| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 371860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.375e-06, | |
| "loss": 6.8604, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.875e-05, | |
| "loss": 5.3674, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.8125e-05, | |
| "loss": 5.0373, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.75e-05, | |
| "loss": 4.8124, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.6874999999999994e-05, | |
| "loss": 4.6412, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.625e-05, | |
| "loss": 4.505, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.5625e-05, | |
| "loss": 4.3856, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 7.5e-05, | |
| "loss": 4.2903, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.437499999999999e-05, | |
| "loss": 4.2018, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.374999999999999e-05, | |
| "loss": 4.132, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000103115625, | |
| "loss": 4.0768, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.000112490625, | |
| "loss": 4.004, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00012184687499999999, | |
| "loss": 3.9406, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.000131221875, | |
| "loss": 3.8851, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001405875, | |
| "loss": 3.8408, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00014995312499999997, | |
| "loss": 3.8061, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.000159328125, | |
| "loss": 3.7695, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.000168703125, | |
| "loss": 3.7341, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.3468402958775906, | |
| "eval_loss": 3.8767805099487305, | |
| "eval_runtime": 147.702, | |
| "eval_samples_per_second": 392.121, | |
| "eval_steps_per_second": 6.127, | |
| "step": 18593 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00017805937499999996, | |
| "loss": 3.6986, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00018743437499999996, | |
| "loss": 3.6662, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00019680937499999996, | |
| "loss": 3.6454, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00020618437499999995, | |
| "loss": 3.6288, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00021554999999999998, | |
| "loss": 3.6088, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00022492499999999998, | |
| "loss": 3.5965, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00023429999999999998, | |
| "loss": 3.5766, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00024367499999999997, | |
| "loss": 3.5683, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.000253040625, | |
| "loss": 3.5511, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.000262415625, | |
| "loss": 3.5396, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00027178124999999994, | |
| "loss": 3.5261, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00028115624999999994, | |
| "loss": 3.5144, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00029053124999999994, | |
| "loss": 3.5059, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.000299896875, | |
| "loss": 3.4945, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00029912699346789853, | |
| "loss": 3.4836, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00029824515977167065, | |
| "loss": 3.4697, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0002973633260754428, | |
| "loss": 3.4557, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.0002964806096628023, | |
| "loss": 3.4421, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002955978932501618, | |
| "loss": 3.4322, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3750516722944931, | |
| "eval_loss": 3.6157917976379395, | |
| "eval_runtime": 148.1928, | |
| "eval_samples_per_second": 390.822, | |
| "eval_steps_per_second": 6.107, | |
| "step": 37186 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00029471605955393393, | |
| "loss": 3.39, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00029383334314129345, | |
| "loss": 3.3768, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.00029295150944506557, | |
| "loss": 3.3755, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0002920687930324251, | |
| "loss": 3.3656, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00029118695933619726, | |
| "loss": 3.3631, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.0002903042429235567, | |
| "loss": 3.3582, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00028942152651091624, | |
| "loss": 3.3528, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00028853969281468836, | |
| "loss": 3.3405, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0002876569764020479, | |
| "loss": 3.338, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.00028677425998940734, | |
| "loss": 3.3309, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.00028589154357676685, | |
| "loss": 3.3267, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00028500970988053903, | |
| "loss": 3.3231, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00028412787618431115, | |
| "loss": 3.3142, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 0.00028324515977167067, | |
| "loss": 3.312, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.00028236244335903013, | |
| "loss": 3.3065, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 0.00028147972694638965, | |
| "loss": 3.3061, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.00028059701053374916, | |
