "epoch": 1.01, "learning_rate": 1.7082371624574233e-05, "loss": 3.3987, "step": 2010624 }, { "epoch": 1.01, "learning_rate": 1.7073985677063713e-05, "loss": 3.3908, "step": 2011136 }, { "epoch": 1.01, "learning_rate": 1.7065599729553193e-05, "loss": 3.3888, "step": 2011648 }, { "epoch": 1.01, "learning_rate": 1.7057230160846405e-05, "loss": 3.3823, "step": 2012160 }, { "epoch": 1.01, "learning_rate": 1.7048844213335885e-05, "loss": 3.3972, "step": 2012672 }, { "epoch": 1.01, "learning_rate": 1.7040458265825365e-05, "loss": 3.3939, "step": 2013184 }, { "epoch": 1.01, "learning_rate": 1.7032072318314845e-05, "loss": 3.3942, "step": 2013696 }, { "epoch": 1.01, "learning_rate": 1.7023686370804325e-05, "loss": 3.4084, "step": 2014208 }, { "epoch": 1.01, "learning_rate": 1.7015300423293805e-05, "loss": 3.3928, "step": 2014720 }, { "epoch": 1.01, "learning_rate": 1.7006914475783285e-05, "loss": 3.3731, "step": 2015232 }, { "epoch": 1.01, "learning_rate": 1.6998544907076498e-05, "loss": 3.4049, "step": 2015744 }, { "epoch": 1.01, "learning_rate": 1.6990158959565974e-05, "loss": 3.3836, "step": 2016256 }, { "epoch": 1.01, "learning_rate": 1.6981773012055454e-05, "loss": 3.3822, "step": 2016768 }, { "epoch": 1.01, "learning_rate": 1.6973387064544934e-05, "loss": 3.3962, "step": 2017280 }, { "epoch": 1.01, "learning_rate": 1.6965001117034414e-05, "loss": 3.3953, "step": 2017792 }, { "epoch": 1.01, "learning_rate": 1.6956615169523894e-05, "loss": 3.3804, "step": 2018304 }, { "epoch": 1.01, "learning_rate": 1.6948229222013377e-05, "loss": 3.3853, "step": 2018816 }, { "epoch": 1.01, "learning_rate": 1.6939843274502857e-05, "loss": 3.3825, "step": 2019328 }, { "epoch": 1.01, "learning_rate": 1.6931473705796066e-05, "loss": 3.386, "step": 2019840 }, { "epoch": 1.01, "learning_rate": 1.6923087758285546e-05, "loss": 3.3958, "step": 2020352 }, { "epoch": 1.01, "learning_rate": 1.6914701810775026e-05, "loss": 3.3911, "step": 2020864 }, { "epoch": 1.01, "learning_rate": 1.6906315863264506e-05, "loss": 3.3911, "step": 2021376 }, { "epoch": 1.01, "learning_rate": 1.689794629455772e-05, "loss": 3.3869, "step": 2021888 }, { "epoch": 1.01, "learning_rate": 1.68895603470472e-05, "loss": 3.4047, "step": 2022400 }, { "epoch": 1.01, "learning_rate": 1.688117439953668e-05, "loss": 3.3873, "step": 2022912 }, { "epoch": 1.01, "learning_rate": 1.6872788452026155e-05, "loss": 3.4025, "step": 2023424 }, { "epoch": 1.01, "learning_rate": 1.6864402504515635e-05, "loss": 3.3854, "step": 2023936 }, { "epoch": 1.01, "learning_rate": 1.6856016557005115e-05, "loss": 3.391, "step": 2024448 }, { "epoch": 1.01, "learning_rate": 1.684764698829833e-05, "loss": 3.3995, "step": 2024960 }, { "epoch": 1.01, "learning_rate": 1.6839261040787808e-05, "loss": 3.3983, "step": 2025472 }, { "epoch": 1.01, "learning_rate": 1.6830875093277288e-05, "loss": 3.3897, "step": 2025984 }, { "epoch": 1.01, "learning_rate": 1.6822489145766767e-05, "loss": 3.3961, "step": 2026496 }, { "epoch": 1.01, "learning_rate": 1.6814103198256247e-05, "loss": 3.3787, "step": 2027008 }, { "epoch": 1.01, "learning_rate": 1.6805717250745727e-05, "loss": 3.3845, "step": 2027520 }, { "epoch": 1.01, "learning_rate": 1.6797331303235207e-05, "loss": 3.3944, "step": 2028032 }, { "epoch": 1.01, "learning_rate": 1.6788945355724687e-05, "loss": 3.4, "step": 2028544 }, { "epoch": 1.01, "learning_rate": 1.678059216582163e-05, "loss": 3.3868, "step": 2029056 }, { "epoch": 1.01, "learning_rate": 1.677220621831111e-05, "loss": 3.3887, "step": 2029568 }, { "epoch": 1.01, "learning_rate": 1.676382027080059e-05, "loss": 3.3862, "step": 2030080 }, { "epoch": 1.02, "learning_rate": 1.675543432329007e-05, "loss": 3.392, "step": 2030592 }, { "epoch": 1.02, "learning_rate": 1.6747048375779552e-05, "loss": 3.3938, "step": 2031104 }, { "epoch": 1.02, "learning_rate": 1.6738662428269032e-05, "loss": 3.3793, "step": 2031616 }, { "epoch": 1.02, "learning_rate": 1.6730276480758512e-05, "loss": 3.3914, "step": 2032128 }, { "epoch": 1.02, "learning_rate": 1.672189053324799e-05, "loss": 3.3968, "step": 2032640 }, { "epoch": 1.02, "learning_rate": 1.67135209645412e-05, "loss": 3.3985, "step": 2033152 }, { "epoch": 1.02, "learning_rate": 1.6705151395834414e-05, "loss": 3.368, "step": 2033664 }, { "epoch": 1.02, "learning_rate": 1.6696765448323894e-05, "loss": 3.3897, "step": 2034176 }, { "epoch": 1.02, "learning_rate": 1.6688379500813373e-05, "loss": 3.3861, "step": 2034688 }, { "epoch": 1.02, "learning_rate": 1.6679993553302853e-05, "loss": 3.3971, "step": 2035200 }, { "epoch": 1.02, "learning_rate": 1.6671607605792333e-05, "loss": 3.3916, "step": 2035712 }, { "epoch": 1.02, "learning_rate": 1.666322165828181e-05, "loss": 3.3904, "step": 2036224 }, { "epoch": 1.02, "learning_rate": 1.665483571077129e-05, "loss": 3.3842, "step": 2036736 }, { "epoch": 1.02, "learning_rate": 1.664644976326077e-05, "loss": 3.388, "step": 2037248 }, { "epoch": 1.02, "learning_rate": 1.6638080194553986e-05, "loss": 3.3834, "step": 2037760 }, { "epoch": 1.02, "learning_rate": 1.6629694247043462e-05, "loss": 3.3886, "step": 2038272 }, { "epoch": 1.02, "learning_rate": 1.6621308299532942e-05, "loss": 3.3831, "step": 2038784 }, { "epoch": 1.02, "learning_rate": 1.6612922352022422e-05, "loss": 3.3931, "step": 2039296 }, { "epoch": 1.02, "learning_rate": 1.660455278331563e-05, "loss": 3.3826, "step": 2039808 }, { "epoch": 1.02, "learning_rate": 1.6596166835805115e-05, "loss": 3.3765, "step": 2040320 }, { "epoch": 1.02, "learning_rate": 1.6587780888294595e-05, "loss": 3.3809, "step": 2040832 }, { "epoch": 1.02, "learning_rate": 1.6579394940784075e-05, "loss": 3.3853, "step": 2041344 }, { "epoch": 1.02, "learning_rate": 1.6571025372077284e-05, "loss": 3.3913, "step": 2041856 }, { "epoch": 1.02, "learning_rate": 1.6562639424566764e-05, "loss": 3.3828, "step": 2042368 }, { "epoch": 1.02, "learning_rate": 1.6554253477056244e-05, "loss": 3.3886, "step": 2042880 }, { "epoch": 1.02, "learning_rate": 1.6545867529545724e-05, "loss": 3.3927, "step": 2043392 }, { "epoch": 1.02, "learning_rate": 1.6537497960838936e-05, "loss": 3.3868, "step": 2043904 }, { "epoch": 1.02, "learning_rate": 1.652912839213215e-05, "loss": 3.3917, "step": 2044416 }, { "epoch": 1.02, "learning_rate": 1.652074244462163e-05, "loss": 3.3908, "step": 2044928 }, { "epoch": 1.02, "learning_rate": 1.6512356497111105e-05, "loss": 3.3904, "step": 2045440 }, { "epoch": 1.02, "learning_rate": 1.6503970549600585e-05, "loss": 3.3809, "step": 2045952 }, { "epoch": 1.02, "learning_rate": 1.64956009808938e-05, "loss": 3.3786, "step": 2046464 }, { "epoch": 1.02, "learning_rate": 1.648721503338328e-05, "loss": 3.3865, "step": 2046976 }, { "epoch": 1.02, "learning_rate": 1.6478829085872757e-05, "loss": 3.386, "step": 2047488 }, { "epoch": 1.02, "learning_rate": 1.6470443138362237e-05, "loss": 3.3933, "step": 2048000 }, { "epoch": 1.02, "learning_rate": 1.6462057190851717e-05, "loss": 3.3905, "step": 2048512 }, { "epoch": 1.02, "learning_rate": 1.6453671243341197e-05, "loss": 3.3829, "step": 2049024 }, { "epoch": 1.02, "learning_rate": 1.6445285295830677e-05, "loss": 3.384, "step": 2049536 }, { "epoch": 1.02, "learning_rate": 1.643691572712389e-05, "loss": 3.3722, "step": 2050048 }, { "epoch": 1.02, "learning_rate": 1.642852977961337e-05, "loss": 3.3974, "step": 2050560 }, { "epoch": 1.02, "learning_rate": 1.642014383210285e-05, "loss": 3.3799, "step": 2051072 }, { "epoch": 1.02, "learning_rate": 1.641175788459233e-05, "loss": 3.3981, "step": 2051584 }, { "epoch": 1.02, "learning_rate": 1.640337193708181e-05, "loss": 3.3823, "step": 2052096 }, { "epoch": 1.02, "learning_rate": 1.6395002368375022e-05, "loss": 3.397, "step": 2052608 }, { "epoch": 1.02, "learning_rate": 1.6386616420864502e-05, "loss": 3.3924, "step": 2053120 }, { "epoch": 1.02, "learning_rate": 1.6378230473353982e-05, "loss": 3.3811, "step": 2053632 }, { "epoch": 1.02, "learning_rate": 1.6369844525843462e-05, "loss": 3.3919, "step": 2054144 }, { "epoch": 1.02, "learning_rate": 1.636145857833294e-05, "loss": 3.3804, "step": 2054656 }, { "epoch": 1.02, "learning_rate": 1.635307263082242e-05, "loss": 3.3951, "step": 2055168 }, { "epoch": 1.02, "learning_rate": 1.63446866833119e-05, "loss": 3.3992, "step": 2055680 }, { "epoch": 1.02, "learning_rate": 1.6336300735801378e-05, "loss": 3.3833, "step": 2056192 }, { "epoch": 1.02, "learning_rate": 1.632793116709459e-05, "loss": 3.3881, "step": 2056704 }, { "epoch": 1.02, "learning_rate": 1.631954521958407e-05, "loss": 3.3868, "step": 2057216 }, { "epoch": 1.02, "learning_rate": 1.631115927207355e-05, "loss": 3.3953, "step": 2057728 }, { "epoch": 1.02, "learning_rate": 1.630277332456303e-05, "loss": 3.3839, "step": 2058240 }, { "epoch": 1.02, "learning_rate": 1.629440375585624e-05, "loss": 3.3959, "step": 2058752 }, { "epoch": 1.02, "learning_rate": 1.6286017808345723e-05, "loss": 3.3818, "step": 2059264 }, { "epoch": 1.02, "learning_rate": 1.6277648239638936e-05, "loss": 3.3951, "step": 2059776 }, { "epoch": 1.02, "learning_rate": 1.6269262292128412e-05, "loss": 3.3854, "step": 2060288 }, { "epoch": 1.03, "eval_loss": 3.9191901683807373, "eval_runtime": 308.339, "eval_samples_per_second": 1237.57, "eval_steps_per_second": 38.675, "step": 2060640 }, { "epoch": 0.0, "learning_rate": 1.6260876344617892e-05, "loss": 3.3816, "step": 2060800 }, { "epoch": 0.0, "learning_rate": 1.6252490397107372e-05, "loss": 3.3808, "step": 2061312 }, { "epoch": 0.0, "learning_rate": 1.6244104449596852e-05, "loss": 3.3898, "step": 2061824 }, { "epoch": 0.0, "learning_rate": 1.6235718502086332e-05, "loss": 3.3924, "step": 2062336 }, { "epoch": 0.0, "learning_rate": 1.6227348933379544e-05, "loss": 3.4017, "step": 2062848 }, { "epoch": 0.0, "learning_rate": 1.6218962985869024e-05, "loss": 3.3865, "step": 2063360 }, { "epoch": 0.0, "learning_rate": 1.6210577038358504e-05, "loss": 3.3841, "step": 2063872 }, { "epoch": 