{ "best_metric": 4.068605422973633, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj2/transformer/1/checkpoints/checkpoint-152640", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 152640, "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 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 9.903640559275008e+16, "trial_name": null, "trial_params": null }