| "loss": 3.2972, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00027971605955393394, | |
| "loss": 3.2902, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.388316999188897, | |
| "eval_loss": 3.481745958328247, | |
| "eval_runtime": 148.0192, | |
| "eval_samples_per_second": 391.28, | |
| "eval_steps_per_second": 6.114, | |
| "step": 55779 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00027883334314129346, | |
| "loss": 3.2736, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0002779506267286529, | |
| "loss": 3.2301, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00027706791031601244, | |
| "loss": 3.2324, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 0.00027618519390337196, | |
| "loss": 3.231, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.0002753033602071441, | |
| "loss": 3.2321, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0002744206437945036, | |
| "loss": 3.2256, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.0002735388100982757, | |
| "loss": 3.2267, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.00027265609368563523, | |
| "loss": 3.2252, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.0002717742599894074, | |
| "loss": 3.2257, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.00027089154357676687, | |
| "loss": 3.2254, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 0.0002700088271641264, | |
| "loss": 3.226, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 0.00026912787618431117, | |
| "loss": 3.2159, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 0.0002682451597716707, | |
| "loss": 3.218, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0002673633260754428, | |
| "loss": 3.2194, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0002664806096628023, | |
| "loss": 3.2157, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.00026559789325016184, | |
| "loss": 3.216, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 0.0002647151768375213, | |
| "loss": 3.2113, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0002638324604248808, | |
| "loss": 3.2057, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00026295062672865294, | |
| "loss": 3.21, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.39601666654461715, | |
| "eval_loss": 3.4285695552825928, | |
| "eval_runtime": 148.0054, | |
| "eval_samples_per_second": 391.317, | |
| "eval_steps_per_second": 6.115, | |
| "step": 74372 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0002620687930324251, | |
| "loss": 3.1616, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0002611860766197846, | |
| "loss": 3.145, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.0002603033602071441, | |
| "loss": 3.1432, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 0.0002594206437945036, | |
| "loss": 3.1437, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00025853881009827573, | |
| "loss": 3.1501, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 0.00025765697640204785, | |
| "loss": 3.1502, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00025677425998940737, | |
| "loss": 3.1521, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.0002558924262931795, | |
| "loss": 3.1551, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 0.000255009709880539, | |
| "loss": 3.1541, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 0.0002541269934678985, | |
| "loss": 3.1562, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.00025324427705525804, | |
| "loss": 3.1514, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 0.00025236244335903016, | |
| "loss": 3.1552, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.0002514797269463897, | |
| "loss": 3.1505, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0002505970105337492, | |
| "loss": 3.1536, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.0002497142941211087, | |
| "loss": 3.1477, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 0.00024883246042488083, | |
| "loss": 3.151, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.0002479515094450656, | |
| "loss": 3.1509, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.0002470687930324251, | |
| "loss": 3.1498, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3977911769485771, | |
| "eval_loss": 3.415144205093384, | |
| "eval_runtime": 148.3328, | |
| "eval_samples_per_second": 390.453, | |
| "eval_steps_per_second": 6.101, | |
| "step": 92965 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0002461860766197846, | |
| "loss": 3.1436, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.0002453033602071441, | |
| "loss": 3.0775, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0002444206437945036, | |
| "loss": 3.0873, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.00024353881009827574, | |
| "loss": 3.0875, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.00024265609368563526, | |
| "loss": 3.0879, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00024177337727299472, | |
| "loss": 3.0948, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.00024089066086035424, | |
| "loss": 3.096, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.00024000882716412636, | |
| "loss": 3.1026, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00023912611075148588, | |
| "loss": 3.0963, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 0.00023824515977167069, | |
| "loss": 3.0989, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.00023736244335903015, | |
| "loss": 3.0981, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 0.00023647972694638966, | |
| "loss": 3.1033, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.00023559789325016179, | |