0.0, "learning_rate": 1.6202191090847984e-05, "loss": 3.3874, "step": 2064384 }, { "epoch": 0.0, "learning_rate": 1.6193821522141193e-05, "loss": 3.3889, "step": 2064896 }, { "epoch": 0.0, "learning_rate": 1.6185435574630677e-05, "loss": 3.3891, "step": 2065408 }, { "epoch": 0.0, "learning_rate": 1.6177049627120157e-05, "loss": 3.3831, "step": 2065920 }, { "epoch": 0.0, "learning_rate": 1.6168663679609637e-05, "loss": 3.3837, "step": 2066432 }, { "epoch": 0.0, "learning_rate": 1.6160294110902846e-05, "loss": 3.3907, "step": 2066944 }, { "epoch": 0.0, "learning_rate": 1.6151908163392326e-05, "loss": 3.376, "step": 2067456 }, { "epoch": 0.0, "learning_rate": 1.6143522215881806e-05, "loss": 3.3824, "step": 2067968 }, { "epoch": 0.0, "learning_rate": 1.6135136268371286e-05, "loss": 3.3741, "step": 2068480 }, { "epoch": 0.0, "learning_rate": 1.6126766699664498e-05, "loss": 3.3713, "step": 2068992 }, { "epoch": 0.0, "learning_rate": 1.6118380752153978e-05, "loss": 3.384, "step": 2069504 }, { "epoch": 0.0, "learning_rate": 1.6109994804643458e-05, "loss": 3.3844, "step": 2070016 }, { "epoch": 0.0, "learning_rate": 1.6101608857132938e-05, "loss": 3.3926, "step": 2070528 }, { "epoch": 0.0, "learning_rate": 1.6093239288426147e-05, "loss": 3.3954, "step": 2071040 }, { "epoch": 0.0, "learning_rate": 1.608486971971936e-05, "loss": 3.3832, "step": 2071552 }, { "epoch": 0.0, "learning_rate": 1.607648377220884e-05, "loss": 3.3861, "step": 2072064 }, { "epoch": 0.0, "learning_rate": 1.606809782469832e-05, "loss": 3.3864, "step": 2072576 }, { "epoch": 0.0, "learning_rate": 1.60597118771878e-05, "loss": 3.375, "step": 2073088 }, { "epoch": 0.0, "learning_rate": 1.605132592967728e-05, "loss": 3.3921, "step": 2073600 }, { "epoch": 0.0, "learning_rate": 1.604293998216676e-05, "loss": 3.3813, "step": 2074112 }, { "epoch": 0.0, "learning_rate": 1.603455403465624e-05, "loss": 3.3726, "step": 2074624 }, { "epoch": 0.0, "learning_rate": 1.602616808714572e-05, "loss": 3.3762, "step": 2075136 }, { "epoch": 0.0, "learning_rate": 1.6017798518438932e-05, "loss": 3.3803, "step": 2075648 }, { "epoch": 0.01, "learning_rate": 1.600941257092841e-05, "loss": 3.3834, "step": 2076160 }, { "epoch": 0.01, "learning_rate": 1.6001026623417888e-05, "loss": 3.3815, "step": 2076672 }, { "epoch": 0.01, "learning_rate": 1.5992640675907368e-05, "loss": 3.3887, "step": 2077184 }, { "epoch": 0.01, "learning_rate": 1.5984271107200584e-05, "loss": 3.3843, "step": 2077696 }, { "epoch": 0.01, "learning_rate": 1.5975885159690064e-05, "loss": 3.3755, "step": 2078208 }, { "epoch": 0.01, "learning_rate": 1.596749921217954e-05, "loss": 3.3897, "step": 2078720 }, { "epoch": 0.01, "learning_rate": 1.595911326466902e-05, "loss": 3.3918, "step": 2079232 }, { "epoch": 0.01, "learning_rate": 1.5950743695962233e-05, "loss": 3.3773, "step": 2079744 }, { "epoch": 0.01, "learning_rate": 1.594235774845171e-05, "loss": 3.3799, "step": 2080256 }, { "epoch": 0.01, "learning_rate": 1.5933971800941193e-05, "loss": 3.3801, "step": 2080768 }, { "epoch": 0.01, "learning_rate": 1.5925585853430673e-05, "loss": 3.373, "step": 2081280 }, { "epoch": 0.01, "learning_rate": 1.5917232663527615e-05, "loss": 3.3891, "step": 2081792 }, { "epoch": 0.01, "learning_rate": 1.5908846716017094e-05, "loss": 3.3914, "step": 2082304 }, { "epoch": 0.01, "learning_rate": 1.5900460768506574e-05, "loss": 3.3875, "step": 2082816 }, { "epoch": 0.01, "learning_rate": 1.5892074820996054e-05, "loss": 3.385, "step": 2083328 }, { "epoch": 0.01, "learning_rate": 1.5883688873485534e-05, "loss": 3.3848, "step": 2083840 }, { "epoch": 0.01, "learning_rate": 1.5875302925975014e-05, "loss": 3.3873, "step": 2084352 }, { "epoch": 0.01, "learning_rate": 1.5866916978464494e-05, "loss": 3.3831, "step": 2084864 }, { "epoch": 0.01, "learning_rate": 1.5858547409757707e-05, "loss": 3.3573, "step": 2085376 }, { "epoch": 0.01, "learning_rate": 1.5850161462247183e-05, "loss": 3.3926, "step": 2085888 }, { "epoch": 0.01, "learning_rate": 1.5841791893540396e-05, "loss": 3.378, "step": 2086400 }, { "epoch": 0.01, "learning_rate": 1.583340594602988e-05, "loss": 3.3901, "step": 2086912 }, { "epoch": 0.01, "learning_rate": 1.582501999851936e-05, "loss": 3.3799, "step": 2087424 }, { "epoch": 0.01, "learning_rate": 1.5816634051008836e-05, "loss": 3.3784, "step": 2087936 }, { "epoch": 0.01, "learning_rate": 1.5808264482302048e-05, "loss": 3.3702, "step": 2088448 }, { "epoch": 0.01, "learning_rate": 1.5799878534791528e-05, "loss": 3.3832, "step": 2088960 }, { "epoch": 0.01, "learning_rate": 1.5791492587281008e-05, "loss": 3.3915, "step": 2089472 }, { "epoch": 0.01, "learning_rate": 1.5783106639770488e-05, "loss": 3.3796, "step": 2089984 }, { "epoch": 0.01, "learning_rate": 1.5774720692259968e-05, "loss": 3.3985, "step": 2090496 }, { "epoch": 0.01, "learning_rate": 1.5766334744749448e-05, "loss": 3.3813, "step": 2091008 }, { "epoch": 0.01, "learning_rate": 1.5757948797238928e-05, "loss": 3.366, "step": 2091520 }, { "epoch": 0.01, "learning_rate": 1.5749562849728408e-05, "loss": 3.393, "step": 2092032 }, { "epoch": 0.01, "learning_rate": 1.5741193281021617e-05, "loss": 3.3773, "step": 2092544 }, { "epoch": 0.01, "learning_rate": 1.57328073335111e-05, "loss": 3.3737, "step": 2093056 }, { "epoch": 0.01, "learning_rate": 1.572442138600058e-05, "loss": 3.3804, "step": 2093568 }, { "epoch": 0.01, "learning_rate": 1.571603543849006e-05, "loss": 3.3866, "step": 2094080 }, { "epoch": 0.01, "learning_rate": 1.570764949097954e-05, "loss": 3.3682, "step": 2094592 }, { "epoch": 0.01, "learning_rate": 1.5699263543469017e-05, "loss": 3.3755, "step": 2095104 }, { "epoch": 0.01, "learning_rate": 1.5690877595958497e-05, "loss": 3.3704, "step": 2095616 }, { "epoch": 0.01, "learning_rate": 1.568250802725171e-05, "loss": 3.3781, "step": 2096128 }, { "epoch": 0.01, "learning_rate": 1.567412207974119e-05, "loss": 3.3823, "step": 2096640 }, { "epoch": 0.01, "learning_rate": 1.566573613223067e-05, "loss": 3.3795, "step": 2097152 }, { "epoch": 0.01, "learning_rate": 1.565735018472015e-05, "loss": 3.3837, "step": 2097664 }, { "epoch": 0.01, "learning_rate": 1.564898061601336e-05, "loss": 3.3747, "step": 2098176 }, { "epoch": 0.01, "learning_rate": 1.5640594668502838e-05, "loss": 3.393, "step": 2098688 }, { "epoch": 0.01, "learning_rate": 1.5632208720992318e-05, "loss": 3.3806, "step": 2099200 }, { "epoch": 0.01, "learning_rate": 1.56238227734818e-05, "loss": 3.3944, "step": 2099712 }, { "epoch": 0.01, "learning_rate": 1.561543682597128e-05, "loss": 3.3754, "step": 2100224 }, { "epoch": 0.01, "learning_rate": 1.560705087846076e-05, "loss": 3.3768, "step": 2100736 }, { "epoch": 0.01, "learning_rate": 1.559868130975397e-05, "loss": 3.3882, "step": 2101248 }, { "epoch": 0.01, "learning_rate": 1.559029536224345e-05, "loss": 3.3843, "step": 2101760 }, { "epoch": 0.01, "learning_rate": 1.558190941473293e-05, "loss": 3.3816, "step": 2102272 }, { "epoch": 0.01, "learning_rate": 1.557352346722241e-05, "loss": 3.3876, "step": 2102784 }, { "epoch": 0.01, "learning_rate": 1.5565137519711894e-05, "loss": 3.3691, "step": 2103296 }, { "epoch": 0.01, "learning_rate": 1.555675157220137e-05, "loss": 3.3735, "step": 2103808 }, { "epoch": 0.01, "learning_rate": 1.554836562469085e-05, "loss": 3.3794, "step": 2104320 }, { "epoch": 0.01, "learning_rate": 1.553997967718033e-05, "loss": 3.3889, "step": 2104832 }, { "epoch": 0.01, "learning_rate": 1.5531626487277272e-05, "loss": 3.3756, "step": 2105344 }, { "epoch": 0.01, "learning_rate": 1.5523240539766755e-05, "loss": 3.3779, "step": 2105856 }, { "epoch": 0.01, "learning_rate": 1.5514854592256235e-05, "loss": 3.3777, "step": 2106368 }, { "epoch": 0.02, "learning_rate": 1.5506468644745715e-05, "loss": 3.3788, "step": 2106880 }, { "epoch": 0.02, "learning_rate": 1.5498082697235195e-05, "loss": 3.3833, "step": 2107392 }, { "epoch": 0.02, "learning_rate": 1.548969674972467e-05, "loss": 3.3702, "step": 2107904 }, { "epoch": 0.02, "learning_rate": 1.548131080221415e-05, "loss": 3.38, "step": 2108416 }, { "epoch": 0.02, "learning_rate": 1.547292485470363e-05, "loss": 3.3881, "step": 2108928 }, { "epoch": 0.02, "learning_rate": 1.5464555285996844e-05, "loss": 3.3861, "step": 2109440 }, { "epoch": 0.02, "learning_rate": 1.5456169338486324e-05, "loss": 3.3624, "step": 2109952 }, { "epoch": 0.02, "learning_rate": 1.5447783390975804e-05, "loss": 3.3775, "step": 2110464 }, { "epoch": 0.02, "learning_rate": 1.5439397443465284e-05, "loss": 3.3719, "step": 2110976 }, { "epoch": 0.02, "learning_rate": 1.5431027874758493e-05, "loss": 3.3897, "step": 2111488 }, { "epoch": 0.02, "learning_rate": 1.5422641927247973e-05, "loss": 3.381, "step": 2112000 }, { "epoch": 0.02, "learning_rate": 1.5414255979737456e-05, "loss": 3.3799, "step": 2112512 }, { "epoch": 0.02, "learning_rate": 1.5405870032226936e-05, "loss": 3.3727, "step": 2113024 }, { "epoch": 0.02, "learning_rate": 1.5397500463520145e-05, "loss": 3.378, "step": 2113536 }, { "epoch": 0.02, "learning_rate": 1.5389114516009625e-05, "loss": 3.3711, "step": 2114048 }, { "epoch": 0.02, "learning_rate": 1.5380728568499105e-05, "loss": 3.3774, "step": 2114560 }, { "epoch": 0.02, "learning_rate": 1.5372342620988585e-05, "loss": 3.3751, "step": 2115072 }, { "epoch": 0.02, "learning_rate": 1.5363973052281798e-05, "loss": 3.3798, "step": 2115584 }, { "epoch": 0.02, "learning_rate": 1.5355587104771278e-05, "loss": 3.3753, "step": 2116096 }, { "epoch": 0.02, "learning_rate": 1.5347201157260757e-05, "loss": 3.3643, "step": 2116608 }, { "epoch": 0.02, "learning_rate": 1.5338815209750237e-05, "loss": 3.3704, "step": 2117120 }, { "epoch": 0.02, "learning_rate": 1.5330445641043447e-05, "loss": 3.3726, "step": 2117632 }, { "epoch": 0.02, "learning_rate": 1.5322059693532926e-05, "loss": 3.3827, "step": 2118144 }, { "epoch": 0.02, "learning_rate": 1.531367374602241e-05, "loss": 3.373, "step": 2118656 }, { "epoch": 0.02, "learning_rate": 