| "loss": 3.1024, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 0.0002347151768375213, | |
| "loss": 3.1051, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.00023383334314129345, | |
| "loss": 3.102, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 0.00023295062672865294, | |
| "loss": 3.1017, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.00023206791031601246, | |
| "loss": 3.103, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 0.00023118519390337195, | |
| "loss": 3.0997, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0002303033602071441, | |
| "loss": 3.0981, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.40221902146429994, | |
| "eval_loss": 3.3789608478546143, | |
| "eval_runtime": 148.2536, | |
| "eval_samples_per_second": 390.662, | |
| "eval_steps_per_second": 6.104, | |
| "step": 111558 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 0.0002294206437945036, | |
| "loss": 3.0702, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.0002285379273818631, | |
| "loss": 3.0358, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 0.00022765609368563525, | |
| "loss": 3.04, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 0.00022677337727299474, | |
| "loss": 3.0432, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 0.00022589242629317952, | |
| "loss": 3.0491, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.00022500970988053904, | |
| "loss": 3.0494, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00022412699346789852, | |
| "loss": 3.0538, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00022324427705525804, | |
| "loss": 3.0567, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 0.00022236156064261753, | |
| "loss": 3.0628, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00022147972694638968, | |
| "loss": 3.0546, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 0.0002205970105337492, | |
| "loss": 3.0556, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.00021971517683752132, | |
| "loss": 3.0621, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00021883334314129347, | |
| "loss": 3.0591, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00021795062672865296, | |
| "loss": 3.0584, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.00021706791031601247, | |
| "loss": 3.0586, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.00021618519390337193, | |
| "loss": 3.0635, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 0.00021530247749073145, | |
| "loss": 3.0624, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 0.00021441976107809097, | |
| "loss": 3.0633, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.0002135379273818631, | |
| "loss": 3.0651, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.403432753526464, | |
| "eval_loss": 3.375000238418579, | |
| "eval_runtime": 148.8138, | |
| "eval_samples_per_second": 389.191, | |
| "eval_steps_per_second": 6.081, | |
| "step": 130151 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.0002126552109692226, | |
| "loss": 3.0019, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 0.0002117724945565821, | |
| "loss": 3.002, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.0002108897781439416, | |
| "loss": 2.9999, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.00021000794444771376, | |
| "loss": 3.009, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.00020912522803507325, | |
| "loss": 3.0157, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 0.00020824251162243276, | |
| "loss": 3.0143, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 0.0002073606779262049, | |
| "loss": 3.0181, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 0.0002064779615135644, | |
| "loss": 3.0178, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 0.00020559612781733655, | |
| "loss": 3.0246, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 0.00020471341140469604, | |
| "loss": 3.0227, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 0.00020383069499205553, | |
| "loss": 3.0226, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 0.00020294797857941502, | |
| "loss": 3.029, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00020206614488318717, | |
| "loss": 3.0251, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 0.00020118519390337198, | |
| "loss": 3.0281, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 0.00020030247749073146, | |
| "loss": 3.0261, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 0.00019941976107809095, | |
| "loss": 3.0284, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 0.0001985379273818631, | |
| "loss": 3.0324, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 0.0001976552109692226, | |
| "loss": 3.0292, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4041203066054072, | |
| "eval_loss": 3.3879382610321045, | |
| "eval_runtime": 149.4888, | |
| "eval_samples_per_second": 387.434, | |
| "eval_steps_per_second": 6.054, | |
| "step": 148744 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 0.0001967724945565821, | |
| "loss": 3.0108, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 0.0001958897781439416, | |
| "loss": 2.9647, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 0.0001950070617313011, | |
| "loss": 2.9687, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 0.00019412522803507323, | |
| "loss": 2.9739, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 0.00019324251162243275, | |
| "loss": 2.9785, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 0.0001923606779262049, | |
| "loss": 2.9798, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 0.0001914779615135644, | |