1.530528779851189e-05, "loss": 3.3804, "step": 2119168 }, { "epoch": 0.02, "learning_rate": 1.52969182298051e-05, "loss": 3.3777, "step": 2119680 }, { "epoch": 0.02, "learning_rate": 1.528853228229458e-05, "loss": 3.3786, "step": 2120192 }, { "epoch": 0.02, "learning_rate": 1.5280162713587788e-05, "loss": 3.382, "step": 2120704 }, { "epoch": 0.02, "learning_rate": 1.527177676607727e-05, "loss": 3.379, "step": 2121216 }, { "epoch": 0.02, "learning_rate": 1.526339081856675e-05, "loss": 3.3825, "step": 2121728 }, { "epoch": 0.02, "learning_rate": 1.5255004871056231e-05, "loss": 3.369, "step": 2122240 }, { "epoch": 0.02, "learning_rate": 1.524663530234944e-05, "loss": 3.3704, "step": 2122752 }, { "epoch": 0.02, "learning_rate": 1.523824935483892e-05, "loss": 3.3749, "step": 2123264 }, { "epoch": 0.02, "learning_rate": 1.5229863407328402e-05, "loss": 3.3764, "step": 2123776 }, { "epoch": 0.02, "learning_rate": 1.5221477459817882e-05, "loss": 3.3812, "step": 2124288 }, { "epoch": 0.02, "learning_rate": 1.5213107891111093e-05, "loss": 3.3781, "step": 2124800 }, { "epoch": 0.02, "learning_rate": 1.5204721943600573e-05, "loss": 3.3727, "step": 2125312 }, { "epoch": 0.02, "learning_rate": 1.5196335996090053e-05, "loss": 3.3722, "step": 2125824 }, { "epoch": 0.02, "learning_rate": 1.5187950048579532e-05, "loss": 3.3659, "step": 2126336 }, { "epoch": 0.02, "learning_rate": 1.5179564101069012e-05, "loss": 3.3824, "step": 2126848 }, { "epoch": 0.02, "learning_rate": 1.5171178153558494e-05, "loss": 3.3757, "step": 2127360 }, { "epoch": 0.02, "learning_rate": 1.516279220604797e-05, "loss": 3.392, "step": 2127872 }, { "epoch": 0.02, "learning_rate": 1.515440625853745e-05, "loss": 3.3703, "step": 2128384 }, { "epoch": 0.02, "learning_rate": 1.5146036689830665e-05, "loss": 3.3834, "step": 2128896 }, { "epoch": 0.02, "learning_rate": 1.5137650742320145e-05, "loss": 3.382, "step": 2129408 }, { "epoch": 0.02, "learning_rate": 1.5129264794809623e-05, "loss": 3.3739, "step": 2129920 }, { "epoch": 0.02, "learning_rate": 1.5120878847299103e-05, "loss": 3.377, "step": 2130432 }, { "epoch": 0.02, "learning_rate": 1.5112492899788583e-05, "loss": 3.3743, "step": 2130944 }, { "epoch": 0.02, "learning_rate": 1.5104106952278063e-05, "loss": 3.3848, "step": 2131456 }, { "epoch": 0.02, "learning_rate": 1.5095721004767543e-05, "loss": 3.3873, "step": 2131968 }, { "epoch": 0.02, "learning_rate": 1.5087335057257024e-05, "loss": 3.3779, "step": 2132480 }, { "epoch": 0.02, "learning_rate": 1.5078965488550234e-05, "loss": 3.3726, "step": 2132992 }, { "epoch": 0.02, "learning_rate": 1.5070579541039714e-05, "loss": 3.3802, "step": 2133504 }, { "epoch": 0.02, "learning_rate": 1.5062193593529195e-05, "loss": 3.3852, "step": 2134016 }, { "epoch": 0.02, "learning_rate": 1.5053807646018675e-05, "loss": 3.3709, "step": 2134528 }, { "epoch": 0.02, "learning_rate": 1.5045438077311886e-05, "loss": 3.3883, "step": 2135040 }, { "epoch": 0.02, "learning_rate": 1.5037052129801366e-05, "loss": 3.3746, "step": 2135552 }, { "epoch": 0.02, "learning_rate": 1.5028666182290846e-05, "loss": 3.3859, "step": 2136064 }, { "epoch": 0.02, "learning_rate": 1.5020296613584057e-05, "loss": 3.3739, "step": 2136576 }, { "epoch": 0.03, "eval_loss": 3.920938491821289, "eval_runtime": 304.1431, "eval_samples_per_second": 1254.643, "eval_steps_per_second": 39.209, "step": 2136960 }, { "epoch": 1.0, "learning_rate": 1.5011910666073537e-05, "loss": 3.3766, "step": 2137088 }, { "epoch": 1.0, "learning_rate": 1.5003524718563017e-05, "loss": 3.3677, "step": 2137600 }, { "epoch": 1.0, "learning_rate": 1.4995138771052497e-05, "loss": 3.3787, "step": 2138112 }, { "epoch": 1.0, "learning_rate": 1.4986769202345707e-05, "loss": 3.3812, "step": 2138624 }, { "epoch": 1.0, "learning_rate": 1.4978383254835187e-05, "loss": 3.3878, "step": 2139136 }, { "epoch": 1.0, "learning_rate": 1.4969997307324667e-05, "loss": 3.3789, "step": 2139648 }, { "epoch": 1.0, "learning_rate": 1.4961611359814149e-05, "loss": 3.3742, "step": 2140160 }, { "epoch": 1.0, "learning_rate": 1.4953241791107358e-05, "loss": 3.3774, "step": 2140672 }, { "epoch": 1.0, "learning_rate": 1.494485584359684e-05, "loss": 3.3762, "step": 2141184 }, { "epoch": 1.0, "learning_rate": 1.493646989608632e-05, "loss": 3.3784, "step": 2141696 }, { "epoch": 1.0, "learning_rate": 1.49280839485758e-05, "loss": 3.376, "step": 2142208 }, { "epoch": 1.0, "learning_rate": 1.491971437986901e-05, "loss": 3.374, "step": 2142720 }, { "epoch": 1.0, "learning_rate": 1.491132843235849e-05, "loss": 3.384, "step": 2143232 }, { "epoch": 1.0, "learning_rate": 1.490294248484797e-05, "loss": 3.3632, "step": 2143744 }, { "epoch": 1.0, "learning_rate": 1.4894556537337448e-05, "loss": 3.3725, "step": 2144256 }, { "epoch": 1.0, "learning_rate": 1.4886186968630661e-05, "loss": 3.3659, "step": 2144768 }, { "epoch": 1.0, "learning_rate": 1.4877801021120141e-05, "loss": 3.3598, "step": 2145280 }, { "epoch": 1.0, "learning_rate": 1.4869415073609621e-05, "loss": 3.3739, "step": 2145792 }, { "epoch": 1.0, "learning_rate": 1.4861029126099099e-05, "loss": 3.3722, "step": 2146304 }, { "epoch": 1.0, "learning_rate": 1.4852659557392312e-05, "loss": 3.3827, "step": 2146816 }, { "epoch": 1.0, "learning_rate": 1.4844273609881793e-05, "loss": 3.3835, "step": 2147328 }, { "epoch": 1.0, "learning_rate": 1.4835887662371273e-05, "loss": 3.3734, "step": 2147840 }, { "epoch": 1.0, "learning_rate": 1.482750171486075e-05, "loss": 3.3746, "step": 2148352 }, { "epoch": 1.0, "learning_rate": 1.4819132146153964e-05, "loss": 3.3758, "step": 2148864 }, { "epoch": 1.0, "learning_rate": 1.4810746198643444e-05, "loss": 3.3613, "step": 2149376 }, { "epoch": 1.0, "learning_rate": 1.480236025113292e-05, "loss": 3.3857, "step": 2149888 }, { "epoch": 1.0, "learning_rate": 1.4793974303622402e-05, "loss": 3.3669, "step": 2150400 }, { "epoch": 1.0, "learning_rate": 1.4785604734915615e-05, "loss": 3.363, "step": 2150912 }, { "epoch": 1.0, "learning_rate": 1.4777218787405095e-05, "loss": 3.3686, "step": 2151424 }, { "epoch": 1.0, "learning_rate": 1.4768832839894573e-05, "loss": 3.3678, "step": 2151936 }, { "epoch": 1.01, "learning_rate": 1.4760446892384053e-05, "loss": 3.3731, "step": 2152448 }, { "epoch": 1.01, "learning_rate": 1.4752077323677265e-05, "loss": 3.3684, "step": 2152960 }, { "epoch": 1.01, "learning_rate": 1.4743691376166747e-05, "loss": 3.3819, "step": 2153472 }, { "epoch": 1.01, "learning_rate": 1.4735305428656224e-05, "loss": 3.3715, "step": 2153984 }, { "epoch": 1.01, "learning_rate": 1.4726919481145703e-05, "loss": 3.3665, "step": 2154496 }, { "epoch": 1.01, "learning_rate": 1.4718549912438918e-05, "loss": 3.3756, "step": 2155008 }, { "epoch": 1.01, "learning_rate": 1.4710163964928394e-05, "loss": 3.3823, "step": 2155520 }, { "epoch": 1.01, "learning_rate": 1.4701778017417874e-05, "loss": 3.3675, "step": 2156032 }, { "epoch": 1.01, "learning_rate": 1.4693392069907356e-05, "loss": 3.3666, "step": 2156544 }, { "epoch": 1.01, "learning_rate": 1.4685022501200568e-05, "loss": 3.3716, "step": 2157056 }, { "epoch": 1.01, "learning_rate": 1.4676636553690047e-05, "loss": 3.3669, "step": 2157568 }, { "epoch": 1.01, "learning_rate": 1.4668266984983259e-05, "loss": 3.3772, "step": 2158080 }, { "epoch": 1.01, "learning_rate": 1.4659881037472739e-05, "loss": 3.3794, "step": 2158592 }, { "epoch": 1.01, "learning_rate": 1.4651495089962219e-05, "loss": 3.3782, "step": 2159104 }, { "epoch": 1.01, "learning_rate": 1.4643109142451697e-05, "loss": 3.3767, "step": 2159616 }, { "epoch": 1.01, "learning_rate": 1.4634723194941177e-05, "loss": 3.3728, "step": 2160128 }, { "epoch": 1.01, "learning_rate": 1.4626337247430657e-05, "loss": 3.3751, "step": 2160640 }, { "epoch": 1.01, "learning_rate": 1.4617951299920137e-05, "loss": 3.3717, "step": 2161152 }, { "epoch": 1.01, "learning_rate": 1.4609565352409619e-05, "loss": 3.3458, "step": 2161664 }, { "epoch": 1.01, "learning_rate": 1.4601195783702828e-05, "loss": 3.3813, "step": 2162176 }, { "epoch": 1.01, "learning_rate": 1.459280983619231e-05, "loss": 3.3702, "step": 2162688 }, { "epoch": 1.01, "learning_rate": 1.458442388868179e-05, "loss": 3.3801, "step": 2163200 }, { "epoch": 1.01, "learning_rate": 1.4576054319974999e-05, "loss": 3.3686, "step": 2163712 }, { "epoch": 1.01, "learning_rate": 1.456766837246448e-05, "loss": 3.3707, "step": 2164224 }, { "epoch": 1.01, "learning_rate": 1.4559298803757693e-05, "loss": 3.3584, "step": 2164736 }, { "epoch": 1.01, "learning_rate": 1.4550912856247171e-05, "loss": 3.3678, "step": 2165248 }, { "epoch": 1.01, "learning_rate": 1.4542526908736651e-05, "loss": 3.3832, "step": 2165760 }, { "epoch": 1.01, "learning_rate": 1.453414096122613e-05, "loss": 3.3719, "step": 2166272 }, { "epoch": 1.01, "learning_rate": 1.452575501371561e-05, "loss": 3.387, "step": 2166784 }, { "epoch": 1.01, "learning_rate": 1.451736906620509e-05, "loss": 3.3708, "step": 2167296 }, { "epoch": 1.01, "learning_rate": 1.4508983118694572e-05, "loss": 3.3535, "step": 2167808 }, { "epoch": 1.01, "learning_rate": 1.4500597171184049e-05, "loss": 3.3863, "step": 2168320 }, { "epoch": 1.01, "learning_rate": 1.4492227602477263e-05, "loss": 3.3666, "step": 2168832 }, { "epoch": 1.01, "learning_rate": 1.4483841654966743e-05, "loss": 3.3613, "step": 2169344 }, { "epoch": 1.01, "learning_rate": 1.4475455707456223e-05, "loss": 3.374, "step": 2169856 }, { "epoch": 1.01, "learning_rate": 1.4467069759945701e-05, "loss": 3.3738, "step": 2170368 }, { "epoch": 1.01, "learning_rate": 1.4458683812435181e-05, "loss": 3.3614, "step": 2170880 }, { "epoch": 1.01, "learning_rate": 1.4450297864924661e-05, "loss": 3.3633, "step": 2171392 }, { "epoch": 1.01, "learning_rate": 1.4441911917414141e-05, "loss": 3.3635, "step": 2171904 }, { "epoch": 1.01, "learning_rate": 1.4433542348707352e-05, "loss": 3.3634, "step": 2172416 }, { "epoch": 1.01, "learning_rate": 1.4425156401196832e-05, "loss": 3.377, "step": 2172928 }, { "epoch": 1.01, "learning_rate": 1.4416770453686312e-05, "loss": 3.3705, "step": 2173440 }, { "epoch": 1.01, "learning_rate": 1.4408384506175794e-05, "loss": 3.3689, "step": 2173952 }, { "epoch": 1.01, "learning_rate": 1.4400014937469003e-05, "loss": 3.3641, "step": 2174464 }, { "epoch": 1.01, "learning_rate": 1.4391628989958483e-05, "loss": 3.3855, "step": 2174976 }, { "epoch": 1.01, "learning_rate": 1.4383243042447964e-05, "loss": 3.3685, "step": 2175488 }, { "epoch": 1.01, "learning_rate": 1.4374857094937444e-05, "loss": 3.3821, "step": 2176000 }, { "epoch": 1.01, "learning_rate": 1.4366471147426924e-05, "loss": 3.3637, "step": 2176512 }, { "epoch": 1.01, "learning_rate": 1.4358085199916404e-05, "loss": 3.3696, "step": 2177024 }, { "epoch": 1.01, "learning_rate": 1.4349715631209615e-05, "loss": 3.3801, "step": 2177536 }, { "epoch": 1.01, "learning_rate": 1.4341329683699095e-05, "loss": 3.3744, "step": 2178048 }, { "epoch": 1.01, "learning_rate": 1.4332943736188575e-05, "loss": 3.3736, "step": 2178560 }, { "epoch": 1.01, "learning_rate": 1.4324557788678053e-05, "loss": 3.3778, "step": 2179072 }, { "epoch": 1.01, "learning_rate": 1.4316171841167533e-05, "loss": 3.3611, "step": 2179584 }, { "epoch": 1.01, "learning_rate": 1.4307785893657013e-05, "loss": 3.3621, "step": 2180096 }, { "epoch": 1.01, "learning_rate": 1.4299399946146495e-05, "loss": 3.3703, "step": 2180608 }, { "epoch": 1.01, "learning_rate": 1.4291013998635975e-05, "loss": 3.377, "step": 2181120 }, { "epoch": 1.01, "learning_rate": 1.4282660808732918e-05, "loss": 3.3657, "step": 2181632 }, { "epoch": 1.01, "learning_rate": 1.4274274861222398e-05, "loss": 3.3698, "step": 2182144 }, { "epoch": 1.01, "learning_rate": 1.4265888913711878e-05, "loss": 3.3667, "step": 2182656 }, { "epoch": 1.02, "learning_rate": 1.4257502966201356e-05, "loss": 3.3702, "step": 2183168 }, { "epoch": 1.02, "learning_rate": 1.4249117018690836e-05, "loss": 3.3715, "step": 2183680 }, { "epoch": 1.02, "learning_rate": 1.4240731071180316e-05, "loss": 3.3634, "step": 2184192 }, { "epoch": 1.02, "learning_rate": 1.4232345123669796e-05, "loss": 3.369, "step": 2184704 }, { "epoch": 1.02, "learning_rate": 1.4223959176159276e-05, "loss": 3.3781, "step": 2185216 }, { "epoch": 1.02, "learning_rate": 1.4215589607452487e-05, "loss": 3.3791, "step": 2185728 }, { "epoch": 1.02, "learning_rate": 1.42072200387457e-05, "loss": 3.3489, "step": 2186240 }, { "epoch": 1.02, "learning_rate": 1.4198834091235177e-05, "loss": 3.369, "step": 2186752 }, { "epoch": 1.02, "learning_rate": 1.4190448143724657e-05, "loss": 3.3623, "step": 2187264 }, { "epoch": 1.02, "learning_rate": 1.4182062196214137e-05, "loss": 3.3802, "step": 2187776 }, { "epoch": 1.02, "learning_rate": 1.4173676248703619e-05, "loss": 3.3729, "step": 2188288 }, { "epoch": 1.02, "learning_rate": 1.4165290301193099e-05, "loss": 3.3682, "step": 2188800 }, { "epoch": 1.02, "learning_rate": 1.4156904353682579e-05, "loss": 3.3613, "step": 2189312 }, { "epoch": 1.02, "learning_rate": 1.4148518406172059e-05, "loss": 3.3687, "step": 2189824 }, { "epoch": 1.02, "learning_rate": 1.414014883746527e-05, "loss": 3.3627, "step": 2190336 }, { "epoch": 1.02, "learning_rate": 1.413176288995475e-05, "loss": 3.3641, "step": 2190848 }, { "epoch": 1.02, "learning_rate": 1.412337694244423e-05, "loss": 3.3618, "step": 2191360 }, { "epoch": 1.02, "learning_rate": 1.4114990994933708e-05, "loss": 3.3676, "step": 2191872 }, { "epoch": 1.02, "learning_rate": 1.410662142622692e-05, "loss": 3.3648, "step": 2192384 }, { "epoch": 1.02, "learning_rate": 1.4098235478716402e-05, "loss": 3.3543, "step": 2192896 }, { "epoch": 1.02, "learning_rate": 1.4089849531205882e-05, "loss": 3.3609, "step": 2193408 }, { "epoch": 1.02, "learning_rate": 1.4081463583695358e-05, "loss": 3.3591, "step": 2193920 }, { "epoch": 1.02, "learning_rate": 1.4073094014988573e-05, "loss": 3.373, "step": 2194432 }, { "epoch": 1.02, "learning_rate": 1.4064708067478053e-05, "loss": 3.36, "step": 2194944 }, { "epoch": 1.02, "learning_rate": 1.4056322119967533e-05, "loss": 3.3697, "step": 2195456 }, { "epoch": 1.02, "learning_rate": 1.404793617245701e-05, "loss": 3.3709, "step": 2195968 }, { "epoch": 1.02, "learning_rate": 1.4039566603750223e-05, "loss": 3.3698, "step": 2196480 }, { "epoch": 1.02, "learning_rate": 1.4031197035043434e-05, "loss": 3.3684, "step": 2196992 }, { "epoch": 1.02, "learning_rate": 1.4022811087532914e-05, "loss": 3.371, "step": 2197504 }, { "epoch": 1.02, "learning_rate": 1.4014425140022394e-05, "loss": 3.3735, "step": 2198016 }, { "epoch": 1.02, "learning_rate": 1.4006039192511874e-05, "loss": 3.3576, "step": 2198528 }, { "epoch": 1.02, "learning_rate": 1.3997653245001354e-05, "loss": 3.3557, "step": 2199040 }, { "epoch": 1.02, "learning_rate": 1.3989283676294565e-05, "loss": 3.3662, "step": 2199552 }, { "epoch": 1.02, "learning_rate": 1.3980897728784045e-05, "loss": 3.3657, "step": 2200064 }, { "epoch": 1.02, "learning_rate": 1.3972511781273526e-05, "loss": 3.3701, "step": 2200576 }, { "epoch": 1.02, "learning_rate": 1.3964142212566735e-05, "loss": 3.3649, "step": 2201088 }, { "epoch": 1.02, "learning_rate": 1.3955756265056217e-05, "loss": 3.3633, "step": 2201600 }, { "epoch": 1.02, "learning_rate": 1.3947370317545697e-05, "loss": 3.3649, "step": 2202112 }, { "epoch": 1.02, "learning_rate": 1.3938984370035177e-05, "loss": 3.3558, "step": 2202624 }, { "epoch": 1.02, "learning_rate": 1.3930598422524655e-05, "loss": 3.3671, "step": 2203136 }, { "epoch": 1.02, "learning_rate": 1.3922212475014135e-05, "loss": 3.3664, "step": 2203648 }, { "epoch": 1.02, "learning_rate": 1.3913826527503615e-05, "loss": 3.3815, "step": 2204160 }, { "epoch": 1.02, "learning_rate": 1.3905440579993095e-05, "loss": 3.361, "step": 2204672 }, { "epoch": 1.02, "learning_rate": 1.3897071011286306e-05, "loss": 3.3689, "step": 2205184 }, { "epoch": 1.02, "learning_rate": 1.3888685063775786e-05, "loss": 3.3717, "step": 2205696 }, { "epoch": 1.02, "learning_rate": 1.3880299116265266e-05, "loss": 3.3628, "step": 2206208 }, { "epoch": 1.02, "learning_rate": 1.3871913168754746e-05, "loss": 3.3609, "step": 2206720 }, { "epoch": 1.02, "learning_rate": 1.3863527221244227e-05, "loss": 3.3651, "step": 2207232 }, { "epoch": 1.02, "learning_rate": 1.3855141273733707e-05, "loss": 3.376, "step": 2207744 }, { "epoch": 1.02, "learning_rate": 1.3846755326223184e-05, "loss": 3.379, "step": 2208256 }, { "epoch": 1.02, "learning_rate": 1.3838369378712666e-05, "loss": 3.3681, "step": 2208768 }, { "epoch": 1.02, "learning_rate": 1.3829999810005878e-05, "loss": 3.3632, "step": 2209280 }, { "epoch": 1.02, "learning_rate": 1.3821613862495358e-05, "loss": 3.3687, "step": 2209792 }, { "epoch": 1.02, "learning_rate": 1.3813227914984836e-05, "loss": 3.3727, "step": 2210304 }, { "epoch": 1.02, "learning_rate": 1.3804841967474316e-05, "loss": 3.3601, "step": 2210816 }, { "epoch": 1.02, "learning_rate": 1.3796472398767529e-05, "loss": 3.3849, "step": 2211328 }, { "epoch": 1.02, "learning_rate": 1.378808645125701e-05, "loss": 3.3596, "step": 2211840 }, { "epoch": 1.02, "learning_rate": 1.3779700503746487e-05, "loss": 3.3744, "step": 2212352 }, { "epoch": 1.02, "learning_rate": 1.3771314556235967e-05, "loss": 3.366, "step": 2212864 }, { "epoch": 1.03, "eval_loss": 3.9216115474700928, "eval_runtime": 303.9904, "eval_samples_per_second": 1255.273, "eval_steps_per_second": 39.228, "step": 2213280 }, { "epoch": 0.0, "learning_rate": 1.3762944987529181e-05, "loss": 3.3869, "step": 2213376 }, { "epoch": 0.0, "learning_rate": 1.3754559040018658e-05, "loss": 3.3599, "step": 2213888 }, { "epoch": 0.0, "learning_rate": 1.3746173092508138e-05, "loss": 3.3651, "step": 2214400 }, { "epoch": 0.0, "learning_rate": 1.373778714499762e-05, "loss": 3.376, "step": 2214912 }, { "epoch": 0.0, "learning_rate": 1.3729417576290832e-05, "loss": 3.3706, "step": 2215424 }, { "epoch": 0.0, "learning_rate": 1.372103162878031e-05, "loss": 3.3719, "step": 2215936 }, { "epoch": 0.0, "learning_rate": 1.371264568126979e-05, "loss": 3.3627, "step": 2216448 }, { "epoch": 0.0, "learning_rate": 1.370425973375927e-05, "loss": 3.364, "step": 2216960 }, { "epoch": 0.0, "learning_rate": 1.3695890165052482e-05, "loss": 3.3643, "step": 2217472 }, { "epoch": 0.0, "learning_rate": 1.368750421754196e-05, "loss": 3.3717, "step": 2217984 }, { "epoch": 0.0, "learning_rate": 1.367911827003144e-05, "loss": 3.3633, "step": 2218496 }, { "epoch": 0.0, "learning_rate": 1.367073232252092e-05, "loss": 3.3702, "step": 2219008 }, { "epoch": 0.0, "learning_rate": 1.3662362753814131e-05, "loss": 3.3713, "step": 2219520 }, { "epoch": 0.0, "learning_rate": 1.3653976806303611e-05, "loss": 3.3539, "step": 2220032 }, { "epoch": 0.0, "learning_rate": 1.3645590858793091e-05, "loss": 3.3654, "step": 2220544 }, { "epoch": 0.0, "learning_rate": 1.3637204911282573e-05, "loss": 3.3525, "step": 2221056 }, { "epoch": 0.0, "learning_rate": 1.3628835342575782e-05, "loss": 3.3489, "step": 2221568 }, { "epoch": 0.0, "learning_rate": 1.3620449395065264e-05, "loss": 3.3668, "step": 2222080 }, { "epoch": 0.0, "learning_rate": 1.3612063447554744e-05, "loss": 3.3576, "step": 2222592 }, { "epoch": 0.0, "learning_rate": 1.3603677500044224e-05, "loss": 3.3738, "step": 2223104 }, { "epoch": 0.0, "learning_rate": 1.3595307931337434e-05, "loss": 3.3752, "step": 2223616 }, { "epoch": 0.0, "learning_rate": 1.3586921983826914e-05, "loss": 3.3629, "step": 2224128 }, { "epoch": 0.0, "learning_rate": 1.3578536036316394e-05, "loss": 3.3666, "step": 2224640 }, { "epoch": 0.0, "learning_rate": 1.3570150088805874e-05, "loss": 3.3664, "step": 2225152 }, { "epoch": 0.0, "learning_rate": 1.3561780520099085e-05, "loss": 3.3556, "step": 2225664 }, { "epoch": 0.0, "learning_rate": 1.3553394572588565e-05, "loss": 3.3691, "step": 2226176 }, { "epoch": 0.0, "learning_rate": 1.3545008625078045e-05, "loss": 3.3583, "step": 2226688 }, { "epoch": 0.0, "learning_rate": 1.3536622677567527e-05, "loss": 3.3563, "step": 2227200 }, { "epoch": 0.0, "learning_rate": 1.3528253108860736e-05, "loss": 3.3606, "step": 2227712 }, { "epoch": 0.0, "learning_rate": 1.3519867161350216e-05, "loss": 3.3517, "step": 2228224 }, { "epoch": 0.01, "learning_rate": 1.3511481213839697e-05, "loss": 3.3605, "step": 2228736 }, { "epoch": 0.01, "learning_rate": 1.3503095266329177e-05, "loss": 3.362, "step": 2229248 }, { "epoch": 0.01, "learning_rate": 1.3494725697622388e-05, "loss": 3.3703, "step": 2229760 }, { "epoch": 0.01, "learning_rate": 1.3486339750111868e-05, "loss": 3.3601, "step": 2230272 }, { "epoch": 0.01, "learning_rate": 1.3477953802601348e-05, "loss": 3.3581, "step": 2230784 }, { "epoch": 0.01, "learning_rate": 1.3469567855090828e-05, "loss": 3.3593, "step": 2231296 }, { "epoch": 0.01, "learning_rate": 1.3461198286384039e-05, "loss": 3.3755, "step": 2231808 }, { "epoch": 0.01, "learning_rate": 1.3452812338873519e-05, "loss": 3.3599, "step": 2232320 }, { "epoch": 0.01, "learning_rate": 1.3444426391362999e-05, "loss": 3.3537, "step": 2232832 }, { "epoch": 0.01, "learning_rate": 1.343604044385248e-05, "loss": 3.3613, "step": 2233344 }, { "epoch": 0.01, "learning_rate": 1.342767087514569e-05, "loss": 3.3591, "step": 2233856 }, { "epoch": 0.01, "learning_rate": 1.3419301306438904e-05, "loss": 3.362, "step": 2234368 }, { "epoch": 0.01, "learning_rate": 1.341091535892838e-05, "loss": 3.3717, "step": 2234880 }, { "epoch": 0.01, "learning_rate": 1.340252941141786e-05, "loss": 3.3693, "step": 2235392 }, { "epoch": 0.01, "learning_rate": 1.3394143463907342e-05, "loss": 3.3627, "step": 2235904 }, { "epoch": 0.01, "learning_rate": 1.3385757516396822e-05, "loss": 3.3638, "step": 2236416 }, { "epoch": 0.01, "learning_rate": 1.3377371568886302e-05, "loss": 3.3649, "step": 2236928 }, { "epoch": 0.01, "learning_rate": 1.3368985621375782e-05, "loss": 3.3642, "step": 2237440 }, { "epoch": 0.01, "learning_rate": 1.336059967386526e-05, "loss": 3.3425, "step": 2237952 }, { "epoch": 0.01, "learning_rate": 1.3352230105158472e-05, "loss": 3.3691, "step": 2238464 }, { "epoch": 0.01, "learning_rate": 1.3343844157647952e-05, "loss": 3.3612, "step": 2238976 }, { "epoch": 0.01, "learning_rate": 1.3335458210137434e-05, "loss": 3.3678, "step": 2239488 }, { "epoch": 0.01, "learning_rate": 1.332707226262691e-05, "loss": 3.3589, "step": 2240000 }, { "epoch": 0.01, "learning_rate": 1.3318702693920123e-05, "loss": 3.3604, "step": 2240512 }, { "epoch": 0.01, "learning_rate": 1.3310316746409605e-05, "loss": 3.3551, "step": 2241024 }, { "epoch": 0.01, "learning_rate": 1.3301930798899085e-05, "loss": 3.3528, "step": 2241536 }, { "epoch": 0.01, "learning_rate": 1.3293561230192295e-05, "loss": 3.3715, "step": 2242048 }, { "epoch": 0.01, "learning_rate": 1.3285175282681775e-05, "loss": 3.3604, "step": 2242560 }, { "epoch": 0.01, "learning_rate": 1.3276789335171255e-05, "loss": 3.3806, "step": 2243072 }, { "epoch": 0.01, "learning_rate": 1.3268403387660734e-05, "loss": 3.3582, "step": 2243584 }, { "epoch": 0.01, "learning_rate": 1.3260033818953946e-05, "loss": 3.3478, "step": 2244096 }, { "epoch": 0.01, "learning_rate": 1.3251647871443426e-05, "loss": 3.3745, "step": 2244608 }, { "epoch": 0.01, "learning_rate": 1.3243278302736637e-05, "loss": 3.3584, "step": 2245120 }, { "epoch": 0.01, "learning_rate": 1.3234892355226117e-05, "loss": 3.3505, "step": 2245632 }, { "epoch": 0.01, "learning_rate": 1.3226506407715597e-05, "loss": 3.357, "step": 2246144 }, { "epoch": 0.01, "learning_rate": 1.3218120460205077e-05, "loss": 3.3669, "step": 2246656 }, { "epoch": 0.01, "learning_rate": 1.3209734512694558e-05, "loss": 3.3474, "step": 2247168 }, { "epoch": 0.01, "learning_rate": 1.3201348565184035e-05, "loss": 3.3541, "step": 2247680 }, { "epoch": 0.01, "learning_rate": 1.3192962617673515e-05, "loss": 3.3527, "step": 2248192 }, { "epoch": 0.01, "learning_rate": 1.3184576670162996e-05, "loss": 3.3517, "step": 2248704 }, { "epoch": 0.01, "learning_rate": 1.3176207101456206e-05, "loss": 3.3698, "step": 2249216 }, { "epoch": 0.01, "learning_rate": 1.3167821153945687e-05, "loss": 3.3612, "step": 2249728 }, { "epoch": 0.01, "learning_rate": 1.3159435206435167e-05, "loss": 3.3577, "step": 2250240 }, { "epoch": 0.01, "learning_rate": 1.315106563772838e-05, "loss": 3.3567, "step": 2250752 }, { "epoch": 0.01, "learning_rate": 1.3142679690217858e-05, "loss": 3.3716, "step": 2251264 }, { "epoch": 0.01, "learning_rate": 1.3134293742707338e-05, "loss": 3.3622, "step": 2251776 }, { "epoch": 0.01, "learning_rate": 1.3125907795196818e-05, "loss": 3.3705, "step": 2252288 }, { "epoch": 0.01, "learning_rate": 1.3117521847686298e-05, "loss": 3.3564, "step": 2252800 }, { "epoch": 0.01, "learning_rate": 1.3109135900175778e-05, "loss": 3.356, "step": 2253312 }, { "epoch": 0.01, "learning_rate": 1.3100766331468989e-05, "loss": 3.37, "step": 2253824 }, { "epoch": 0.01, "learning_rate": 1.3092380383958468e-05, "loss": 3.3603, "step": 2254336 }, { "epoch": 0.01, "learning_rate": 1.308399443644795e-05, "loss": 3.3615, "step": 2254848 }, { "epoch": 0.01, "learning_rate": 1.307560848893743e-05, "loss": 3.3662, "step": 2255360 }, { "epoch": 0.01, "learning_rate": 1.306722254142691e-05, "loss": 3.3559, "step": 2255872 }, { "epoch": 0.01, "learning_rate": 1.3058836593916388e-05, "loss": 3.3489, "step": 2256384 }, { "epoch": 0.01, "learning_rate": 1.3050450646405868e-05, "loss": 3.3581, "step": 2256896 }, { "epoch": 0.01, "learning_rate": 1.3042064698895348e-05, "loss": 3.3689, "step": 2257408 }, { "epoch": 0.01, "learning_rate": 1.3033711508992292e-05, "loss": 3.3578, "step": 2257920 }, { "epoch": 0.01, "learning_rate": 1.3025325561481771e-05, "loss": 3.3571, "step": 2258432 }, { "epoch": 0.01, "learning_rate": 1.3016939613971251e-05, "loss": 3.3584, "step": 2258944 }, { "epoch": 0.02, "learning_rate": 1.3008553666460731e-05, "loss": 3.357, "step": 2259456 }, { "epoch": 0.02, "learning_rate": 1.300016771895021e-05, "loss": 3.3586, "step": 2259968 }, { "epoch": 0.02, "learning_rate": 1.299178177143969e-05, "loss": 3.3564, "step": 2260480 }, { "epoch": 0.02, "learning_rate": 1.298339582392917e-05, "loss": 3.3586, "step": 2260992 }, { "epoch": 0.02, "learning_rate": 1.2975009876418651e-05, "loss": 3.3657, "step": 2261504 }, { "epoch": 0.02, "learning_rate": 1.296664030771186e-05, "loss": 3.3695, "step": 2262016 }, { "epoch": 0.02, "learning_rate": 1.2958270739005075e-05, "loss": 3.3383, "step": 2262528 }, { "epoch": 0.02, "learning_rate": 1.2949884791494554e-05, "loss": 3.3562, "step": 2263040 }, { "epoch": 0.02, "learning_rate": 1.2941498843984034e-05, "loss": 3.3528, "step": 2263552 }, { "epoch": 0.02, "learning_rate": 1.2933112896473513e-05, "loss": 3.3663, "step": 2264064 }, { "epoch": 0.02, "learning_rate": 1.2924726948962993e-05, "loss": 3.3628, "step": 2264576 }, { "epoch": 0.02, "learning_rate": 1.2916341001452473e-05, "loss": 3.3584, "step": 2265088 }, { "epoch": 0.02, "learning_rate": 1.2907955053941953e-05, "loss": 3.3482, "step": 2265600 }, { "epoch": 0.02, "learning_rate": 1.2899569106431434e-05, "loss": 3.3574, "step": 2266112 }, { "epoch": 0.02, "learning_rate": 1.2891199537724643e-05, "loss": 3.3554, "step": 2266624 }, { "epoch": 0.02, "learning_rate": 1.2882813590214123e-05, "loss": 3.3556, "step": 2267136 }, { "epoch": 0.02, "learning_rate": 1.2874427642703605e-05, "loss": 3.3506, "step": 2267648 }, { "epoch": 0.02, "learning_rate": 1.2866041695193085e-05, "loss": 3.3599, "step": 2268160 }, { "epoch": 0.02, "learning_rate": 1.2857672126486296e-05, "loss": 3.3563, "step": 2268672 }, { "epoch": 0.02, "learning_rate": 1.2849286178975776e-05, "loss": 3.3465, "step": 2269184 }, { "epoch": 0.02, "learning_rate": 1.2840900231465256e-05, "loss": 3.3532, "step": 2269696 }, { "epoch": 0.02, "learning_rate": 1.2832514283954736e-05, "loss": 3.3438, "step": 2270208 }, { "epoch": 0.02, "learning_rate": 1.2824144715247946e-05, "loss": 3.3631, "step": 2270720 }, { "epoch": 0.02, "learning_rate": 1.2815758767737426e-05, "loss": 3.3546, "step": 2271232 }, { "epoch": 0.02, "learning_rate": 1.2807372820226906e-05, "loss": 3.3542, "step": 2271744 }, { "epoch": 0.02, "learning_rate": 1.2798986872716386e-05, "loss": 3.3606, "step": 2272256 }, { "epoch": 0.02, "learning_rate": 1.2790617304009597e-05, "loss": 3.3624, "step": 2272768 }, { "epoch": 0.02, "learning_rate": 1.2782247735302808e-05, "loss": 3.3571, "step": 2273280 }, { "epoch": 0.02, "learning_rate": 1.2773861787792288e-05, "loss": 3.36, "step": 2273792 }, { "epoch": 0.02, "learning_rate": 1.2765475840281768e-05, "loss": 3.363, "step": 2274304 }, { "epoch": 0.02, "learning_rate": 1.2757089892771248e-05, "loss": 3.3487, "step": 2274816 }, { "epoch": 0.02, "learning_rate": 1.274870394526073e-05, "loss": 3.3463, "step": 2275328 }, { "epoch": 0.02, "learning_rate": 1.2740334376553938e-05, "loss": 3.3575, "step": 2275840 }, { "epoch": 0.02, "learning_rate": 1.273194842904342e-05, "loss": 3.3579, "step": 2276352 }, { "epoch": 0.02, "learning_rate": 1.27235624815329e-05, "loss": 3.3593, "step": 2276864 }, { "epoch": 0.02, "learning_rate": 1.271517653402238e-05, "loss": 3.3537, "step": 2277376 }, { "epoch": 0.02, "learning_rate": 1.270680696531559e-05, "loss": 3.3581, "step": 2277888 }, { "epoch": 0.02, "learning_rate": 1.269842101780507e-05, "loss": 3.357, "step": 2278400 }, { "epoch": 0.02, "learning_rate": 1.269003507029455e-05, "loss": 3.3463, "step": 2278912 }, { "epoch": 0.02, "learning_rate": 1.268164912278403e-05, "loss": 3.3495, "step": 2279424 }, { "epoch": 0.02, "learning_rate": 1.2673263175273512e-05, "loss": 3.3636, "step": 2279936 }, { "epoch": 0.02, "learning_rate": 1.2664877227762989e-05, "loss": 3.3703, "step": 2280448 }, { "epoch": 0.02, "learning_rate": 1.2656491280252469e-05, "loss": 3.3499, "step": 2280960 }, { "epoch": 0.02, "learning_rate": 1.2648121711545683e-05, "loss": 