| "loss": 2.9856, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 0.00019059612781733654, | |
| "loss": 2.9866, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 0.00018971429412110866, | |
| "loss": 2.9896, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 0.00018883157770846818, | |
| "loss": 2.9881, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 0.0001879488612958277, | |
| "loss": 2.9945, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 0.00018706614488318718, | |
| "loss": 2.995, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 0.00018618431118695933, | |
| "loss": 2.9923, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 0.00018530159477431882, | |
| "loss": 2.9984, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 0.00018441976107809097, | |
| "loss": 2.9962, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.00018353704466545048, | |
| "loss": 2.9945, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 0.00018265432825280997, | |
| "loss": 3.0023, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 0.00018177249455658212, | |
| "loss": 3.0015, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 0.0001808897781439416, | |
| "loss": 3.0031, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.40460066663222405, | |
| "eval_loss": 3.3772807121276855, | |
| "eval_runtime": 149.5517, | |
| "eval_samples_per_second": 387.271, | |
| "eval_steps_per_second": 6.051, | |
| "step": 167337 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 0.0001800070617313011, | |
| "loss": 2.9559, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.00017912522803507328, | |
| "loss": 2.9312, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 0.00017824251162243274, | |
| "loss": 2.9478, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 0.00017736067792620491, | |
| "loss": 2.9454, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 0.00017647796151356438, | |
| "loss": 2.9545, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 0.0001755952451009239, | |
| "loss": 2.9576, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 0.00017471341140469601, | |
| "loss": 2.9584, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 9.41, | |
| "learning_rate": 0.00017383069499205553, | |
| "loss": 2.9623, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 0.00017294797857941505, | |
| "loss": 2.9621, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 0.00017206614488318717, | |
| "loss": 2.9639, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 0.00017118342847054669, | |
| "loss": 2.9646, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 0.00017030071205790617, | |
| "loss": 2.971, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 0.0001694179956452657, | |
| "loss": 2.9679, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 0.0001685352792326252, | |
| "loss": 2.9688, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 0.00016765344553639733, | |
| "loss": 2.9722, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 0.00016677072912375684, | |
| "loss": 2.9733, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 0.00016588889542752897, | |
| "loss": 2.9735, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00016500617901488848, | |
| "loss": 2.9713, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.40607473367395674, | |
| "eval_loss": 3.3769428730010986, | |
| "eval_runtime": 149.8012, | |
| "eval_samples_per_second": 386.626, | |
| "eval_steps_per_second": 6.041, | |
| "step": 185930 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00016412434531866063, | |
| "loss": 2.9708, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 0.00016324162890602012, | |
| "loss": 2.9066, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 0.00016235979520979227, | |
| "loss": 2.9124, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 0.00016147707879715173, | |
| "loss": 2.9222, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 0.00016059436238451125, | |
| "loss": 2.9209, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 0.00015971252868828337, | |
| "loss": 2.9286, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 0.00015882981227564289, | |
| "loss": 2.9338, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 0.0001579470958630024, | |
| "loss": 2.9341, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 0.0001570643794503619, | |
| "loss": 2.9312, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 0.0001561816630377214, | |
| "loss": 2.9368, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 0.00015529894662508092, | |
| "loss": 2.9439, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 0.00015441711292885305, | |
| "loss": 2.9446, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 0.00015353439651621256, | |
| "loss": 2.9427, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 0.00015265168010357205, | |
| "loss": 2.948, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 0.0001517698464073442, | |
| "loss": 2.946, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.00015088712999470372, | |
| "loss": 2.9485, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 0.00015000441358206318, | |
| "loss": 2.9457, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 0.00014912257988583533, | |
| "loss": 2.9496, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 0.00014823986347319484, | |
| "loss": 2.9529, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.40687119075338524, | |
| "eval_loss": 3.377762794494629, | |
| "eval_runtime": 148.6642, | |
| "eval_samples_per_second": 389.583, | |