3.3573, "step": 2281472 }, { "epoch": 0.02, "learning_rate": 1.2639735764035163e-05, "loss": 3.3649, "step": 2281984 }, { "epoch": 0.02, "learning_rate": 1.263134981652464e-05, "loss": 3.3539, "step": 2282496 }, { "epoch": 0.02, "learning_rate": 1.2622963869014121e-05, "loss": 3.3527, "step": 2283008 }, { "epoch": 0.02, "learning_rate": 1.2614577921503601e-05, "loss": 3.3542, "step": 2283520 }, { "epoch": 0.02, "learning_rate": 1.2606191973993081e-05, "loss": 3.3696, "step": 2284032 }, { "epoch": 0.02, "learning_rate": 1.2597806026482561e-05, "loss": 3.368, "step": 2284544 }, { "epoch": 0.02, "learning_rate": 1.2589420078972043e-05, "loss": 3.3589, "step": 2285056 }, { "epoch": 0.02, "learning_rate": 1.2581050510265252e-05, "loss": 3.3516, "step": 2285568 }, { "epoch": 0.02, "learning_rate": 1.2572664562754732e-05, "loss": 3.3591, "step": 2286080 }, { "epoch": 0.02, "learning_rate": 1.2564278615244213e-05, "loss": 3.3602, "step": 2286592 }, { "epoch": 0.02, "learning_rate": 1.2555892667733693e-05, "loss": 3.3504, "step": 2287104 }, { "epoch": 0.02, "learning_rate": 1.2547523099026904e-05, "loss": 3.3736, "step": 2287616 }, { "epoch": 0.02, "learning_rate": 1.2539137151516384e-05, "loss": 3.3522, "step": 2288128 }, { "epoch": 0.02, "learning_rate": 1.2530767582809593e-05, "loss": 3.3649, "step": 2288640 }, { "epoch": 0.02, "learning_rate": 1.2522381635299075e-05, "loss": 3.3551, "step": 2289152 }, { "epoch": 0.03, "eval_loss": 3.9243946075439453, "eval_runtime": 303.6161, "eval_samples_per_second": 1256.821, "eval_steps_per_second": 39.277, "step": 2289600 }, { "epoch": 1.0, "learning_rate": 1.2513995687788555e-05, "loss": 3.3583, "step": 2289664 }, { "epoch": 1.0, "learning_rate": 1.2505609740278035e-05, "loss": 3.3466, "step": 2290176 }, { "epoch": 1.0, "learning_rate": 1.2497223792767513e-05, "loss": 3.3564, "step": 2290688 }, { "epoch": 1.0, "learning_rate": 1.2488837845256995e-05, "loss": 3.3647, "step": 2291200 }, { "epoch": 1.0, "learning_rate": 1.2480451897746475e-05, "loss": 3.3617, "step": 2291712 }, { "epoch": 1.0, "learning_rate": 1.2472065950235953e-05, "loss": 3.3605, "step": 2292224 }, { "epoch": 1.0, "learning_rate": 1.2463696381529165e-05, "loss": 3.3545, "step": 2292736 }, { "epoch": 1.0, "learning_rate": 1.2455310434018645e-05, "loss": 3.3548, "step": 2293248 }, { "epoch": 1.0, "learning_rate": 1.2446924486508124e-05, "loss": 3.3563, "step": 2293760 }, { "epoch": 1.0, "learning_rate": 1.2438538538997605e-05, "loss": 3.3609, "step": 2294272 }, { "epoch": 1.0, "learning_rate": 1.2430168970290816e-05, "loss": 3.3551, "step": 2294784 }, { "epoch": 1.0, "learning_rate": 1.2421783022780296e-05, "loss": 3.3601, "step": 2295296 }, { "epoch": 1.0, "learning_rate": 1.2413397075269776e-05, "loss": 3.3611, "step": 2295808 }, { "epoch": 1.0, "learning_rate": 1.2405011127759256e-05, "loss": 3.341, "step": 2296320 }, { "epoch": 1.0, "learning_rate": 1.2396641559052467e-05, "loss": 3.3544, "step": 2296832 }, { "epoch": 1.0, "learning_rate": 1.2388255611541948e-05, "loss": 3.3418, "step": 2297344 }, { "epoch": 1.0, "learning_rate": 1.2379869664031427e-05, "loss": 3.3419, "step": 2297856 }, { "epoch": 1.0, "learning_rate": 1.2371483716520906e-05, "loss": 3.354, "step": 2298368 }, { "epoch": 1.0, "learning_rate": 1.2363114147814119e-05, "loss": 3.3472, "step": 2298880 }, { "epoch": 1.0, "learning_rate": 1.2354728200303597e-05, "loss": 3.3627, "step": 2299392 }, { "epoch": 1.0, "learning_rate": 1.2346342252793077e-05, "loss": 3.3697, "step": 2299904 }, { "epoch": 1.0, "learning_rate": 1.2337956305282559e-05, "loss": 3.3515, "step": 2300416 }, { "epoch": 1.0, "learning_rate": 1.232958673657577e-05, "loss": 3.3554, "step": 2300928 }, { "epoch": 1.0, "learning_rate": 1.2321200789065248e-05, "loss": 3.3577, "step": 2301440 }, { "epoch": 1.0, "learning_rate": 1.231281484155473e-05, "loss": 3.3459, "step": 2301952 }, { "epoch": 1.0, "learning_rate": 1.230442889404421e-05, "loss": 3.3626, "step": 2302464 }, { "epoch": 1.0, "learning_rate": 1.229605932533742e-05, "loss": 3.3464, "step": 2302976 }, { "epoch": 1.0, "learning_rate": 1.22876733778269e-05, "loss": 3.351, "step": 2303488 }, { "epoch": 1.0, "learning_rate": 1.227928743031638e-05, "loss": 3.3488, "step": 2304000 }, { "epoch": 1.0, "learning_rate": 1.227090148280586e-05, "loss": 3.3428, "step": 2304512 }, { "epoch": 1.01, "learning_rate": 1.2262531914099071e-05, "loss": 3.3485, "step": 2305024 }, { "epoch": 1.01, "learning_rate": 1.2254145966588551e-05, "loss": 3.3548, "step": 2305536 }, { "epoch": 1.01, "learning_rate": 1.224576001907803e-05, "loss": 3.3602, "step": 2306048 }, { "epoch": 1.01, "learning_rate": 1.2237390450371243e-05, "loss": 3.3531, "step": 2306560 }, { "epoch": 1.01, "learning_rate": 1.2229004502860722e-05, "loss": 3.3453, "step": 2307072 }, { "epoch": 1.01, "learning_rate": 1.2220618555350202e-05, "loss": 3.3508, "step": 2307584 }, { "epoch": 1.01, "learning_rate": 1.2212232607839683e-05, "loss": 3.3672, "step": 2308096 }, { "epoch": 1.01, "learning_rate": 1.2203863039132894e-05, "loss": 3.3463, "step": 2308608 }, { "epoch": 1.01, "learning_rate": 1.2195477091622374e-05, "loss": 3.3489, "step": 2309120 }, { "epoch": 1.01, "learning_rate": 1.2187091144111854e-05, "loss": 3.3501, "step": 2309632 }, { "epoch": 1.01, "learning_rate": 1.2178705196601334e-05, "loss": 3.3448, "step": 2310144 }, { "epoch": 1.01, "learning_rate": 1.2170335627894545e-05, "loss": 3.355, "step": 2310656 }, { "epoch": 1.01, "learning_rate": 1.2161949680384025e-05, "loss": 3.3609, "step": 2311168 }, { "epoch": 1.01, "learning_rate": 1.2153563732873505e-05, "loss": 3.3628, "step": 2311680 }, { "epoch": 1.01, "learning_rate": 1.2145177785362985e-05, "loss": 3.3538, "step": 2312192 }, { "epoch": 1.01, "learning_rate": 1.2136791837852464e-05, "loss": 3.353, "step": 2312704 }, { "epoch": 1.01, "learning_rate": 1.2128405890341944e-05, "loss": 3.3514, "step": 2313216 }, { "epoch": 1.01, "learning_rate": 1.2120019942831424e-05, "loss": 3.3568, "step": 2313728 }, { "epoch": 1.01, "learning_rate": 1.2111633995320903e-05, "loss": 3.3273, "step": 2314240 }, { "epoch": 1.01, "learning_rate": 1.2103264426614115e-05, "loss": 3.3589, "step": 2314752 }, { "epoch": 1.01, "learning_rate": 1.2094894857907328e-05, "loss": 3.3552, "step": 2315264 }, { "epoch": 1.01, "learning_rate": 1.2086508910396808e-05, "loss": 3.3555, "step": 2315776 }, { "epoch": 1.01, "learning_rate": 1.2078122962886286e-05, "loss": 3.3477, "step": 2316288 }, { "epoch": 1.01, "learning_rate": 1.2069737015375766e-05, "loss": 3.3442, "step": 2316800 }, { "epoch": 1.01, "learning_rate": 1.2061351067865247e-05, "loss": 3.3491, "step": 2317312 }, { "epoch": 1.01, "learning_rate": 1.2052965120354726e-05, "loss": 3.3408, "step": 2317824 }, { "epoch": 1.01, "learning_rate": 1.2044579172844206e-05, "loss": 3.3607, "step": 2318336 }, { "epoch": 1.01, "learning_rate": 1.2036193225333686e-05, "loss": 3.3509, "step": 2318848 }, { "epoch": 1.01, "learning_rate": 1.2027823656626898e-05, "loss": 3.3668, "step": 2319360 }, { "epoch": 1.01, "learning_rate": 1.2019437709116376e-05, "loss": 3.3484, "step": 2319872 }, { "epoch": 1.01, "learning_rate": 1.2011051761605856e-05, "loss": 3.3366, "step": 2320384 }, { "epoch": 1.01, "learning_rate": 1.2002665814095338e-05, "loss": 3.3653, "step": 2320896 }, { "epoch": 1.01, "learning_rate": 1.199431262419228e-05, "loss": 3.3464, "step": 2321408 }, { "epoch": 1.01, "learning_rate": 1.198592667668176e-05, "loss": 3.3426, "step": 2321920 }, { "epoch": 1.01, "learning_rate": 1.197754072917124e-05, "loss": 3.3498, "step": 2322432 }, { "epoch": 1.01, "learning_rate": 1.196915478166072e-05, "loss": 3.3554, "step": 2322944 }, { "epoch": 1.01, "learning_rate": 1.19607688341502e-05, "loss": 3.3393, "step": 2323456 }, { "epoch": 1.01, "learning_rate": 1.195238288663968e-05, "loss": 3.3469, "step": 2323968 }, { "epoch": 1.01, "learning_rate": 1.194399693912916e-05, "loss": 3.3454, "step": 2324480 }, { "epoch": 1.01, "learning_rate": 1.193561099161864e-05, "loss": 3.3402, "step": 2324992 }, { "epoch": 1.01, "learning_rate": 1.192724142291185e-05, "loss": 3.3578, "step": 2325504 }, { "epoch": 1.01, "learning_rate": 1.191885547540133e-05, "loss": 3.3523, "step": 2326016 }, { "epoch": 1.01, "learning_rate": 1.191046952789081e-05, "loss": 3.3486, "step": 2326528 }, { "epoch": 1.01, "learning_rate": 1.190209995918402e-05, "loss": 3.3485, "step": 2327040 }, { "epoch": 1.01, "learning_rate": 1.18937140116735e-05, "loss": 3.361, "step": 2327552 }, { "epoch": 1.01, "learning_rate": 1.1885328064162982e-05, "loss": 3.3487, "step": 2328064 }, { "epoch": 1.01, "learning_rate": 1.1876942116652462e-05, "loss": 3.3582, "step": 2328576 }, { "epoch": 1.01, "learning_rate": 1.186855616914194e-05, "loss": 3.3504, "step": 2329088 }, { "epoch": 1.01, "learning_rate": 1.186017022163142e-05, "loss": 3.3463, "step": 2329600 }, { "epoch": 1.01, "learning_rate": 1.1851800652924633e-05, "loss": 3.3586, "step": 2330112 }, { "epoch": 1.01, "learning_rate": 1.1843414705414111e-05, "loss": 3.3504, "step": 2330624 }, { "epoch": 1.01, "learning_rate": 1.1835028757903591e-05, "loss": 3.3541, "step": 2331136 }, { "epoch": 1.01, "learning_rate": 1.1826642810393073e-05, "loss": 3.3567, "step": 2331648 }, { "epoch": 1.01, "learning_rate": 1.1818256862882553e-05, "loss": 3.3525, "step": 2332160 }, { "epoch": 1.01, "learning_rate": 1.1809870915372031e-05, "loss": 3.335, "step": 2332672 }, { "epoch": 1.01, "learning_rate": 1.1801484967861513e-05, "loss": 3.3496, "step": 2333184 }, { "epoch": 1.01, "learning_rate": 1.1793099020350993e-05, "loss": 3.3611, "step": 2333696 }, { "epoch": 1.01, "learning_rate": 1.1784745830447936e-05, "loss": 3.3472, "step": 2334208 }, { "epoch": 1.01, "learning_rate": 1.1776359882937414e-05, "loss": 3.3471, "step": 2334720 }, { "epoch": 1.01, "learning_rate": 1.1767973935426894e-05, "loss": 3.3455, "step": 2335232 }, { "epoch": 1.02, "learning_rate": 1.1759587987916374e-05, "loss": 3.3491, "step": 2335744 }, { "epoch": 1.02, "learning_rate": 1.1751202040405854e-05, "loss": 3.3473, "step": 2336256 }, { "epoch": 1.02, "learning_rate": 1.1742816092895334e-05, "loss": 3.3481, "step": 2336768 }, { "epoch": 1.02, "learning_rate": 1.1734430145384814e-05, "loss": 3.3509, "step": 2337280 }, { "epoch": 1.02, "learning_rate": 1.1726044197874294e-05, "loss": 3.3512, "step": 2337792 }, { "epoch": 1.02, "learning_rate": 1.1717674629167505e-05, "loss": 3.3632, "step": 2338304 }, { "epoch": 1.02, "learning_rate": 1.1709288681656985e-05, "loss": 3.3266, "step": 2338816 }, { "epoch": 1.02, "learning_rate": 1.1700902734146465e-05, "loss": 3.3492, "step": 2339328 }, { "epoch": 1.02, "learning_rate": 1.1692516786635945e-05, "loss": 3.3445, "step": 2339840 }, { "epoch": 1.02, "learning_rate": 1.1684147217929155e-05, "loss": 3.3558, "step": 2340352 }, { "epoch": 1.02, "learning_rate": 1.1675761270418637e-05, "loss": 3.3493, "step": 2340864 }, { "epoch": 1.02, "learning_rate": 1.1667375322908117e-05, "loss": 3.35, "step": 2341376 }, { "epoch": 1.02, "learning_rate": 1.1658989375397595e-05, "loss": 3.3383, "step": 2341888 }, { "epoch": 1.02, "learning_rate": 1.1650619806690808e-05, "loss": 3.3493, "step": 2342400 }, { "epoch": 1.02, "learning_rate": 1.1642233859180288e-05, "loss": 3.3466, "step": 2342912 }, { "epoch": 1.02, "learning_rate": 1.1633847911669766e-05, "loss": 3.3418, "step": 2343424 }, { "epoch": 1.02, "learning_rate": 1.1625461964159248e-05, "loss": 3.3408, "step": 2343936 }, { "epoch": 1.02, "learning_rate": 1.1617092395452458e-05, "loss": 3.3474, "step": 2344448 }, { "epoch": 1.02, "learning_rate": 1.1608706447941938e-05, "loss": 3.3541, "step": 2344960 }, { "epoch": 1.02, "learning_rate": 1.1600320500431418e-05, "loss": 3.3335, "step": 2345472 }, { "epoch": 1.02, "learning_rate": 1.1591934552920898e-05, "loss": 3.3456, "step": 2345984 }, { "epoch": 1.02, "learning_rate": 1.1583564984214109e-05, "loss": 3.3344, "step": 2346496 }, { "epoch": 1.02, "learning_rate": 1.157517903670359e-05, "loss": 3.3545, "step": 2347008 }, { "epoch": 1.02, "learning_rate": 1.1566793089193069e-05, "loss": 3.3427, "step": 2347520 }, { "epoch": 1.02, "learning_rate": 1.1558407141682549e-05, "loss": 3.3447, "step": 2348032 }, { "epoch": 1.02, "learning_rate": 1.1550037572975762e-05, "loss": 3.351, "step": 2348544 }, { "epoch": 1.02, "learning_rate": 1.154165162546524e-05, "loss": 3.3516, "step": 2349056 }, { "epoch": 1.02, "learning_rate": 1.153326567795472e-05, "loss": 3.3445, "step": 2349568 }, { "epoch": 1.02, "learning_rate": 1.15248797304442e-05, "loss": 3.3488, "step": 2350080 }, { "epoch": 1.02, "learning_rate": 1.1516510161737412e-05, "loss": 3.3539, "step": 2350592 }, { "epoch": 1.02, "learning_rate": 1.150812421422689e-05, "loss": 3.3349, "step": 2351104 }, { "epoch": 1.02, "learning_rate": 1.1499738266716372e-05, "loss": 3.3335, "step": 2351616 }, { "epoch": 1.02, "learning_rate": 1.1491352319205852e-05, "loss": 3.3472, "step": 2352128 }, { "epoch": 1.02, "learning_rate": 1.1482982750499063e-05, "loss": 3.3512, "step": 2352640 }, { "epoch": 1.02, "learning_rate": 1.1474596802988543e-05, "loss": 3.35, "step": 2353152 }, { "epoch": 1.02, "learning_rate": 1.1466210855478023e-05, "loss": 3.3423, "step": 2353664 }, { "epoch": 1.02, "learning_rate": 1.1457841286771234e-05, "loss": 3.3452, "step": 2354176 }, { "epoch": 1.02, "learning_rate": 1.1449455339260713e-05, "loss": 3.3452, "step": 2354688 }, { "epoch": 1.02, "learning_rate": 1.1441069391750193e-05, "loss": 3.3353, "step": 2355200 }, { "epoch": 1.02, "learning_rate": 1.1432683444239673e-05, "loss": 3.3372, "step": 2355712 }, { "epoch": 1.02, "learning_rate": 1.1424297496729153e-05, "loss": 3.3545, "step": 2356224 }, { "epoch": 1.02, "learning_rate": 1.1415911549218633e-05, "loss": 3.3606, "step": 2356736 }, { "epoch": 1.02, "learning_rate": 1.1407525601708113e-05, "loss": 3.3445, "step": 2357248 }, { "epoch": 1.02, "learning_rate": 1.1399156033001326e-05, "loss": 3.347, "step": 2357760 }, { "epoch": 1.02, "learning_rate": 1.1390770085490804e-05, "loss": 3.3512, "step": 2358272 }, { "epoch": 1.02, "learning_rate": 1.1382384137980284e-05, "loss": 3.3453, "step": 2358784 }, { "epoch": 1.02, "learning_rate": 1.1373998190469764e-05, "loss": 3.3427, "step": 2359296 }, { "epoch": 1.02, "learning_rate": 1.1365612242959246e-05, "loss": 3.3484, "step": 2359808 }, { "epoch": 1.02, "learning_rate": 1.1357226295448724e-05, "loss": 3.3566, "step": 2360320 }, { "epoch": 1.02, "learning_rate": 1.1348840347938204e-05, "loss": 3.3561, "step": 2360832 }, { "epoch": 1.02, "learning_rate": 1.1340454400427684e-05, "loss": 3.3481, "step": 2361344 }, { "epoch": 1.02, "learning_rate": 1.1332084831720895e-05, "loss": 3.3408, "step": 2361856 }, { "epoch": 1.02, "learning_rate": 1.1323698884210374e-05, "loss": 3.3497, "step": 2362368 }, { "epoch": 1.02, "learning_rate": 1.1315312936699856e-05, "loss": 3.3525, "step": 2362880 }, { "epoch": 1.02, "learning_rate": 1.1306926989189334e-05, "loss": 3.3383, "step": 2363392 }, { "epoch": 1.02, "learning_rate": 1.1298557420482545e-05, "loss": 3.3639, "step": 2363904 }, { "epoch": 1.02, "learning_rate": 1.1290171472972027e-05, "loss": 3.3439, "step": 2364416 }, { "epoch": 1.02, "learning_rate": 1.1281801904265238e-05, "loss": 3.3523, "step": 2364928 }, { "epoch": 1.02, "learning_rate": 1.1273415956754718e-05, "loss": 3.3427, "step": 2365440 }, { "epoch": 1.03, "eval_loss": 3.925236463546753, "eval_runtime": 303.3985, "eval_samples_per_second": 1257.722, "eval_steps_per_second": 39.305, "step": 2365920 }, { "epoch": 0.0, "learning_rate": 1.1265030009244198e-05, "loss": 3.3382, "step": 2365952 }, { "epoch": 0.0, "learning_rate": 1.1256644061733677e-05, "loss": 3.341, "step": 2366464 }, { "epoch": 0.0, "learning_rate": 1.1248258114223157e-05, "loss": 3.3465, "step": 2366976 }, { "epoch": 0.0, "learning_rate": 1.1239872166712637e-05, "loss": 3.3534, "step": 2367488 }, { "epoch": 0.0, "learning_rate": 1.1231502598005848e-05, "loss": 3.3546, "step": 2368000 }, { "epoch": 0.0, "learning_rate": 1.1223116650495328e-05, "loss": 3.3516, "step": 2368512 }, { "epoch": 0.0, "learning_rate": 1.1214730702984808e-05, "loss": 3.3388, "step": 2369024 }, { "epoch": 0.0, "learning_rate": 1.1206344755474288e-05, "loss": 3.3479, "step": 2369536 }, { "epoch": 0.0, "learning_rate": 1.1197975186767499e-05, "loss": 3.3458, "step": 2370048 }, { "epoch": 0.0, "learning_rate": 1.118958923925698e-05, "loss": 3.3507, "step": 2370560 }, { "epoch": 0.0, "learning_rate": 1.1181203291746459e-05, "loss": 3.3446, "step": 2371072 }, { "epoch": 0.0, "learning_rate": 1.1172817344235939e-05, "loss": 3.349, "step": 2371584 }, { "epoch": 0.0, "learning_rate": 1.1164447775529151e-05, "loss": 3.3493, "step": 2372096 }, { "epoch": 0.0, "learning_rate": 1.1156061828018631e-05, "loss": 3.3336, "step": 2372608 }, { "epoch": 0.0, "learning_rate": 1.114767588050811e-05, "loss": 3.3421, "step": 2373120 }, { "epoch": 0.0, "learning_rate": 1.1139289932997591e-05, "loss": 3.3304, "step": 2373632 }, { "epoch": 0.0, "learning_rate": 1.1130920364290802e-05, "loss": 3.3343, "step": 2374144 }, { "epoch": 0.0, "learning_rate": 1.112253441678028e-05, "loss": 3.3448, "step": 2374656 }, { "epoch": 0.0, "learning_rate": 1.1114148469269762e-05, "loss": 3.3391, "step": 2375168 }, { "epoch": 0.0, "learning_rate": 1.1105762521759242e-05, "loss": 3.348, "step": 2375680 }, { "epoch": 0.0, "learning_rate": 1.1097392953052453e-05, "loss": 3.3586, "step": 2376192 }, { "epoch": 0.0, "learning_rate": 1.1089007005541932e-05, "loss": 3.3418, "step": 2376704 }, { "epoch": 0.0, "learning_rate": 1.1080621058031412e-05, "loss": 3.3439, "step": 2377216 }, { "epoch": 0.0, "learning_rate": 1.1072235110520892e-05, "loss": 3.3488, "step": 2377728 }, { "epoch": 0.0, "learning_rate": 1.1063865541814105e-05, "loss": 3.3405, "step": 2378240 }, { "epoch": 0.0, "learning_rate": 1.1055479594303583e-05, "loss": 3.3487, "step": 2378752 }, { "epoch": 0.0, "learning_rate": 1.1047093646793063e-05, "loss": 3.3336, "step": 2379264 }, { "epoch": 0.0, "learning_rate": 1.1038707699282545e-05, "loss": 3.3443, "step": 2379776 }, { "epoch": 0.0, "learning_rate": 1.1030338130575754e-05, "loss": 3.3411, "step": 2380288 }, { "epoch": 0.0, "learning_rate": 1.1021952183065234e-05, "loss": 3.3327, "step": 2380800 }, { "epoch": 0.01, "learning_rate": 1.1013566235554715e-05, "loss": 3.3442, "step": 2381312 }, { "epoch": 0.01, "learning_rate": 1.1005180288044195e-05, "loss": 3.3384, "step": 2381824 }, { "epoch": 0.01, "learning_rate": 1.0996810719337406e-05, "loss": 3.3487, "step": 2382336 }, { "epoch": 0.01, "learning_rate": 1.0988424771826886e-05, "loss": 3.3476, "step": 2382848 }, { "epoch": 0.01, "learning_rate": 1.0980038824316366e-05, "loss": 3.3363, "step": 2383360 }, { "epoch": 0.01, "learning_rate": 1.0971652876805844e-05, "loss": 3.3398, "step": 2383872 }, { "epoch": 0.01, "learning_rate": 1.0963283308099057e-05, "loss": 3.3577, "step": 2384384 }, { "epoch": 0.01, "learning_rate": 1.0954897360588537e-05, "loss": 3.3348, "step": 2384896 }, { "epoch": 0.01, "learning_rate": 1.0946511413078017e-05, "loss": 3.3393, "step": 2385408 }, { "epoch": 0.01, "learning_rate": 1.0938125465567497e-05, "loss": 3.3384, "step": 2385920 }, { "epoch": 0.01, "learning_rate": 1.0929755896860707e-05, "loss": 3.3392, "step": 2386432 }, { "epoch": 0.01, "learning_rate": 1.092138632815392e-05, "loss": 3.3383, "step": 2386944 }, { "epoch": 0.01, "learning_rate": 1.09130003806434e-05, "loss": 3.3585, "step": 2387456 }, { "epoch": 0.01, "learning_rate": 1.0904614433132878e-05, "loss": 3.3462, "step": 2387968 }, { "epoch": 0.01, "learning_rate": 1.0896228485622358e-05, "loss": 3.3437, "step": 2388480 }, { "epoch": 0.01, "learning_rate": 1.088784253811184e-05, "loss": 3.3455, "step": 2388992 }, { "epoch": 