| "eval_steps_per_second": 6.088, | |
| "step": 204523 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 0.00014735714706055433, | |
| "loss": 2.9161, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 11.08, | |
| "learning_rate": 0.00014647531336432648, | |
| "loss": 2.8894, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 0.00014559259695168597, | |
| "loss": 2.8969, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 0.00014470988053904549, | |
| "loss": 2.9007, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 0.0001438280468428176, | |
| "loss": 2.9004, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "learning_rate": 0.00014294533043017712, | |
| "loss": 2.905, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 0.0001420643794503619, | |
| "loss": 2.9086, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 0.00014118166303772142, | |
| "loss": 2.9085, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 0.0001402989466250809, | |
| "loss": 2.9164, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 11.51, | |
| "learning_rate": 0.0001394162302124404, | |
| "loss": 2.9167, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 0.00013853439651621255, | |
| "loss": 2.9206, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 0.00013765168010357204, | |
| "loss": 2.919, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 0.0001367698464073442, | |
| "loss": 2.9194, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 0.0001358871299947037, | |
| "loss": 2.9209, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 0.0001350044135820632, | |
| "loss": 2.9232, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 11.83, | |
| "learning_rate": 0.00013412169716942268, | |
| "loss": 2.9243, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 0.00013323986347319483, | |
| "loss": 2.9277, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 0.00013235714706055432, | |
| "loss": 2.9257, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 0.00013147531336432647, | |
| "loss": 2.9286, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4076532706236195, | |
| "eval_loss": 3.3611626625061035, | |
| "eval_runtime": 148.2811, | |
| "eval_samples_per_second": 390.589, | |
| "eval_steps_per_second": 6.103, | |
| "step": 223116 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 0.00013059259695168599, | |
| "loss": 2.8738, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 0.00012970988053904547, | |
| "loss": 2.8733, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 0.000128827164126405, | |
| "loss": 2.8777, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 0.00012794444771376448, | |
| "loss": 2.8803, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 0.00012706261401753663, | |
| "loss": 2.8838, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 0.00012617989760489612, | |
| "loss": 2.8893, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 0.00012529718119225563, | |
| "loss": 2.8851, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 0.00012441534749602776, | |
| "loss": 2.8896, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 0.00012353263108338727, | |
| "loss": 2.8907, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 0.0001226507973871594, | |
| "loss": 2.8957, | |
| "step": 233000 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 0.00012176808097451891, | |
| "loss": 2.8963, | |
| "step": 234000 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 0.00012088536456187841, | |
| "loss": 2.8977, | |
| "step": 235000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 0.0001200026481492379, | |
| "loss": 2.8986, | |
| "step": 236000 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 0.00011912081445301006, | |
| "loss": 2.8993, | |
| "step": 237000 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 0.00011823809804036955, | |
| "loss": 2.9017, | |
| "step": 238000 | |
| }, | |
| { | |
| "epoch": 12.85, | |
| "learning_rate": 0.00011735626434414169, | |
| "loss": 2.9029, | |
| "step": 239000 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 0.00011647354793150119, | |
| "loss": 2.9069, | |
| "step": 240000 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 0.00011559171423527333, | |
| "loss": 2.9065, | |
| "step": 241000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4073469823212058, | |
| "eval_loss": 3.3685669898986816, | |
| "eval_runtime": 148.8974, | |
| "eval_samples_per_second": 388.973, | |
| "eval_steps_per_second": 6.078, | |
| "step": 241709 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 0.00011470899782263284, | |
| "loss": 2.888, | |
| "step": 242000 | |
| }, | |
| { | |
| "epoch": 13.07, | |
| "learning_rate": 0.00011382716412640498, | |
| "loss": 2.8448, | |
| "step": 243000 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 0.00011294444771376448, | |
| "loss": 2.8515, | |
| "step": 244000 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 0.00011206173130112398, | |
| "loss": 2.8606, | |
| "step": 245000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 0.00011117989760489612, | |
| "loss": 2.862, | |
| "step": 246000 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 0.00011029718119225563, | |
| "loss": 2.8684, | |
| "step": 247000 | |
| }, | |
| { | |
| "epoch": 13.34, | |
| "learning_rate": 0.00010941446477961512, | |
| "loss": 2.8647, | |
| "step": 248000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 0.00010853263108338727, | |
| "loss": 2.8691, | |
| "step": 249000 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 0.00010764991467074676, | |
| "loss": 2.8722, | |
| "step": 250000 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 0.00010676719825810626, | |
| "loss": 2.8771, | |
| "step": 251000 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 0.00010588624727829105, | |
| "loss": 2.8746, | |
| "step": 252000 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 0.00010500353086565056, | |
| "loss": 2.8798, | |
| "step": 253000 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 0.00010412081445301005, | |
| "loss": 2.8781, | |
| "step": 254000 | |
| }, | |
| { | |
| "epoch": 13.71, | |
| "learning_rate": 0.00010323809804036955, | |
| "loss": 2.8778, | |
| "step": 255000 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 0.00010235538162772906, | |
| "loss": 2.8773, | |
| "step": 256000 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 0.00010147266521508855, | |
| "loss": 2.8783, | |
| "step": 257000 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 0.00010059083151886071, | |
| "loss": 2.886, | |
| "step": 258000 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 9.97081151062202e-05, | |
| "loss": 2.8859, | |
| "step": 259000 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 9.882628140999235e-05, | |
| "loss": 2.8837, | |
| "step": 260000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.40777769394804814, | |
| "eval_loss": 3.386112689971924, | |
| "eval_runtime": 148.4943, | |
| "eval_samples_per_second": 390.028, | |
| "eval_steps_per_second": 6.095, | |
| "step": 260302 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 9.794356499735184e-05, | |
| "loss": 2.8456, | |
| "step": 261000 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 9.706084858471134e-05, | |
| "loss": 2.8337, | |
| "step": 262000 | |
| }, | |
| { | |
| "epoch": 14.15, | |
| "learning_rate": 9.617901488848347e-05, | |
| "loss": 2.8387, | |
| "step": 263000 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 9.529718119225564e-05, | |
| "loss": 2.8384, | |
| "step": 264000 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 9.441446477961513e-05, | |
| "loss": 2.8414, | |
| "step": 265000 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 9.353174836697463e-05, | |
| "loss": 2.8443, | |
| "step": 266000 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 9.264903195433413e-05, | |
| "loss": 2.8524, | |
| "step": 267000 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 9.176631554169362e-05, | |
| "loss": 2.8527, | |
| "step": 268000 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 9.088448184546578e-05, | |
| "loss": 2.8543, | |
| "step": 269000 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 9.000176543282527e-05, | |
| "loss": 2.8563, | |
| "step": 270000 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 8.911993173659742e-05, | |
| "loss": 2.8578, | |
| "step": 271000 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 8.823721532395691e-05, | |
| "loss": 2.8596, | |
| "step": 272000 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 8.735449891131641e-05, | |
| "loss": 2.855, | |
| "step": 273000 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 8.647266521508856e-05, | |
| "loss": 2.8646, | |
| "step": 274000 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 8.55908315188607e-05, | |
| "loss": 2.8602, | |
| "step": 275000 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 8.47081151062202e-05, | |
| "loss": 2.8634, | |
| "step": 276000 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 8.38253986935797e-05, | |
| "loss": 2.8631, | |
| "step": 277000 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 8.29426822809392e-05, | |
| "loss": 2.8621, | |
| "step": 278000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.4076843092715061, | |
| "eval_loss": 3.3850700855255127, | |
| "eval_runtime": 148.6493, | |
| "eval_samples_per_second": 389.622, | |
| "eval_steps_per_second": 6.088, | |
| "step": 278895 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 8.20599658682987e-05, | |
| "loss": 2.8557, | |
| "step": 279000 | |
| }, | |
| { | |
| "epoch": 15.06, | |
| "learning_rate": 8.117813217207086e-05, | |
| "loss": 2.8128, | |
| "step": 280000 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 8.029541575943034e-05, | |
| "loss": 2.8187, | |
| "step": 281000 | |
| }, | |
| { | |
| "epoch": 15.17, | |
| "learning_rate": 7.941358206320248e-05, | |
| "loss": 2.8213, | |
| "step": 282000 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 7.853086565056198e-05, | |
| "loss": 2.8249, | |
| "step": 283000 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 7.764814923792149e-05, | |
| "loss": 2.8253, | |
| "step": 284000 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 7.6765432825281e-05, | |
| "loss": 2.8271, | |
| "step": 285000 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 7.588359912905314e-05, | |
| "loss": 2.8351, | |
| "step": 286000 | |
| }, | |
| { | |
| "epoch": 15.44, | |
| "learning_rate": 7.500088271641264e-05, | |
| "loss": 2.8346, | |
| "step": 287000 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 7.411904902018478e-05, | |
| "loss": 2.8358, | |
| "step": 288000 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 7.323633260754428e-05, | |
| "loss": 2.8346, | |
| "step": 289000 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 7.235361619490378e-05, | |
| "loss": 2.8411, | |
| "step": 290000 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 7.147178249867592e-05, | |
| "loss": 2.8374, | |
| "step": 291000 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 7.058906608603542e-05, | |
| "loss": 2.8405, | |
| "step": 292000 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 6.970634967339492e-05, | |