0.01, "learning_rate": 1.0879456590601318e-05, "loss": 3.3364, "step": 2389504 }, { "epoch": 0.01, "learning_rate": 1.0871070643090798e-05, "loss": 3.3467, "step": 2390016 }, { "epoch": 0.01, "learning_rate": 1.086268469558028e-05, "loss": 3.318, "step": 2390528 }, { "epoch": 0.01, "learning_rate": 1.085431512687349e-05, "loss": 3.3463, "step": 2391040 }, { "epoch": 0.01, "learning_rate": 1.0845929179362969e-05, "loss": 3.3459, "step": 2391552 }, { "epoch": 0.01, "learning_rate": 1.083754323185245e-05, "loss": 3.346, "step": 2392064 }, { "epoch": 0.01, "learning_rate": 1.082915728434193e-05, "loss": 3.3407, "step": 2392576 }, { "epoch": 0.01, "learning_rate": 1.0820787715635141e-05, "loss": 3.3311, "step": 2393088 }, { "epoch": 0.01, "learning_rate": 1.0812418146928352e-05, "loss": 3.341, "step": 2393600 }, { "epoch": 0.01, "learning_rate": 1.0804032199417832e-05, "loss": 3.3295, "step": 2394112 }, { "epoch": 0.01, "learning_rate": 1.0795646251907312e-05, "loss": 3.3566, "step": 2394624 }, { "epoch": 0.01, "learning_rate": 1.0787260304396792e-05, "loss": 3.3401, "step": 2395136 }, { "epoch": 0.01, "learning_rate": 1.0778874356886272e-05, "loss": 3.3602, "step": 2395648 }, { "epoch": 0.01, "learning_rate": 1.0770488409375752e-05, "loss": 3.3389, "step": 2396160 }, { "epoch": 0.01, "learning_rate": 1.0762102461865232e-05, "loss": 3.3328, "step": 2396672 }, { "epoch": 0.01, "learning_rate": 1.0753716514354712e-05, "loss": 3.3507, "step": 2397184 }, { "epoch": 0.01, "learning_rate": 1.0745346945647922e-05, "loss": 3.3342, "step": 2397696 }, { "epoch": 0.01, "learning_rate": 1.0736960998137404e-05, "loss": 3.3371, "step": 2398208 }, { "epoch": 0.01, "learning_rate": 1.0728575050626882e-05, "loss": 3.336, "step": 2398720 }, { "epoch": 0.01, "learning_rate": 1.0720189103116362e-05, "loss": 3.3472, "step": 2399232 }, { "epoch": 0.01, "learning_rate": 1.0711819534409575e-05, "loss": 3.3288, "step": 2399744 }, { "epoch": 0.01, "learning_rate": 1.0703433586899055e-05, "loss": 3.3349, "step": 2400256 }, { "epoch": 0.01, "learning_rate": 1.0695047639388533e-05, "loss": 3.3329, "step": 2400768 }, { "epoch": 0.01, "learning_rate": 1.0686661691878015e-05, "loss": 3.3318, "step": 2401280 }, { "epoch": 0.01, "learning_rate": 1.0678292123171225e-05, "loss": 3.3471, "step": 2401792 }, { "epoch": 0.01, "learning_rate": 1.0669906175660704e-05, "loss": 3.3459, "step": 2402304 }, { "epoch": 0.01, "learning_rate": 1.0661520228150185e-05, "loss": 3.3359, "step": 2402816 }, { "epoch": 0.01, "learning_rate": 1.0653150659443396e-05, "loss": 3.3397, "step": 2403328 }, { "epoch": 0.01, "learning_rate": 1.0644764711932876e-05, "loss": 3.3474, "step": 2403840 }, { "epoch": 0.01, "learning_rate": 1.0636378764422356e-05, "loss": 3.3396, "step": 2404352 }, { "epoch": 0.01, "learning_rate": 1.0627992816911836e-05, "loss": 3.347, "step": 2404864 }, { "epoch": 0.01, "learning_rate": 1.0619606869401316e-05, "loss": 3.3421, "step": 2405376 }, { "epoch": 0.01, "learning_rate": 1.0611220921890796e-05, "loss": 3.3387, "step": 2405888 }, { "epoch": 0.01, "learning_rate": 1.0602851353184007e-05, "loss": 3.3479, "step": 2406400 }, { "epoch": 0.01, "learning_rate": 1.0594465405673487e-05, "loss": 3.3396, "step": 2406912 }, { "epoch": 0.01, "learning_rate": 1.0586079458162967e-05, "loss": 3.3417, "step": 2407424 }, { "epoch": 0.01, "learning_rate": 1.0577693510652447e-05, "loss": 3.3509, "step": 2407936 }, { "epoch": 0.01, "learning_rate": 1.0569307563141926e-05, "loss": 3.3395, "step": 2408448 }, { "epoch": 0.01, "learning_rate": 1.0560921615631406e-05, "loss": 3.3234, "step": 2408960 }, { "epoch": 0.01, "learning_rate": 1.0552535668120886e-05, "loss": 3.3412, "step": 2409472 }, { "epoch": 0.01, "learning_rate": 1.0544149720610366e-05, "loss": 3.345, "step": 2409984 }, { "epoch": 0.01, "learning_rate": 1.053579653070731e-05, "loss": 3.3417, "step": 2410496 }, { "epoch": 0.01, "learning_rate": 1.052741058319679e-05, "loss": 3.3408, "step": 2411008 }, { "epoch": 0.01, "learning_rate": 1.0519024635686268e-05, "loss": 3.3361, "step": 2411520 }, { "epoch": 0.02, "learning_rate": 1.051063868817575e-05, "loss": 3.3415, "step": 2412032 }, { "epoch": 0.02, "learning_rate": 1.050225274066523e-05, "loss": 3.3373, "step": 2412544 }, { "epoch": 0.02, "learning_rate": 1.049386679315471e-05, "loss": 3.3354, "step": 2413056 }, { "epoch": 0.02, "learning_rate": 1.0485480845644188e-05, "loss": 3.3408, "step": 2413568 }, { "epoch": 0.02, "learning_rate": 1.047709489813367e-05, "loss": 3.3393, "step": 2414080 }, { "epoch": 0.02, "learning_rate": 1.046872532942688e-05, "loss": 3.3547, "step": 2414592 }, { "epoch": 0.02, "learning_rate": 1.0460339381916358e-05, "loss": 3.3218, "step": 2415104 }, { "epoch": 0.02, "learning_rate": 1.045195343440584e-05, "loss": 3.3347, "step": 2415616 }, { "epoch": 0.02, "learning_rate": 1.044356748689532e-05, "loss": 3.3391, "step": 2416128 }, { "epoch": 0.02, "learning_rate": 1.043519791818853e-05, "loss": 3.3419, "step": 2416640 }, { "epoch": 0.02, "learning_rate": 1.042681197067801e-05, "loss": 3.3419, "step": 2417152 }, { "epoch": 0.02, "learning_rate": 1.041842602316749e-05, "loss": 3.3446, "step": 2417664 }, { "epoch": 0.02, "learning_rate": 1.041004007565697e-05, "loss": 3.3266, "step": 2418176 }, { "epoch": 0.02, "learning_rate": 1.0401670506950183e-05, "loss": 3.3407, "step": 2418688 }, { "epoch": 0.02, "learning_rate": 1.0393284559439661e-05, "loss": 3.3383, "step": 2419200 }, { "epoch": 0.02, "learning_rate": 1.0384898611929141e-05, "loss": 3.3308, "step": 2419712 }, { "epoch": 0.02, "learning_rate": 1.0376512664418623e-05, "loss": 3.33, "step": 2420224 }, { "epoch": 0.02, "learning_rate": 1.0368143095711832e-05, "loss": 3.3399, "step": 2420736 }, { "epoch": 0.02, "learning_rate": 1.0359757148201312e-05, "loss": 3.3454, "step": 2421248 }, { "epoch": 0.02, "learning_rate": 1.0351371200690794e-05, "loss": 3.3217, "step": 2421760 }, { "epoch": 0.02, "learning_rate": 1.0342985253180274e-05, "loss": 3.3332, "step": 2422272 }, { "epoch": 0.02, "learning_rate": 1.0334615684473484e-05, "loss": 3.3259, "step": 2422784 }, { "epoch": 0.02, "learning_rate": 1.0326229736962964e-05, "loss": 3.3444, "step": 2423296 }, { "epoch": 0.02, "learning_rate": 1.0317843789452444e-05, "loss": 3.3338, "step": 2423808 }, { "epoch": 0.02, "learning_rate": 1.0309457841941923e-05, "loss": 3.3352, "step": 2424320 }, { "epoch": 0.02, "learning_rate": 1.0301088273235135e-05, "loss": 3.3399, "step": 2424832 }, { "epoch": 0.02, "learning_rate": 1.0292702325724615e-05, "loss": 3.3419, "step": 2425344 }, { "epoch": 0.02, "learning_rate": 1.0284332757017828e-05, "loss": 3.3347, "step": 2425856 }, { "epoch": 0.02, "learning_rate": 1.0275946809507306e-05, "loss": 3.3405, "step": 2426368 }, { "epoch": 0.02, "learning_rate": 1.0267560861996786e-05, "loss": 3.3418, "step": 2426880 }, { "epoch": 0.02, "learning_rate": 1.0259174914486266e-05, "loss": 3.3297, "step": 2427392 }, { "epoch": 0.02, "learning_rate": 1.0250788966975747e-05, "loss": 3.3254, "step": 2427904 }, { "epoch": 0.02, "learning_rate": 1.0242419398268956e-05, "loss": 3.3354, "step": 2428416 }, { "epoch": 0.02, "learning_rate": 1.0234033450758438e-05, "loss": 3.3348, "step": 2428928 }, { "epoch": 0.02, "learning_rate": 1.0225647503247918e-05, "loss": 3.3461, "step": 2429440 }, { "epoch": 0.02, "learning_rate": 1.0217261555737396e-05, "loss": 3.3308, "step": 2429952 }, { "epoch": 0.02, "learning_rate": 1.0208891987030609e-05, "loss": 3.3351, "step": 2430464 }, { "epoch": 0.02, "learning_rate": 1.0200506039520089e-05, "loss": 3.3342, "step": 2430976 }, { "epoch": 0.02, "learning_rate": 1.0192120092009569e-05, "loss": 3.328, "step": 2431488 }, { "epoch": 0.02, "learning_rate": 1.0183734144499047e-05, "loss": 3.3241, "step": 2432000 }, { "epoch": 0.02, "learning_rate": 1.0175348196988529e-05, "loss": 3.342, "step": 2432512 }, { "epoch": 0.02, "learning_rate": 1.0166962249478009e-05, "loss": 3.3509, "step": 2433024 }, { "epoch": 0.02, "learning_rate": 1.0158576301967487e-05, "loss": 3.3369, "step": 2433536 }, { "epoch": 0.02, "learning_rate": 1.01502067332607e-05, "loss": 3.3322, "step": 2434048 }, { "epoch": 0.02, "learning_rate": 1.014182078575018e-05, "loss": 3.3412, "step": 2434560 }, { "epoch": 0.02, "learning_rate": 1.013343483823966e-05, "loss": 3.3367, "step": 2435072 }, { "epoch": 0.02, "learning_rate": 1.012504889072914e-05, "loss": 3.3307, "step": 2435584 }, { "epoch": 0.02, "learning_rate": 1.011666294321862e-05, "loss": 3.3403, "step": 2436096 }, { "epoch": 0.02, "learning_rate": 1.0108276995708099e-05, "loss": 3.3467, "step": 2436608 }, { "epoch": 0.02, "learning_rate": 1.0099891048197577e-05, "loss": 3.3423, "step": 2437120 }, { "epoch": 0.02, "learning_rate": 1.0091505100687059e-05, "loss": 3.3405, "step": 2437632 }, { "epoch": 0.02, "learning_rate": 1.008313553198027e-05, "loss": 3.3334, "step": 2438144 }, { "epoch": 0.02, "learning_rate": 1.007474958446975e-05, "loss": 3.3407, "step": 2438656 }, { "epoch": 0.02, "learning_rate": 1.006636363695923e-05, "loss": 3.3394, "step": 2439168 }, { "epoch": 0.02, "learning_rate": 1.005797768944871e-05, "loss": 3.3275, "step": 2439680 }, { "epoch": 0.02, "learning_rate": 1.004960812074192e-05, "loss": 3.3555, "step": 2440192 }, { "epoch": 0.02, "learning_rate": 1.00412221732314e-05, "loss": 3.3349, "step": 2440704 }, { "epoch": 0.02, "learning_rate": 1.0032852604524611e-05, "loss": 3.3438, "step": 2441216 }, { "epoch": 0.02, "learning_rate": 1.0024466657014093e-05, "loss": 3.3369, "step": 2441728 }, { "epoch": 0.03, "learning_rate": 1.0016080709503573e-05, "loss": 3.3348, "step": 2442240 }, { "epoch": 0.03, "eval_loss": 3.9253616333007812, "eval_runtime": 303.6118, "eval_samples_per_second": 1256.838, "eval_steps_per_second": 39.277, "step": 2442240 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.5845824894840013e+18, "trial_name": null, "trial_params": null }