| "loss": 2.8422, | |
| "step": 293000 | |
| }, | |
| { | |
| "epoch": 15.81, | |
| "learning_rate": 6.882451597716706e-05, | |
| "loss": 2.8431, | |
| "step": 294000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 6.79426822809392e-05, | |
| "loss": 2.8419, | |
| "step": 295000 | |
| }, | |
| { | |
| "epoch": 15.92, | |
| "learning_rate": 6.705996586829871e-05, | |
| "loss": 2.8454, | |
| "step": 296000 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 6.617724945565821e-05, | |
| "loss": 2.8487, | |
| "step": 297000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.4080129024031371, | |
| "eval_loss": 3.3876492977142334, | |
| "eval_runtime": 148.2172, | |
| "eval_samples_per_second": 390.758, | |
| "eval_steps_per_second": 6.106, | |
| "step": 297488 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 6.529453304301771e-05, | |
| "loss": 2.8206, | |
| "step": 298000 | |
| }, | |
| { | |
| "epoch": 16.08, | |
| "learning_rate": 6.441269934678985e-05, | |
| "loss": 2.8018, | |
| "step": 299000 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 6.352998293414935e-05, | |
| "loss": 2.807, | |
| "step": 300000 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 6.264726652150885e-05, | |
| "loss": 2.8058, | |
| "step": 301000 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 6.176543282528099e-05, | |
| "loss": 2.8091, | |
| "step": 302000 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 6.088271641264049e-05, | |
| "loss": 2.8106, | |
| "step": 303000 | |
| }, | |
| { | |
| "epoch": 16.35, | |
| "learning_rate": 6.0000882716412634e-05, | |
| "loss": 2.8151, | |
| "step": 304000 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 5.911816630377214e-05, | |
| "loss": 2.8171, | |
| "step": 305000 | |
| }, | |
| { | |
| "epoch": 16.46, | |
| "learning_rate": 5.823544989113164e-05, | |
| "loss": 2.8159, | |
| "step": 306000 | |
| }, | |
| { | |
| "epoch": 16.51, | |
| "learning_rate": 5.735361619490378e-05, | |
| "loss": 2.8207, | |
| "step": 307000 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 5.647089978226328e-05, | |
| "loss": 2.8201, | |
| "step": 308000 | |
| }, | |
| { | |
| "epoch": 16.62, | |
| "learning_rate": 5.558818336962278e-05, | |
| "loss": 2.817, | |
| "step": 309000 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 5.470634967339492e-05, | |
| "loss": 2.8249, | |
| "step": 310000 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 5.3823633260754425e-05, | |
| "loss": 2.8227, | |
| "step": 311000 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 5.294091684811392e-05, | |
| "loss": 2.8209, | |
| "step": 312000 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 5.205908315188607e-05, | |
| "loss": 2.8207, | |
| "step": 313000 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 5.1176366739245566e-05, | |
| "loss": 2.8236, | |
| "step": 314000 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 5.029365032660506e-05, | |
| "loss": 2.8292, | |
| "step": 315000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 4.941181663037721e-05, | |
| "loss": 2.8243, | |
| "step": 316000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.4080727626526327, | |
| "eval_loss": 3.3908307552337646, | |
| "eval_runtime": 148.0007, | |
| "eval_samples_per_second": 391.329, | |
| "eval_steps_per_second": 6.115, | |
| "step": 316081 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 4.8529100217736706e-05, | |
| "loss": 2.7892, | |
| "step": 317000 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 4.7647266521508855e-05, | |
| "loss": 2.7837, | |
| "step": 318000 | |
| }, | |
| { | |
| "epoch": 17.16, | |
| "learning_rate": 4.676455010886835e-05, | |
| "loss": 2.7921, | |
| "step": 319000 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 4.5881833696227854e-05, | |
| "loss": 2.7919, | |
| "step": 320000 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 2.795, | |
| "step": 321000 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 4.41172835873595e-05, | |
| "loss": 2.7977, | |
| "step": 322000 | |
| }, | |
| { | |
| "epoch": 17.37, | |
| "learning_rate": 4.323544989113164e-05, | |
| "loss": 2.7947, | |
| "step": 323000 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 4.2352733478491144e-05, | |
| "loss": 2.7987, | |
| "step": 324000 | |
| }, | |
| { | |
| "epoch": 17.48, | |
| "learning_rate": 4.147089978226328e-05, | |
| "loss": 2.803, | |
| "step": 325000 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 4.058818336962278e-05, | |
| "loss": 2.7993, | |
| "step": 326000 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 3.9705466956982284e-05, | |
| "loss": 2.8047, | |
| "step": 327000 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 3.882451597716706e-05, | |
| "loss": 2.8075, | |
| "step": 328000 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 3.794179956452657e-05, | |
| "loss": 2.8025, | |
| "step": 329000 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 3.705996586829871e-05, | |
| "loss": 2.805, | |
| "step": 330000 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 3.6177249455658213e-05, | |
| "loss": 2.8074, | |
| "step": 331000 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 3.529453304301771e-05, | |
| "loss": 2.8035, | |
| "step": 332000 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 3.441181663037721e-05, | |
| "loss": 2.8047, | |
| "step": 333000 | |
| }, | |
| { | |
| "epoch": 17.96, | |
| "learning_rate": 3.3529100217736715e-05, | |
| "loss": 2.8078, | |
| "step": 334000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.40818549609668847, | |
| "eval_loss": 3.395204544067383, | |
| "eval_runtime": 150.5726, | |
| "eval_samples_per_second": 384.645, | |
| "eval_steps_per_second": 6.01, | |
| "step": 334674 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.264726652150886e-05, | |
| "loss": 2.8035, | |
| "step": 335000 | |
| }, | |
| { | |
| "epoch": 18.07, | |
| "learning_rate": 3.176455010886835e-05, | |
| "loss": 2.778, | |
| "step": 336000 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 3.0882716412640495e-05, | |
| "loss": 2.7751, | |
| "step": 337000 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.7814, | |
| "step": 338000 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 2.911816630377214e-05, | |
| "loss": 2.78, | |
| "step": 339000 | |
| }, | |
| { | |
| "epoch": 18.29, | |
| "learning_rate": 2.823544989113164e-05, | |
| "loss": 2.7839, | |
| "step": 340000 | |
| }, | |
| { | |
| "epoch": 18.34, | |
| "learning_rate": 2.735273347849114e-05, | |
| "loss": 2.7843, | |
| "step": 341000 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 2.647089978226328e-05, | |
| "loss": 2.7898, | |
| "step": 342000 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 2.5588183369622783e-05, | |
| "loss": 2.7812, | |
| "step": 343000 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 2.4705466956982285e-05, | |
| "loss": 2.7859, | |
| "step": 344000 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.3823633260754428e-05, | |
| "loss": 2.784, | |
| "step": 345000 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 2.2940916848113927e-05, | |
| "loss": 2.7845, | |
| "step": 346000 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 2.2058200435473426e-05, | |
| "loss": 2.7858, | |
| "step": 347000 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.1176366739245572e-05, | |
| "loss": 2.7868, | |
| "step": 348000 | |
| }, | |
| { | |
| "epoch": 18.77, | |
| "learning_rate": 2.029365032660507e-05, | |
| "loss": 2.7852, | |
| "step": 349000 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 1.941093391396457e-05, | |
| "loss": 2.7876, | |
| "step": 350000 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 1.8528217501324073e-05, | |
| "loss": 2.7895, | |
| "step": 351000 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 1.7647266521508855e-05, | |
| "loss": 2.7865, | |
| "step": 352000 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 1.6764550108868357e-05, | |
| "loss": 2.7887, | |
| "step": 353000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.40817017832240676, | |
| "eval_loss": 3.4020464420318604, | |
| "eval_runtime": 148.6908, | |
| "eval_samples_per_second": 389.513, | |
| "eval_steps_per_second": 6.086, | |
| "step": 353267 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 1.5882716412640496e-05, | |
| "loss": 2.7705, | |
| "step": 354000 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 2.7667, | |
| "step": 355000 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 1.41172835873595e-05, | |
| "loss": 2.7656, | |
| "step": 356000 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.323544989113164e-05, | |
| "loss": 2.7689, | |
| "step": 357000 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "learning_rate": 1.2352733478491143e-05, | |
| "loss": 2.7669, | |
| "step": 358000 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 1.1470017065850642e-05, | |
| "loss": 2.7673, | |
| "step": 359000 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.0588183369622786e-05, | |
| "loss": 2.769, | |
| "step": 360000 | |
| }, | |
| { | |
| "epoch": 19.42, | |
| "learning_rate": 9.705466956982285e-06, | |
| "loss": 2.7746, | |
| "step": 361000 | |
| }, | |
| { | |
| "epoch": 19.47, | |
| "learning_rate": 8.823633260754427e-06, | |
| "loss": 2.7726, | |
| "step": 362000 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 7.940916848113928e-06, | |
| "loss": 2.7711, | |
| "step": 363000 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 7.05820043547343e-06, | |
| "loss": 2.7705, | |
| "step": 364000 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 6.176366739245571e-06, | |
| "loss": 2.7765, | |
| "step": 365000 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 5.293650326605072e-06, | |
| "loss": 2.7654, | |
| "step": 366000 | |
| }, | |
| { | |
| "epoch": 19.74, | |
| "learning_rate": 4.410933913964573e-06, | |
| "loss": 2.7721, | |
| "step": 367000 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 3.528217501324074e-06, | |
| "loss": 2.7713, | |
| "step": 368000 | |
| }, | |
| { | |
| "epoch": 19.85, | |
| "learning_rate": 2.646383805096216e-06, | |
| "loss": 2.7746, | |
| "step": 369000 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 1.7645501088683575e-06, | |
| "loss": 2.7718, | |
| "step": 370000 | |
| }, | |
| { | |
| "epoch": 19.95, | |
| "learning_rate": 8.818336962278584e-07, | |
| "loss": 2.7716, | |
| "step": 371000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.40804219428728983, | |
| "eval_loss": 3.408212900161743, | |
| "eval_runtime": 148.9611, | |
| "eval_samples_per_second": 388.806, | |
| "eval_steps_per_second": 6.075, | |
| "step": 371860 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 371860, | |
| "total_flos": 1.56671772051456e+18, | |
| "train_loss": 3.060997604840363, | |
| "train_runtime": 47398.1424, | |
| "train_samples_per_second": 251.046, | |
| "train_steps_per_second": 7.845 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 371860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 5000, | |
| "total_flos": 1.56671772051456e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |