| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9956440572495333, | |
| "eval_steps": 10, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012445550715619166, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8073, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002489110143123833, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8285, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00373366521468575, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7975, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004978220286247666, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.798, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006222775357809583, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8443, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0074673304293715, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8074, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008711885500933417, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7588, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009956440572495333, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8136, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01120099564405725, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7397, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012445550715619166, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012445550715619166, | |
| "eval_loss": 2.8210322856903076, | |
| "eval_runtime": 43.0476, | |
| "eval_samples_per_second": 23.23, | |
| "eval_steps_per_second": 0.976, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013690105787181083, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.8275, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014934660858743, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7762, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016179215930304917, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7799, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017423771001866834, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.7906, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018668326073428748, | |
| "grad_norm": 5.01304292678833, | |
| "learning_rate": 2.0746887966804982e-08, | |
| "loss": 2.7712, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019912881144990666, | |
| "grad_norm": 4.976474761962891, | |
| "learning_rate": 4.1493775933609963e-08, | |
| "loss": 2.829, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021157436216552583, | |
| "grad_norm": 5.539012908935547, | |
| "learning_rate": 6.224066390041494e-08, | |
| "loss": 2.813, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0224019912881145, | |
| "grad_norm": 5.4900407791137695, | |
| "learning_rate": 8.298755186721993e-08, | |
| "loss": 2.8126, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.023646546359676415, | |
| "grad_norm": 5.457218647003174, | |
| "learning_rate": 1.037344398340249e-07, | |
| "loss": 2.7482, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "grad_norm": 5.231036186218262, | |
| "learning_rate": 1.2448132780082988e-07, | |
| "loss": 2.8323, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "eval_loss": 2.819715738296509, | |
| "eval_runtime": 43.9884, | |
| "eval_samples_per_second": 22.733, | |
| "eval_steps_per_second": 0.955, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02613565650280025, | |
| "grad_norm": 5.337130546569824, | |
| "learning_rate": 1.4522821576763488e-07, | |
| "loss": 2.776, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027380211574362167, | |
| "grad_norm": 4.973108291625977, | |
| "learning_rate": 1.6597510373443985e-07, | |
| "loss": 2.8239, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02862476664592408, | |
| "grad_norm": 4.8733906745910645, | |
| "learning_rate": 1.8672199170124483e-07, | |
| "loss": 2.8069, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.029869321717486, | |
| "grad_norm": 5.061434745788574, | |
| "learning_rate": 2.074688796680498e-07, | |
| "loss": 2.8063, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031113876789047916, | |
| "grad_norm": 4.782018661499023, | |
| "learning_rate": 2.2821576763485478e-07, | |
| "loss": 2.7488, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03235843186060983, | |
| "grad_norm": 4.394975662231445, | |
| "learning_rate": 2.4896265560165975e-07, | |
| "loss": 2.7683, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03360298693217175, | |
| "grad_norm": 4.475763320922852, | |
| "learning_rate": 2.6970954356846476e-07, | |
| "loss": 2.8143, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03484754200373367, | |
| "grad_norm": 4.362309455871582, | |
| "learning_rate": 2.9045643153526976e-07, | |
| "loss": 2.7875, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03609209707529558, | |
| "grad_norm": 3.9444823265075684, | |
| "learning_rate": 3.112033195020747e-07, | |
| "loss": 2.766, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "grad_norm": 3.4614129066467285, | |
| "learning_rate": 3.319502074688797e-07, | |
| "loss": 2.7644, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "eval_loss": 2.772022008895874, | |
| "eval_runtime": 45.8513, | |
| "eval_samples_per_second": 21.81, | |
| "eval_steps_per_second": 0.916, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.038581207218419414, | |
| "grad_norm": 3.449410915374756, | |
| "learning_rate": 3.5269709543568466e-07, | |
| "loss": 2.7653, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03982576228998133, | |
| "grad_norm": 3.3115482330322266, | |
| "learning_rate": 3.7344398340248966e-07, | |
| "loss": 2.7032, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04107031736154325, | |
| "grad_norm": 3.2057440280914307, | |
| "learning_rate": 3.941908713692946e-07, | |
| "loss": 2.7766, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.042314872433105166, | |
| "grad_norm": 3.4503021240234375, | |
| "learning_rate": 4.149377593360996e-07, | |
| "loss": 2.7214, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.043559427504667084, | |
| "grad_norm": 3.1477363109588623, | |
| "learning_rate": 4.3568464730290456e-07, | |
| "loss": 2.7333, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.044803982576229, | |
| "grad_norm": 2.8025119304656982, | |
| "learning_rate": 4.5643153526970956e-07, | |
| "loss": 2.7535, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04604853764779091, | |
| "grad_norm": 2.967703342437744, | |
| "learning_rate": 4.771784232365145e-07, | |
| "loss": 2.7615, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04729309271935283, | |
| "grad_norm": 2.9308114051818848, | |
| "learning_rate": 4.979253112033195e-07, | |
| "loss": 2.7115, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04853764779091475, | |
| "grad_norm": 2.9203720092773438, | |
| "learning_rate": 5.186721991701245e-07, | |
| "loss": 2.701, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.049782202862476664, | |
| "grad_norm": 2.8226709365844727, | |
| "learning_rate": 5.394190871369295e-07, | |
| "loss": 2.6267, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.049782202862476664, | |
| "eval_loss": 2.6964941024780273, | |
| "eval_runtime": 46.5181, | |
| "eval_samples_per_second": 21.497, | |
| "eval_steps_per_second": 0.903, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05102675793403858, | |
| "grad_norm": 2.7212748527526855, | |
| "learning_rate": 5.601659751037345e-07, | |
| "loss": 2.6505, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0522713130056005, | |
| "grad_norm": 2.658881425857544, | |
| "learning_rate": 5.809128630705395e-07, | |
| "loss": 2.6655, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.053515868077162417, | |
| "grad_norm": 2.4534730911254883, | |
| "learning_rate": 6.016597510373444e-07, | |
| "loss": 2.7098, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.054760423148724334, | |
| "grad_norm": 2.4222075939178467, | |
| "learning_rate": 6.224066390041494e-07, | |
| "loss": 2.6793, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.056004978220286245, | |
| "grad_norm": 2.5824973583221436, | |
| "learning_rate": 6.431535269709543e-07, | |
| "loss": 2.6212, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05724953329184816, | |
| "grad_norm": 2.5982468128204346, | |
| "learning_rate": 6.639004149377594e-07, | |
| "loss": 2.5901, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05849408836341008, | |
| "grad_norm": 2.213388442993164, | |
| "learning_rate": 6.846473029045644e-07, | |
| "loss": 2.6156, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.059738643434972, | |
| "grad_norm": 2.097372531890869, | |
| "learning_rate": 7.053941908713693e-07, | |
| "loss": 2.6154, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.060983198506533914, | |
| "grad_norm": 1.9788408279418945, | |
| "learning_rate": 7.261410788381744e-07, | |
| "loss": 2.5516, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06222775357809583, | |
| "grad_norm": 2.052147150039673, | |
| "learning_rate": 7.468879668049793e-07, | |
| "loss": 2.6128, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06222775357809583, | |
| "eval_loss": 2.6048905849456787, | |
| "eval_runtime": 51.2137, | |
| "eval_samples_per_second": 19.526, | |
| "eval_steps_per_second": 0.82, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06347230864965775, | |
| "grad_norm": 1.8841335773468018, | |
| "learning_rate": 7.676348547717843e-07, | |
| "loss": 2.5617, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06471686372121967, | |
| "grad_norm": 2.0841684341430664, | |
| "learning_rate": 7.883817427385892e-07, | |
| "loss": 2.5627, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06596141879278158, | |
| "grad_norm": 1.8119730949401855, | |
| "learning_rate": 8.091286307053943e-07, | |
| "loss": 2.5572, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0672059738643435, | |
| "grad_norm": 1.7168290615081787, | |
| "learning_rate": 8.298755186721992e-07, | |
| "loss": 2.5465, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.06845052893590542, | |
| "grad_norm": 1.7731754779815674, | |
| "learning_rate": 8.506224066390042e-07, | |
| "loss": 2.543, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06969508400746734, | |
| "grad_norm": 1.9654561281204224, | |
| "learning_rate": 8.713692946058091e-07, | |
| "loss": 2.5547, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.07093963907902924, | |
| "grad_norm": 1.8032375574111938, | |
| "learning_rate": 8.921161825726142e-07, | |
| "loss": 2.5319, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.07218419415059116, | |
| "grad_norm": 1.8775644302368164, | |
| "learning_rate": 9.128630705394191e-07, | |
| "loss": 2.5533, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.07342874922215308, | |
| "grad_norm": 1.6019998788833618, | |
| "learning_rate": 9.336099585062241e-07, | |
| "loss": 2.5402, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.07467330429371499, | |
| "grad_norm": 1.7785435914993286, | |
| "learning_rate": 9.54356846473029e-07, | |
| "loss": 2.4704, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07467330429371499, | |
| "eval_loss": 2.541548252105713, | |
| "eval_runtime": 51.1601, | |
| "eval_samples_per_second": 19.546, | |
| "eval_steps_per_second": 0.821, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07591785936527691, | |
| "grad_norm": 1.5377200841903687, | |
| "learning_rate": 9.751037344398341e-07, | |
| "loss": 2.5028, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.07716241443683883, | |
| "grad_norm": 1.7212916612625122, | |
| "learning_rate": 9.95850622406639e-07, | |
| "loss": 2.4621, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07840696950840075, | |
| "grad_norm": 1.632606029510498, | |
| "learning_rate": 1.0165975103734441e-06, | |
| "loss": 2.4868, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07965152457996266, | |
| "grad_norm": 1.8643872737884521, | |
| "learning_rate": 1.037344398340249e-06, | |
| "loss": 2.4582, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.08089607965152458, | |
| "grad_norm": 1.8329377174377441, | |
| "learning_rate": 1.058091286307054e-06, | |
| "loss": 2.464, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0821406347230865, | |
| "grad_norm": 1.9488356113433838, | |
| "learning_rate": 1.078838174273859e-06, | |
| "loss": 2.4275, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.08338518979464841, | |
| "grad_norm": 1.7663215398788452, | |
| "learning_rate": 1.099585062240664e-06, | |
| "loss": 2.516, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.08462974486621033, | |
| "grad_norm": 1.7675347328186035, | |
| "learning_rate": 1.120331950207469e-06, | |
| "loss": 2.4535, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.08587429993777225, | |
| "grad_norm": 1.7481404542922974, | |
| "learning_rate": 1.141078838174274e-06, | |
| "loss": 2.4089, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.08711885500933417, | |
| "grad_norm": 1.7963330745697021, | |
| "learning_rate": 1.161825726141079e-06, | |
| "loss": 2.4408, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08711885500933417, | |
| "eval_loss": 2.466163396835327, | |
| "eval_runtime": 50.4204, | |
| "eval_samples_per_second": 19.833, | |
| "eval_steps_per_second": 0.833, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08836341008089608, | |
| "grad_norm": 2.053469657897949, | |
| "learning_rate": 1.182572614107884e-06, | |
| "loss": 2.408, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.089607965152458, | |
| "grad_norm": 1.900294303894043, | |
| "learning_rate": 1.2033195020746888e-06, | |
| "loss": 2.4066, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.09085252022401992, | |
| "grad_norm": 2.38637113571167, | |
| "learning_rate": 1.224066390041494e-06, | |
| "loss": 2.3548, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.09209707529558182, | |
| "grad_norm": 1.8274579048156738, | |
| "learning_rate": 1.2448132780082988e-06, | |
| "loss": 2.3844, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.09334163036714374, | |
| "grad_norm": 1.9040184020996094, | |
| "learning_rate": 1.2655601659751037e-06, | |
| "loss": 2.4406, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09458618543870566, | |
| "grad_norm": 2.0351619720458984, | |
| "learning_rate": 1.2863070539419086e-06, | |
| "loss": 2.3624, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.09583074051026758, | |
| "grad_norm": 1.989876627922058, | |
| "learning_rate": 1.307053941908714e-06, | |
| "loss": 2.4097, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0970752955818295, | |
| "grad_norm": 1.8507741689682007, | |
| "learning_rate": 1.3278008298755188e-06, | |
| "loss": 2.4482, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.09831985065339141, | |
| "grad_norm": 2.6118454933166504, | |
| "learning_rate": 1.3485477178423237e-06, | |
| "loss": 2.3178, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.09956440572495333, | |
| "grad_norm": 1.9467326402664185, | |
| "learning_rate": 1.3692946058091288e-06, | |
| "loss": 2.3175, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09956440572495333, | |
| "eval_loss": 2.3719911575317383, | |
| "eval_runtime": 52.3293, | |
| "eval_samples_per_second": 19.11, | |
| "eval_steps_per_second": 0.803, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10080896079651525, | |
| "grad_norm": 2.4913370609283447, | |
| "learning_rate": 1.3900414937759337e-06, | |
| "loss": 2.3063, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.10205351586807716, | |
| "grad_norm": 2.4838919639587402, | |
| "learning_rate": 1.4107883817427386e-06, | |
| "loss": 2.3534, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.10329807093963908, | |
| "grad_norm": 2.798588991165161, | |
| "learning_rate": 1.4315352697095435e-06, | |
| "loss": 2.2732, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.104542626011201, | |
| "grad_norm": 2.688399076461792, | |
| "learning_rate": 1.4522821576763488e-06, | |
| "loss": 2.3112, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.10578718108276292, | |
| "grad_norm": 2.7367143630981445, | |
| "learning_rate": 1.4730290456431537e-06, | |
| "loss": 2.3055, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.10703173615432483, | |
| "grad_norm": 2.6406664848327637, | |
| "learning_rate": 1.4937759336099586e-06, | |
| "loss": 2.312, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.10827629122588675, | |
| "grad_norm": 2.703355312347412, | |
| "learning_rate": 1.5145228215767635e-06, | |
| "loss": 2.3305, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.10952084629744867, | |
| "grad_norm": 2.420084238052368, | |
| "learning_rate": 1.5352697095435686e-06, | |
| "loss": 2.2608, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.11076540136901059, | |
| "grad_norm": 2.999835729598999, | |
| "learning_rate": 1.5560165975103735e-06, | |
| "loss": 2.2389, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.11200995644057249, | |
| "grad_norm": 2.35611629486084, | |
| "learning_rate": 1.5767634854771784e-06, | |
| "loss": 2.2671, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11200995644057249, | |
| "eval_loss": 2.2900290489196777, | |
| "eval_runtime": 52.1871, | |
| "eval_samples_per_second": 19.162, | |
| "eval_steps_per_second": 0.805, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1132545115121344, | |
| "grad_norm": 2.2686431407928467, | |
| "learning_rate": 1.5975103734439833e-06, | |
| "loss": 2.2405, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.11449906658369632, | |
| "grad_norm": 2.883517265319824, | |
| "learning_rate": 1.6182572614107886e-06, | |
| "loss": 2.2364, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.11574362165525824, | |
| "grad_norm": 2.4562909603118896, | |
| "learning_rate": 1.6390041493775935e-06, | |
| "loss": 2.2308, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.11698817672682016, | |
| "grad_norm": 2.7968456745147705, | |
| "learning_rate": 1.6597510373443984e-06, | |
| "loss": 2.1959, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.11823273179838208, | |
| "grad_norm": 2.8692259788513184, | |
| "learning_rate": 1.6804979253112035e-06, | |
| "loss": 2.215, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.119477286869944, | |
| "grad_norm": 2.8436100482940674, | |
| "learning_rate": 1.7012448132780084e-06, | |
| "loss": 2.1816, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.12072184194150591, | |
| "grad_norm": 2.4477386474609375, | |
| "learning_rate": 1.7219917012448133e-06, | |
| "loss": 2.1684, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.12196639701306783, | |
| "grad_norm": 2.610046863555908, | |
| "learning_rate": 1.7427385892116182e-06, | |
| "loss": 2.1656, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.12321095208462975, | |
| "grad_norm": 2.698709487915039, | |
| "learning_rate": 1.7634854771784235e-06, | |
| "loss": 2.2115, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.12445550715619166, | |
| "grad_norm": 2.476600408554077, | |
| "learning_rate": 1.7842323651452284e-06, | |
| "loss": 2.1619, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12445550715619166, | |
| "eval_loss": 2.221313953399658, | |
| "eval_runtime": 51.6214, | |
| "eval_samples_per_second": 19.372, | |
| "eval_steps_per_second": 0.814, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12570006222775357, | |
| "grad_norm": 3.238584518432617, | |
| "learning_rate": 1.8049792531120333e-06, | |
| "loss": 2.1543, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.1269446172993155, | |
| "grad_norm": 2.3609964847564697, | |
| "learning_rate": 1.8257261410788382e-06, | |
| "loss": 2.1602, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.1281891723708774, | |
| "grad_norm": 3.3314859867095947, | |
| "learning_rate": 1.8464730290456433e-06, | |
| "loss": 2.1843, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.12943372744243933, | |
| "grad_norm": 2.42441725730896, | |
| "learning_rate": 1.8672199170124482e-06, | |
| "loss": 2.135, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.13067828251400124, | |
| "grad_norm": 3.2766177654266357, | |
| "learning_rate": 1.8879668049792531e-06, | |
| "loss": 2.158, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.13192283758556317, | |
| "grad_norm": 2.8646531105041504, | |
| "learning_rate": 1.908713692946058e-06, | |
| "loss": 2.1214, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.13316739265712507, | |
| "grad_norm": 2.8570213317871094, | |
| "learning_rate": 1.929460580912863e-06, | |
| "loss": 2.1345, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.134411947728687, | |
| "grad_norm": 2.5014989376068115, | |
| "learning_rate": 1.9502074688796682e-06, | |
| "loss": 2.1147, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.1356565028002489, | |
| "grad_norm": 2.818286895751953, | |
| "learning_rate": 1.970954356846473e-06, | |
| "loss": 2.0914, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.13690105787181084, | |
| "grad_norm": 3.0579800605773926, | |
| "learning_rate": 1.991701244813278e-06, | |
| "loss": 2.0879, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13690105787181084, | |
| "eval_loss": 2.167081594467163, | |
| "eval_runtime": 42.3907, | |
| "eval_samples_per_second": 23.59, | |
| "eval_steps_per_second": 0.991, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13814561294337274, | |
| "grad_norm": 2.6039772033691406, | |
| "learning_rate": 2.012448132780083e-06, | |
| "loss": 2.1006, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.13939016801493467, | |
| "grad_norm": 3.1309447288513184, | |
| "learning_rate": 2.0331950207468883e-06, | |
| "loss": 2.0758, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.14063472308649658, | |
| "grad_norm": 2.6772613525390625, | |
| "learning_rate": 2.053941908713693e-06, | |
| "loss": 2.1542, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.14187927815805848, | |
| "grad_norm": 3.2689080238342285, | |
| "learning_rate": 2.074688796680498e-06, | |
| "loss": 2.0873, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.1431238332296204, | |
| "grad_norm": 2.7289857864379883, | |
| "learning_rate": 2.095435684647303e-06, | |
| "loss": 2.0697, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.14436838830118232, | |
| "grad_norm": 2.8635787963867188, | |
| "learning_rate": 2.116182572614108e-06, | |
| "loss": 2.0908, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.14561294337274425, | |
| "grad_norm": 2.805933713912964, | |
| "learning_rate": 2.136929460580913e-06, | |
| "loss": 2.0643, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.14685749844430615, | |
| "grad_norm": 2.562567710876465, | |
| "learning_rate": 2.157676348547718e-06, | |
| "loss": 2.0559, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.14810205351586808, | |
| "grad_norm": 3.000135898590088, | |
| "learning_rate": 2.178423236514523e-06, | |
| "loss": 2.0442, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.14934660858742999, | |
| "grad_norm": 2.6913654804229736, | |
| "learning_rate": 2.199170124481328e-06, | |
| "loss": 2.0551, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14934660858742999, | |
| "eval_loss": 2.130500316619873, | |
| "eval_runtime": 44.3089, | |
| "eval_samples_per_second": 22.569, | |
| "eval_steps_per_second": 0.948, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15059116365899192, | |
| "grad_norm": 3.38159441947937, | |
| "learning_rate": 2.219917012448133e-06, | |
| "loss": 2.0359, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.15183571873055382, | |
| "grad_norm": 2.4632813930511475, | |
| "learning_rate": 2.240663900414938e-06, | |
| "loss": 2.0805, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.15308027380211575, | |
| "grad_norm": 3.2085115909576416, | |
| "learning_rate": 2.2614107883817427e-06, | |
| "loss": 2.0617, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.15432482887367766, | |
| "grad_norm": 2.7810094356536865, | |
| "learning_rate": 2.282157676348548e-06, | |
| "loss": 2.0467, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.1555693839452396, | |
| "grad_norm": 2.6023035049438477, | |
| "learning_rate": 2.302904564315353e-06, | |
| "loss": 2.0578, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1568139390168015, | |
| "grad_norm": 3.073814630508423, | |
| "learning_rate": 2.323651452282158e-06, | |
| "loss": 2.0742, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.15805849408836342, | |
| "grad_norm": 2.622281312942505, | |
| "learning_rate": 2.3443983402489627e-06, | |
| "loss": 2.1668, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.15930304915992533, | |
| "grad_norm": 3.3766582012176514, | |
| "learning_rate": 2.365145228215768e-06, | |
| "loss": 2.0129, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.16054760423148726, | |
| "grad_norm": 3.1513423919677734, | |
| "learning_rate": 2.385892116182573e-06, | |
| "loss": 2.0215, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.16179215930304916, | |
| "grad_norm": 3.2852959632873535, | |
| "learning_rate": 2.4066390041493776e-06, | |
| "loss": 2.0557, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16179215930304916, | |
| "eval_loss": 2.096493721008301, | |
| "eval_runtime": 46.9447, | |
| "eval_samples_per_second": 21.302, | |
| "eval_steps_per_second": 0.895, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16303671437461106, | |
| "grad_norm": 2.526399612426758, | |
| "learning_rate": 2.4273858921161828e-06, | |
| "loss": 2.065, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.164281269446173, | |
| "grad_norm": 3.3448667526245117, | |
| "learning_rate": 2.448132780082988e-06, | |
| "loss": 2.0472, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.1655258245177349, | |
| "grad_norm": 2.6260809898376465, | |
| "learning_rate": 2.468879668049793e-06, | |
| "loss": 1.9804, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.16677037958929683, | |
| "grad_norm": 3.6141812801361084, | |
| "learning_rate": 2.4896265560165977e-06, | |
| "loss": 2.0197, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.16801493466085873, | |
| "grad_norm": 2.4911234378814697, | |
| "learning_rate": 2.5103734439834028e-06, | |
| "loss": 1.9642, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.16925948973242066, | |
| "grad_norm": 2.928642749786377, | |
| "learning_rate": 2.5311203319502074e-06, | |
| "loss": 1.9489, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.17050404480398257, | |
| "grad_norm": 3.090965509414673, | |
| "learning_rate": 2.5518672199170125e-06, | |
| "loss": 1.994, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.1717485998755445, | |
| "grad_norm": 3.2897465229034424, | |
| "learning_rate": 2.5726141078838172e-06, | |
| "loss": 1.9746, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.1729931549471064, | |
| "grad_norm": 2.857083320617676, | |
| "learning_rate": 2.5933609958506228e-06, | |
| "loss": 1.9774, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.17423771001866833, | |
| "grad_norm": 3.803220510482788, | |
| "learning_rate": 2.614107883817428e-06, | |
| "loss": 1.9731, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17423771001866833, | |
| "eval_loss": 2.064887046813965, | |
| "eval_runtime": 44.0231, | |
| "eval_samples_per_second": 22.715, | |
| "eval_steps_per_second": 0.954, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17548226509023024, | |
| "grad_norm": 2.9923534393310547, | |
| "learning_rate": 2.6348547717842326e-06, | |
| "loss": 1.9854, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.17672682016179217, | |
| "grad_norm": 3.3368566036224365, | |
| "learning_rate": 2.6556016597510377e-06, | |
| "loss": 2.0687, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.17797137523335407, | |
| "grad_norm": 3.3132379055023193, | |
| "learning_rate": 2.6763485477178423e-06, | |
| "loss": 1.9696, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.179215930304916, | |
| "grad_norm": 3.7914819717407227, | |
| "learning_rate": 2.6970954356846475e-06, | |
| "loss": 1.9926, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.1804604853764779, | |
| "grad_norm": 3.20161509513855, | |
| "learning_rate": 2.717842323651452e-06, | |
| "loss": 1.9193, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.18170504044803984, | |
| "grad_norm": 3.440420150756836, | |
| "learning_rate": 2.7385892116182577e-06, | |
| "loss": 1.991, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.18294959551960174, | |
| "grad_norm": 3.152684450149536, | |
| "learning_rate": 2.7593360995850628e-06, | |
| "loss": 1.9695, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.18419415059116365, | |
| "grad_norm": 3.0402464866638184, | |
| "learning_rate": 2.7800829875518675e-06, | |
| "loss": 1.9274, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.18543870566272558, | |
| "grad_norm": 2.778444290161133, | |
| "learning_rate": 2.8008298755186726e-06, | |
| "loss": 1.9198, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.18668326073428748, | |
| "grad_norm": 2.7946548461914062, | |
| "learning_rate": 2.8215767634854773e-06, | |
| "loss": 1.8958, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18668326073428748, | |
| "eval_loss": 2.043288230895996, | |
| "eval_runtime": 44.2268, | |
| "eval_samples_per_second": 22.611, | |
| "eval_steps_per_second": 0.95, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1879278158058494, | |
| "grad_norm": 3.269259452819824, | |
| "learning_rate": 2.8423236514522824e-06, | |
| "loss": 1.9832, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.18917237087741132, | |
| "grad_norm": 3.2673771381378174, | |
| "learning_rate": 2.863070539419087e-06, | |
| "loss": 1.9345, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.19041692594897325, | |
| "grad_norm": 3.016599655151367, | |
| "learning_rate": 2.883817427385892e-06, | |
| "loss": 1.8969, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.19166148102053515, | |
| "grad_norm": 3.2771544456481934, | |
| "learning_rate": 2.9045643153526977e-06, | |
| "loss": 1.921, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.19290603609209708, | |
| "grad_norm": 3.008080244064331, | |
| "learning_rate": 2.9253112033195024e-06, | |
| "loss": 1.9367, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.194150591163659, | |
| "grad_norm": 3.2312428951263428, | |
| "learning_rate": 2.9460580912863075e-06, | |
| "loss": 1.9021, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.19539514623522092, | |
| "grad_norm": 3.294121503829956, | |
| "learning_rate": 2.966804979253112e-06, | |
| "loss": 1.9216, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.19663970130678282, | |
| "grad_norm": 2.771685838699341, | |
| "learning_rate": 2.9875518672199173e-06, | |
| "loss": 1.9435, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.19788425637834475, | |
| "grad_norm": 2.971971273422241, | |
| "learning_rate": 3.008298755186722e-06, | |
| "loss": 1.8851, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.19912881144990666, | |
| "grad_norm": 3.3144047260284424, | |
| "learning_rate": 3.029045643153527e-06, | |
| "loss": 1.853, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.19912881144990666, | |
| "eval_loss": 2.023491859436035, | |
| "eval_runtime": 44.9425, | |
| "eval_samples_per_second": 22.251, | |
| "eval_steps_per_second": 0.935, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2003733665214686, | |
| "grad_norm": 3.3733646869659424, | |
| "learning_rate": 3.0497925311203326e-06, | |
| "loss": 1.8836, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.2016179215930305, | |
| "grad_norm": 3.1801207065582275, | |
| "learning_rate": 3.0705394190871373e-06, | |
| "loss": 1.9438, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.2028624766645924, | |
| "grad_norm": 3.1199593544006348, | |
| "learning_rate": 3.0912863070539424e-06, | |
| "loss": 1.9219, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.20410703173615433, | |
| "grad_norm": 3.344089984893799, | |
| "learning_rate": 3.112033195020747e-06, | |
| "loss": 1.9174, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.20535158680771623, | |
| "grad_norm": 3.269702911376953, | |
| "learning_rate": 3.132780082987552e-06, | |
| "loss": 1.894, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.20659614187927816, | |
| "grad_norm": 3.021744966506958, | |
| "learning_rate": 3.153526970954357e-06, | |
| "loss": 1.8799, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.20784069695084006, | |
| "grad_norm": 3.0104167461395264, | |
| "learning_rate": 3.174273858921162e-06, | |
| "loss": 1.9116, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.209085252022402, | |
| "grad_norm": 3.3018341064453125, | |
| "learning_rate": 3.1950207468879666e-06, | |
| "loss": 1.8389, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2103298070939639, | |
| "grad_norm": 3.0919857025146484, | |
| "learning_rate": 3.215767634854772e-06, | |
| "loss": 1.9522, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.21157436216552583, | |
| "grad_norm": 3.4702494144439697, | |
| "learning_rate": 3.2365145228215773e-06, | |
| "loss": 1.9204, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.21157436216552583, | |
| "eval_loss": 1.997478723526001, | |
| "eval_runtime": 43.2143, | |
| "eval_samples_per_second": 23.14, | |
| "eval_steps_per_second": 0.972, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.21281891723708773, | |
| "grad_norm": 3.133046865463257, | |
| "learning_rate": 3.257261410788382e-06, | |
| "loss": 1.891, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.21406347230864967, | |
| "grad_norm": 3.1828863620758057, | |
| "learning_rate": 3.278008298755187e-06, | |
| "loss": 1.8816, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.21530802738021157, | |
| "grad_norm": 3.374898910522461, | |
| "learning_rate": 3.2987551867219918e-06, | |
| "loss": 1.8886, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.2165525824517735, | |
| "grad_norm": 3.6660516262054443, | |
| "learning_rate": 3.319502074688797e-06, | |
| "loss": 1.9442, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.2177971375233354, | |
| "grad_norm": 3.080636978149414, | |
| "learning_rate": 3.3402489626556016e-06, | |
| "loss": 1.866, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.21904169259489734, | |
| "grad_norm": 3.3684473037719727, | |
| "learning_rate": 3.360995850622407e-06, | |
| "loss": 1.8699, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.22028624766645924, | |
| "grad_norm": 3.818382740020752, | |
| "learning_rate": 3.381742738589212e-06, | |
| "loss": 1.8541, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.22153080273802117, | |
| "grad_norm": 3.0995497703552246, | |
| "learning_rate": 3.402489626556017e-06, | |
| "loss": 1.8453, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.22277535780958307, | |
| "grad_norm": 3.5696587562561035, | |
| "learning_rate": 3.423236514522822e-06, | |
| "loss": 1.9289, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.22401991288114498, | |
| "grad_norm": 3.480571985244751, | |
| "learning_rate": 3.4439834024896267e-06, | |
| "loss": 1.8175, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.22401991288114498, | |
| "eval_loss": 1.9842805862426758, | |
| "eval_runtime": 43.7649, | |
| "eval_samples_per_second": 22.849, | |
| "eval_steps_per_second": 0.96, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2252644679527069, | |
| "grad_norm": 3.229316473007202, | |
| "learning_rate": 3.4647302904564318e-06, | |
| "loss": 1.9048, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.2265090230242688, | |
| "grad_norm": 3.1970808506011963, | |
| "learning_rate": 3.4854771784232365e-06, | |
| "loss": 1.907, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.22775357809583074, | |
| "grad_norm": 3.5275299549102783, | |
| "learning_rate": 3.5062240663900416e-06, | |
| "loss": 1.8147, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.22899813316739265, | |
| "grad_norm": 3.367077589035034, | |
| "learning_rate": 3.526970954356847e-06, | |
| "loss": 1.8189, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.23024268823895458, | |
| "grad_norm": 3.3052914142608643, | |
| "learning_rate": 3.5477178423236518e-06, | |
| "loss": 1.8362, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.23148724331051648, | |
| "grad_norm": 3.4737954139709473, | |
| "learning_rate": 3.568464730290457e-06, | |
| "loss": 1.8747, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.23273179838207841, | |
| "grad_norm": 2.851705312728882, | |
| "learning_rate": 3.5892116182572616e-06, | |
| "loss": 1.7835, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.23397635345364032, | |
| "grad_norm": 3.615224599838257, | |
| "learning_rate": 3.6099585062240667e-06, | |
| "loss": 1.7855, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.23522090852520225, | |
| "grad_norm": 2.7468442916870117, | |
| "learning_rate": 3.6307053941908714e-06, | |
| "loss": 1.843, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.23646546359676415, | |
| "grad_norm": 3.3228273391723633, | |
| "learning_rate": 3.6514522821576765e-06, | |
| "loss": 1.8453, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23646546359676415, | |
| "eval_loss": 1.9668089151382446, | |
| "eval_runtime": 44.9228, | |
| "eval_samples_per_second": 22.26, | |
| "eval_steps_per_second": 0.935, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23771001866832608, | |
| "grad_norm": 2.7882697582244873, | |
| "learning_rate": 3.672199170124482e-06, | |
| "loss": 1.8625, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.238954573739888, | |
| "grad_norm": 3.244044780731201, | |
| "learning_rate": 3.6929460580912867e-06, | |
| "loss": 1.8903, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.24019912881144992, | |
| "grad_norm": 2.8844549655914307, | |
| "learning_rate": 3.713692946058092e-06, | |
| "loss": 1.8929, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.24144368388301182, | |
| "grad_norm": 2.9207894802093506, | |
| "learning_rate": 3.7344398340248965e-06, | |
| "loss": 1.8458, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.24268823895457373, | |
| "grad_norm": 2.908562183380127, | |
| "learning_rate": 3.7551867219917016e-06, | |
| "loss": 1.828, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.24393279402613566, | |
| "grad_norm": 3.1195480823516846, | |
| "learning_rate": 3.7759336099585063e-06, | |
| "loss": 1.855, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.24517734909769756, | |
| "grad_norm": 3.3910183906555176, | |
| "learning_rate": 3.7966804979253114e-06, | |
| "loss": 1.7868, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.2464219041692595, | |
| "grad_norm": 2.921475887298584, | |
| "learning_rate": 3.817427385892116e-06, | |
| "loss": 1.7505, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.2476664592408214, | |
| "grad_norm": 3.5471713542938232, | |
| "learning_rate": 3.838174273858922e-06, | |
| "loss": 1.8445, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.24891101431238333, | |
| "grad_norm": 3.047698736190796, | |
| "learning_rate": 3.858921161825726e-06, | |
| "loss": 1.8037, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24891101431238333, | |
| "eval_loss": 1.9400665760040283, | |
| "eval_runtime": 49.1044, | |
| "eval_samples_per_second": 20.365, | |
| "eval_steps_per_second": 0.855, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.25015556938394523, | |
| "grad_norm": 3.4988913536071777, | |
| "learning_rate": 3.879668049792531e-06, | |
| "loss": 1.8061, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.25140012445550713, | |
| "grad_norm": 3.0373125076293945, | |
| "learning_rate": 3.9004149377593365e-06, | |
| "loss": 1.8081, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.2526446795270691, | |
| "grad_norm": 2.9764745235443115, | |
| "learning_rate": 3.921161825726142e-06, | |
| "loss": 1.8244, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.253889234598631, | |
| "grad_norm": 3.4413554668426514, | |
| "learning_rate": 3.941908713692946e-06, | |
| "loss": 1.8492, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.2551337896701929, | |
| "grad_norm": 2.9980437755584717, | |
| "learning_rate": 3.962655601659751e-06, | |
| "loss": 1.805, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.2563783447417548, | |
| "grad_norm": 3.228750228881836, | |
| "learning_rate": 3.983402489626556e-06, | |
| "loss": 1.7683, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.25762289981331676, | |
| "grad_norm": 3.008496046066284, | |
| "learning_rate": 4.004149377593361e-06, | |
| "loss": 1.8602, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.25886745488487867, | |
| "grad_norm": 3.338935375213623, | |
| "learning_rate": 4.024896265560166e-06, | |
| "loss": 1.7978, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.26011200995644057, | |
| "grad_norm": 3.1450204849243164, | |
| "learning_rate": 4.045643153526971e-06, | |
| "loss": 1.8243, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.2613565650280025, | |
| "grad_norm": 3.5714142322540283, | |
| "learning_rate": 4.0663900414937765e-06, | |
| "loss": 1.8386, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2613565650280025, | |
| "eval_loss": 1.9310717582702637, | |
| "eval_runtime": 42.4826, | |
| "eval_samples_per_second": 23.539, | |
| "eval_steps_per_second": 0.989, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.26260112009956443, | |
| "grad_norm": 3.3498189449310303, | |
| "learning_rate": 4.087136929460581e-06, | |
| "loss": 1.8055, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.26384567517112634, | |
| "grad_norm": 3.2423200607299805, | |
| "learning_rate": 4.107883817427386e-06, | |
| "loss": 1.8378, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.26509023024268824, | |
| "grad_norm": 3.0533974170684814, | |
| "learning_rate": 4.128630705394191e-06, | |
| "loss": 1.7699, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.26633478531425014, | |
| "grad_norm": 3.135615587234497, | |
| "learning_rate": 4.149377593360996e-06, | |
| "loss": 1.8019, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.26757934038581205, | |
| "grad_norm": 2.9863040447235107, | |
| "learning_rate": 4.170124481327801e-06, | |
| "loss": 1.7817, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.268823895457374, | |
| "grad_norm": 3.270598888397217, | |
| "learning_rate": 4.190871369294606e-06, | |
| "loss": 1.7542, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.2700684505289359, | |
| "grad_norm": 3.2279393672943115, | |
| "learning_rate": 4.211618257261411e-06, | |
| "loss": 1.7964, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.2713130056004978, | |
| "grad_norm": 3.0626120567321777, | |
| "learning_rate": 4.232365145228216e-06, | |
| "loss": 1.7687, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.2725575606720597, | |
| "grad_norm": 3.070702075958252, | |
| "learning_rate": 4.253112033195021e-06, | |
| "loss": 1.8075, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.2738021157436217, | |
| "grad_norm": 3.3623268604278564, | |
| "learning_rate": 4.273858921161826e-06, | |
| "loss": 1.8517, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2738021157436217, | |
| "eval_loss": 1.9212934970855713, | |
| "eval_runtime": 46.8503, | |
| "eval_samples_per_second": 21.345, | |
| "eval_steps_per_second": 0.896, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2750466708151836, | |
| "grad_norm": 3.005740165710449, | |
| "learning_rate": 4.294605809128631e-06, | |
| "loss": 1.816, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.2762912258867455, | |
| "grad_norm": 3.5257251262664795, | |
| "learning_rate": 4.315352697095436e-06, | |
| "loss": 1.8191, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.2775357809583074, | |
| "grad_norm": 3.361103057861328, | |
| "learning_rate": 4.336099585062241e-06, | |
| "loss": 1.8378, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.27878033602986935, | |
| "grad_norm": 3.787623405456543, | |
| "learning_rate": 4.356846473029046e-06, | |
| "loss": 1.7736, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.28002489110143125, | |
| "grad_norm": 3.45717453956604, | |
| "learning_rate": 4.3775933609958506e-06, | |
| "loss": 1.8195, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.28126944617299315, | |
| "grad_norm": 3.1698601245880127, | |
| "learning_rate": 4.398340248962656e-06, | |
| "loss": 1.7756, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.28251400124455506, | |
| "grad_norm": 3.345258951187134, | |
| "learning_rate": 4.419087136929461e-06, | |
| "loss": 1.7272, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.28375855631611696, | |
| "grad_norm": 2.905773639678955, | |
| "learning_rate": 4.439834024896266e-06, | |
| "loss": 1.84, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.2850031113876789, | |
| "grad_norm": 3.2004425525665283, | |
| "learning_rate": 4.460580912863071e-06, | |
| "loss": 1.8164, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.2862476664592408, | |
| "grad_norm": 2.965275287628174, | |
| "learning_rate": 4.481327800829876e-06, | |
| "loss": 1.7718, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2862476664592408, | |
| "eval_loss": 1.903228521347046, | |
| "eval_runtime": 51.1663, | |
| "eval_samples_per_second": 19.544, | |
| "eval_steps_per_second": 0.821, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2874922215308027, | |
| "grad_norm": 2.8130710124969482, | |
| "learning_rate": 4.502074688796681e-06, | |
| "loss": 1.7696, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.28873677660236463, | |
| "grad_norm": 2.9987664222717285, | |
| "learning_rate": 4.5228215767634855e-06, | |
| "loss": 1.775, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.2899813316739266, | |
| "grad_norm": 3.0936989784240723, | |
| "learning_rate": 4.543568464730291e-06, | |
| "loss": 1.7775, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.2912258867454885, | |
| "grad_norm": 3.0936989784240723, | |
| "learning_rate": 4.543568464730291e-06, | |
| "loss": 1.7154, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.2924704418170504, | |
| "grad_norm": 2.8632843494415283, | |
| "learning_rate": 4.564315352697096e-06, | |
| "loss": 1.7771, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2937149968886123, | |
| "grad_norm": 3.3314013481140137, | |
| "learning_rate": 4.585062240663901e-06, | |
| "loss": 1.7243, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.29495955196017426, | |
| "grad_norm": 2.8522872924804688, | |
| "learning_rate": 4.605809128630706e-06, | |
| "loss": 1.7543, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.29620410703173616, | |
| "grad_norm": 3.319157600402832, | |
| "learning_rate": 4.626556016597511e-06, | |
| "loss": 1.7652, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.29744866210329807, | |
| "grad_norm": 3.123116970062256, | |
| "learning_rate": 4.647302904564316e-06, | |
| "loss": 1.6933, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.29869321717485997, | |
| "grad_norm": 3.1735854148864746, | |
| "learning_rate": 4.66804979253112e-06, | |
| "loss": 1.7437, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.29869321717485997, | |
| "eval_loss": 1.891274333000183, | |
| "eval_runtime": 50.0054, | |
| "eval_samples_per_second": 19.998, | |
| "eval_steps_per_second": 0.84, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.29993777224642193, | |
| "grad_norm": 3.0996642112731934, | |
| "learning_rate": 4.6887966804979255e-06, | |
| "loss": 1.7594, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.30118232731798383, | |
| "grad_norm": 3.255063533782959, | |
| "learning_rate": 4.709543568464731e-06, | |
| "loss": 1.7645, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.30242688238954574, | |
| "grad_norm": 2.722285747528076, | |
| "learning_rate": 4.730290456431536e-06, | |
| "loss": 1.7549, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.30367143746110764, | |
| "grad_norm": 3.1903417110443115, | |
| "learning_rate": 4.751037344398341e-06, | |
| "loss": 1.7382, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.30491599253266954, | |
| "grad_norm": 2.8352959156036377, | |
| "learning_rate": 4.771784232365146e-06, | |
| "loss": 1.7497, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.3061605476042315, | |
| "grad_norm": 3.158536434173584, | |
| "learning_rate": 4.792531120331951e-06, | |
| "loss": 1.7467, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.3074051026757934, | |
| "grad_norm": 2.8456921577453613, | |
| "learning_rate": 4.813278008298755e-06, | |
| "loss": 1.7472, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.3086496577473553, | |
| "grad_norm": 3.1215128898620605, | |
| "learning_rate": 4.83402489626556e-06, | |
| "loss": 1.7577, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.3098942128189172, | |
| "grad_norm": 2.928015947341919, | |
| "learning_rate": 4.8547717842323655e-06, | |
| "loss": 1.6932, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.3111387678904792, | |
| "grad_norm": 3.001044511795044, | |
| "learning_rate": 4.875518672199171e-06, | |
| "loss": 1.7276, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3111387678904792, | |
| "eval_loss": 1.8855507373809814, | |
| "eval_runtime": 46.0143, | |
| "eval_samples_per_second": 21.732, | |
| "eval_steps_per_second": 0.913, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3123833229620411, | |
| "grad_norm": 2.988994598388672, | |
| "learning_rate": 4.896265560165976e-06, | |
| "loss": 1.739, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.313627878033603, | |
| "grad_norm": 3.0091233253479004, | |
| "learning_rate": 4.91701244813278e-06, | |
| "loss": 1.7118, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.3148724331051649, | |
| "grad_norm": 3.2735323905944824, | |
| "learning_rate": 4.937759336099586e-06, | |
| "loss": 1.7832, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.31611698817672684, | |
| "grad_norm": 3.055468797683716, | |
| "learning_rate": 4.95850622406639e-06, | |
| "loss": 1.7151, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.31736154324828875, | |
| "grad_norm": 3.0889883041381836, | |
| "learning_rate": 4.979253112033195e-06, | |
| "loss": 1.7411, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.31860609831985065, | |
| "grad_norm": 2.8418147563934326, | |
| "learning_rate": 5e-06, | |
| "loss": 1.7575, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.31985065339141255, | |
| "grad_norm": 3.09739351272583, | |
| "learning_rate": 4.99769372693727e-06, | |
| "loss": 1.7988, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.3210952084629745, | |
| "grad_norm": 3.245515823364258, | |
| "learning_rate": 4.995387453874539e-06, | |
| "loss": 1.7706, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.3223397635345364, | |
| "grad_norm": 3.250432014465332, | |
| "learning_rate": 4.993081180811809e-06, | |
| "loss": 1.7839, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.3235843186060983, | |
| "grad_norm": 3.1325368881225586, | |
| "learning_rate": 4.990774907749078e-06, | |
| "loss": 1.754, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3235843186060983, | |
| "eval_loss": 1.869175672531128, | |
| "eval_runtime": 49.0199, | |
| "eval_samples_per_second": 20.4, | |
| "eval_steps_per_second": 0.857, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3248288736776602, | |
| "grad_norm": 3.1627941131591797, | |
| "learning_rate": 4.988468634686347e-06, | |
| "loss": 1.7123, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.3260734287492221, | |
| "grad_norm": 2.848202705383301, | |
| "learning_rate": 4.986162361623617e-06, | |
| "loss": 1.7231, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.3273179838207841, | |
| "grad_norm": 2.9585494995117188, | |
| "learning_rate": 4.983856088560886e-06, | |
| "loss": 1.7301, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.328562538892346, | |
| "grad_norm": 3.160170316696167, | |
| "learning_rate": 4.981549815498156e-06, | |
| "loss": 1.7283, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.3298070939639079, | |
| "grad_norm": 2.6879520416259766, | |
| "learning_rate": 4.979243542435424e-06, | |
| "loss": 1.7494, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.3310516490354698, | |
| "grad_norm": 3.1313576698303223, | |
| "learning_rate": 4.976937269372694e-06, | |
| "loss": 1.7224, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.33229620410703176, | |
| "grad_norm": 3.0477867126464844, | |
| "learning_rate": 4.974630996309964e-06, | |
| "loss": 1.6951, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.33354075917859366, | |
| "grad_norm": 3.133974313735962, | |
| "learning_rate": 4.972324723247233e-06, | |
| "loss": 1.7362, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.33478531425015556, | |
| "grad_norm": 3.4925222396850586, | |
| "learning_rate": 4.970018450184502e-06, | |
| "loss": 1.7053, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.33602986932171747, | |
| "grad_norm": 2.848466634750366, | |
| "learning_rate": 4.9677121771217715e-06, | |
| "loss": 1.7336, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.33602986932171747, | |
| "eval_loss": 1.8723454475402832, | |
| "eval_runtime": 47.9758, | |
| "eval_samples_per_second": 20.844, | |
| "eval_steps_per_second": 0.875, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3372744243932794, | |
| "grad_norm": 3.405003309249878, | |
| "learning_rate": 4.965405904059041e-06, | |
| "loss": 1.7178, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.33851897946484133, | |
| "grad_norm": 2.982916831970215, | |
| "learning_rate": 4.96309963099631e-06, | |
| "loss": 1.7255, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.33976353453640323, | |
| "grad_norm": 3.1712088584899902, | |
| "learning_rate": 4.96079335793358e-06, | |
| "loss": 1.7328, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.34100808960796514, | |
| "grad_norm": 3.325481414794922, | |
| "learning_rate": 4.958487084870849e-06, | |
| "loss": 1.7268, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.3422526446795271, | |
| "grad_norm": 3.0751800537109375, | |
| "learning_rate": 4.956180811808119e-06, | |
| "loss": 1.7916, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.343497199751089, | |
| "grad_norm": 2.9451465606689453, | |
| "learning_rate": 4.953874538745388e-06, | |
| "loss": 1.7588, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.3447417548226509, | |
| "grad_norm": 3.1492040157318115, | |
| "learning_rate": 4.9515682656826574e-06, | |
| "loss": 1.7312, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.3459863098942128, | |
| "grad_norm": 3.165748119354248, | |
| "learning_rate": 4.949261992619927e-06, | |
| "loss": 1.7645, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.3472308649657747, | |
| "grad_norm": 3.059307336807251, | |
| "learning_rate": 4.946955719557196e-06, | |
| "loss": 1.6783, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.34847542003733667, | |
| "grad_norm": 2.940147638320923, | |
| "learning_rate": 4.944649446494466e-06, | |
| "loss": 1.7079, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.34847542003733667, | |
| "eval_loss": 1.8577951192855835, | |
| "eval_runtime": 50.1741, | |
| "eval_samples_per_second": 19.931, | |
| "eval_steps_per_second": 0.837, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3497199751088986, | |
| "grad_norm": 2.6892037391662598, | |
| "learning_rate": 4.942343173431734e-06, | |
| "loss": 1.7104, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.3509645301804605, | |
| "grad_norm": 3.136791467666626, | |
| "learning_rate": 4.940036900369004e-06, | |
| "loss": 1.763, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.3522090852520224, | |
| "grad_norm": 2.6873879432678223, | |
| "learning_rate": 4.937730627306274e-06, | |
| "loss": 1.722, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.35345364032358434, | |
| "grad_norm": 3.1375961303710938, | |
| "learning_rate": 4.9354243542435426e-06, | |
| "loss": 1.7048, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.35469819539514624, | |
| "grad_norm": 2.920725107192993, | |
| "learning_rate": 4.933118081180812e-06, | |
| "loss": 1.7014, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.35594275046670815, | |
| "grad_norm": 2.750018835067749, | |
| "learning_rate": 4.930811808118081e-06, | |
| "loss": 1.6283, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.35718730553827005, | |
| "grad_norm": 3.399036169052124, | |
| "learning_rate": 4.928505535055351e-06, | |
| "loss": 1.7265, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.358431860609832, | |
| "grad_norm": 3.1734066009521484, | |
| "learning_rate": 4.92619926199262e-06, | |
| "loss": 1.7007, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.3596764156813939, | |
| "grad_norm": 3.038865089416504, | |
| "learning_rate": 4.92389298892989e-06, | |
| "loss": 1.7357, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.3609209707529558, | |
| "grad_norm": 3.0309486389160156, | |
| "learning_rate": 4.921586715867159e-06, | |
| "loss": 1.7487, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3609209707529558, | |
| "eval_loss": 1.8484960794448853, | |
| "eval_runtime": 50.374, | |
| "eval_samples_per_second": 19.852, | |
| "eval_steps_per_second": 0.834, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3621655258245177, | |
| "grad_norm": 2.867432117462158, | |
| "learning_rate": 4.9192804428044285e-06, | |
| "loss": 1.6988, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.3634100808960797, | |
| "grad_norm": 3.31636905670166, | |
| "learning_rate": 4.916974169741698e-06, | |
| "loss": 1.7003, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.3646546359676416, | |
| "grad_norm": 3.1181511878967285, | |
| "learning_rate": 4.914667896678967e-06, | |
| "loss": 1.6762, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.3658991910392035, | |
| "grad_norm": 2.978194236755371, | |
| "learning_rate": 4.912361623616237e-06, | |
| "loss": 1.6435, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.3671437461107654, | |
| "grad_norm": 3.0623116493225098, | |
| "learning_rate": 4.910055350553506e-06, | |
| "loss": 1.7038, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3683883011823273, | |
| "grad_norm": 2.83353853225708, | |
| "learning_rate": 4.907749077490776e-06, | |
| "loss": 1.7237, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.36963285625388925, | |
| "grad_norm": 2.8587100505828857, | |
| "learning_rate": 4.905442804428044e-06, | |
| "loss": 1.6927, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.37087741132545116, | |
| "grad_norm": 2.7930493354797363, | |
| "learning_rate": 4.903136531365314e-06, | |
| "loss": 1.7381, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.37212196639701306, | |
| "grad_norm": 2.8992788791656494, | |
| "learning_rate": 4.900830258302584e-06, | |
| "loss": 1.6485, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.37336652146857496, | |
| "grad_norm": 2.8896944522857666, | |
| "learning_rate": 4.898523985239853e-06, | |
| "loss": 1.7143, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.37336652146857496, | |
| "eval_loss": 1.8331259489059448, | |
| "eval_runtime": 51.0214, | |
| "eval_samples_per_second": 19.6, | |
| "eval_steps_per_second": 0.823, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3746110765401369, | |
| "grad_norm": 2.885444164276123, | |
| "learning_rate": 4.896217712177122e-06, | |
| "loss": 1.6914, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.3758556316116988, | |
| "grad_norm": 3.2996826171875, | |
| "learning_rate": 4.893911439114391e-06, | |
| "loss": 1.7353, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.37710018668326073, | |
| "grad_norm": 2.7231531143188477, | |
| "learning_rate": 4.891605166051661e-06, | |
| "loss": 1.6837, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.37834474175482263, | |
| "grad_norm": 2.9413955211639404, | |
| "learning_rate": 4.88929889298893e-06, | |
| "loss": 1.6448, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.3795892968263846, | |
| "grad_norm": 2.6486589908599854, | |
| "learning_rate": 4.8869926199262e-06, | |
| "loss": 1.6826, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.3808338518979465, | |
| "grad_norm": 2.977836847305298, | |
| "learning_rate": 4.884686346863469e-06, | |
| "loss": 1.6737, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.3820784069695084, | |
| "grad_norm": 2.635324716567993, | |
| "learning_rate": 4.8823800738007384e-06, | |
| "loss": 1.7112, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.3833229620410703, | |
| "grad_norm": 3.0650839805603027, | |
| "learning_rate": 4.880073800738008e-06, | |
| "loss": 1.7123, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.3845675171126322, | |
| "grad_norm": 3.059629440307617, | |
| "learning_rate": 4.877767527675277e-06, | |
| "loss": 1.662, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.38581207218419417, | |
| "grad_norm": 2.7559597492218018, | |
| "learning_rate": 4.875461254612546e-06, | |
| "loss": 1.7418, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.38581207218419417, | |
| "eval_loss": 1.8277366161346436, | |
| "eval_runtime": 42.6671, | |
| "eval_samples_per_second": 23.437, | |
| "eval_steps_per_second": 0.984, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.38705662725575607, | |
| "grad_norm": 2.7987024784088135, | |
| "learning_rate": 4.873154981549816e-06, | |
| "loss": 1.7326, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.388301182327318, | |
| "grad_norm": 2.999824047088623, | |
| "learning_rate": 4.8708487084870856e-06, | |
| "loss": 1.7344, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.3895457373988799, | |
| "grad_norm": 2.942995071411133, | |
| "learning_rate": 4.868542435424355e-06, | |
| "loss": 1.7055, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.39079029247044184, | |
| "grad_norm": 2.823906183242798, | |
| "learning_rate": 4.8662361623616235e-06, | |
| "loss": 1.6819, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.39203484754200374, | |
| "grad_norm": 2.7798759937286377, | |
| "learning_rate": 4.863929889298894e-06, | |
| "loss": 1.6694, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.39327940261356564, | |
| "grad_norm": 2.599005699157715, | |
| "learning_rate": 4.861623616236163e-06, | |
| "loss": 1.6924, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.39452395768512755, | |
| "grad_norm": 2.687539577484131, | |
| "learning_rate": 4.859317343173432e-06, | |
| "loss": 1.685, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.3957685127566895, | |
| "grad_norm": 2.9679677486419678, | |
| "learning_rate": 4.857011070110701e-06, | |
| "loss": 1.718, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.3970130678282514, | |
| "grad_norm": 2.8611817359924316, | |
| "learning_rate": 4.854704797047971e-06, | |
| "loss": 1.7247, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.3982576228998133, | |
| "grad_norm": 2.7461249828338623, | |
| "learning_rate": 4.85239852398524e-06, | |
| "loss": 1.6434, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3982576228998133, | |
| "eval_loss": 1.8234667778015137, | |
| "eval_runtime": 44.3433, | |
| "eval_samples_per_second": 22.551, | |
| "eval_steps_per_second": 0.947, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3995021779713752, | |
| "grad_norm": 2.7142515182495117, | |
| "learning_rate": 4.8500922509225095e-06, | |
| "loss": 1.6855, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.4007467330429372, | |
| "grad_norm": 2.87727689743042, | |
| "learning_rate": 4.847785977859779e-06, | |
| "loss": 1.705, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.4019912881144991, | |
| "grad_norm": 2.9598982334136963, | |
| "learning_rate": 4.845479704797048e-06, | |
| "loss": 1.6482, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.403235843186061, | |
| "grad_norm": 2.8654463291168213, | |
| "learning_rate": 4.843173431734318e-06, | |
| "loss": 1.5816, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.4044803982576229, | |
| "grad_norm": 2.983837842941284, | |
| "learning_rate": 4.840867158671587e-06, | |
| "loss": 1.6962, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.4057249533291848, | |
| "grad_norm": 2.730914354324341, | |
| "learning_rate": 4.838560885608857e-06, | |
| "loss": 1.6991, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.40696950840074675, | |
| "grad_norm": 2.6901161670684814, | |
| "learning_rate": 4.836254612546126e-06, | |
| "loss": 1.6839, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.40821406347230865, | |
| "grad_norm": 2.6661486625671387, | |
| "learning_rate": 4.8339483394833955e-06, | |
| "loss": 1.6894, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.40945861854387056, | |
| "grad_norm": 2.64243221282959, | |
| "learning_rate": 4.831642066420665e-06, | |
| "loss": 1.6533, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.41070317361543246, | |
| "grad_norm": 2.586725950241089, | |
| "learning_rate": 4.8293357933579335e-06, | |
| "loss": 1.6486, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.41070317361543246, | |
| "eval_loss": 1.82283616065979, | |
| "eval_runtime": 46.5937, | |
| "eval_samples_per_second": 21.462, | |
| "eval_steps_per_second": 0.901, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4119477286869944, | |
| "grad_norm": 2.899968147277832, | |
| "learning_rate": 4.827029520295204e-06, | |
| "loss": 1.7136, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.4131922837585563, | |
| "grad_norm": 3.067671537399292, | |
| "learning_rate": 4.824723247232473e-06, | |
| "loss": 1.672, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.4144368388301182, | |
| "grad_norm": 2.8144404888153076, | |
| "learning_rate": 4.822416974169742e-06, | |
| "loss": 1.7173, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.41568139390168013, | |
| "grad_norm": 3.0551373958587646, | |
| "learning_rate": 4.820110701107011e-06, | |
| "loss": 1.6843, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.4169259489732421, | |
| "grad_norm": 2.7585153579711914, | |
| "learning_rate": 4.817804428044281e-06, | |
| "loss": 1.6834, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.418170504044804, | |
| "grad_norm": 2.8691210746765137, | |
| "learning_rate": 4.81549815498155e-06, | |
| "loss": 1.6814, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.4194150591163659, | |
| "grad_norm": 2.871523380279541, | |
| "learning_rate": 4.8131918819188194e-06, | |
| "loss": 1.6222, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.4206596141879278, | |
| "grad_norm": 2.8928768634796143, | |
| "learning_rate": 4.810885608856089e-06, | |
| "loss": 1.6984, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.42190416925948976, | |
| "grad_norm": 3.285256862640381, | |
| "learning_rate": 4.808579335793358e-06, | |
| "loss": 1.7029, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.42314872433105166, | |
| "grad_norm": 2.785504102706909, | |
| "learning_rate": 4.806273062730628e-06, | |
| "loss": 1.6857, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.42314872433105166, | |
| "eval_loss": 1.8053412437438965, | |
| "eval_runtime": 48.0656, | |
| "eval_samples_per_second": 20.805, | |
| "eval_steps_per_second": 0.874, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.42439327940261357, | |
| "grad_norm": 3.0227086544036865, | |
| "learning_rate": 4.803966789667897e-06, | |
| "loss": 1.6903, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.42563783447417547, | |
| "grad_norm": 2.616769790649414, | |
| "learning_rate": 4.8016605166051665e-06, | |
| "loss": 1.6144, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.4268823895457374, | |
| "grad_norm": 2.9519753456115723, | |
| "learning_rate": 4.799354243542436e-06, | |
| "loss": 1.6157, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.42812694461729933, | |
| "grad_norm": 2.764512062072754, | |
| "learning_rate": 4.797047970479705e-06, | |
| "loss": 1.6248, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.42937149968886124, | |
| "grad_norm": 2.999178886413574, | |
| "learning_rate": 4.794741697416975e-06, | |
| "loss": 1.6764, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.43061605476042314, | |
| "grad_norm": 3.0472185611724854, | |
| "learning_rate": 4.792435424354243e-06, | |
| "loss": 1.6421, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.43186060983198504, | |
| "grad_norm": 2.6638400554656982, | |
| "learning_rate": 4.790129151291514e-06, | |
| "loss": 1.6304, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.433105164903547, | |
| "grad_norm": 2.945295810699463, | |
| "learning_rate": 4.787822878228783e-06, | |
| "loss": 1.6181, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.4343497199751089, | |
| "grad_norm": 2.915125846862793, | |
| "learning_rate": 4.7855166051660525e-06, | |
| "loss": 1.6789, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.4355942750466708, | |
| "grad_norm": 2.5674026012420654, | |
| "learning_rate": 4.783210332103321e-06, | |
| "loss": 1.6723, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.4355942750466708, | |
| "eval_loss": 1.8109745979309082, | |
| "eval_runtime": 43.9943, | |
| "eval_samples_per_second": 22.73, | |
| "eval_steps_per_second": 0.955, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.4368388301182327, | |
| "grad_norm": 2.9533393383026123, | |
| "learning_rate": 4.7809040590405905e-06, | |
| "loss": 1.6271, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.43808338518979467, | |
| "grad_norm": 2.7677664756774902, | |
| "learning_rate": 4.778597785977861e-06, | |
| "loss": 1.6633, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.4393279402613566, | |
| "grad_norm": 2.527456521987915, | |
| "learning_rate": 4.776291512915129e-06, | |
| "loss": 1.5644, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.4405724953329185, | |
| "grad_norm": 2.9778528213500977, | |
| "learning_rate": 4.773985239852399e-06, | |
| "loss": 1.6166, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.4418170504044804, | |
| "grad_norm": 2.5554800033569336, | |
| "learning_rate": 4.771678966789668e-06, | |
| "loss": 1.5573, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.44306160547604234, | |
| "grad_norm": 2.7415409088134766, | |
| "learning_rate": 4.769372693726938e-06, | |
| "loss": 1.6564, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.44430616054760425, | |
| "grad_norm": 3.0275440216064453, | |
| "learning_rate": 4.767066420664207e-06, | |
| "loss": 1.67, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.44555071561916615, | |
| "grad_norm": 2.720694065093994, | |
| "learning_rate": 4.7647601476014765e-06, | |
| "loss": 1.6374, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.44679527069072805, | |
| "grad_norm": 2.97589111328125, | |
| "learning_rate": 4.762453874538746e-06, | |
| "loss": 1.6596, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.44803982576228996, | |
| "grad_norm": 2.8005781173706055, | |
| "learning_rate": 4.760147601476015e-06, | |
| "loss": 1.6281, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.44803982576228996, | |
| "eval_loss": 1.8139524459838867, | |
| "eval_runtime": 44.5817, | |
| "eval_samples_per_second": 22.431, | |
| "eval_steps_per_second": 0.942, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4492843808338519, | |
| "grad_norm": 3.3947463035583496, | |
| "learning_rate": 4.757841328413285e-06, | |
| "loss": 1.7149, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.4505289359054138, | |
| "grad_norm": 2.991457939147949, | |
| "learning_rate": 4.755535055350554e-06, | |
| "loss": 1.5971, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.4517734909769757, | |
| "grad_norm": 2.653313398361206, | |
| "learning_rate": 4.753228782287823e-06, | |
| "loss": 1.6465, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.4530180460485376, | |
| "grad_norm": 2.716360569000244, | |
| "learning_rate": 4.750922509225093e-06, | |
| "loss": 1.6775, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.4542626011200996, | |
| "grad_norm": 2.733598470687866, | |
| "learning_rate": 4.748616236162362e-06, | |
| "loss": 1.6087, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.4555071561916615, | |
| "grad_norm": 2.581547737121582, | |
| "learning_rate": 4.746309963099631e-06, | |
| "loss": 1.6339, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.4567517112632234, | |
| "grad_norm": 2.6841800212860107, | |
| "learning_rate": 4.7440036900369e-06, | |
| "loss": 1.6193, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.4579962663347853, | |
| "grad_norm": 2.658369302749634, | |
| "learning_rate": 4.741697416974171e-06, | |
| "loss": 1.6287, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.45924082140634725, | |
| "grad_norm": 2.7204179763793945, | |
| "learning_rate": 4.739391143911439e-06, | |
| "loss": 1.6755, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.46048537647790916, | |
| "grad_norm": 2.6627941131591797, | |
| "learning_rate": 4.737084870848709e-06, | |
| "loss": 1.6142, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.46048537647790916, | |
| "eval_loss": 1.8019787073135376, | |
| "eval_runtime": 42.7804, | |
| "eval_samples_per_second": 23.375, | |
| "eval_steps_per_second": 0.982, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.46172993154947106, | |
| "grad_norm": 2.650705337524414, | |
| "learning_rate": 4.734778597785978e-06, | |
| "loss": 1.641, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.46297448662103297, | |
| "grad_norm": 2.7031619548797607, | |
| "learning_rate": 4.7324723247232475e-06, | |
| "loss": 1.6596, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.4642190416925949, | |
| "grad_norm": 3.3050339221954346, | |
| "learning_rate": 4.730166051660517e-06, | |
| "loss": 1.6664, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.46546359676415683, | |
| "grad_norm": 2.841404676437378, | |
| "learning_rate": 4.727859778597786e-06, | |
| "loss": 1.6474, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.46670815183571873, | |
| "grad_norm": 3.0990259647369385, | |
| "learning_rate": 4.725553505535056e-06, | |
| "loss": 1.6008, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.46795270690728064, | |
| "grad_norm": 2.987772226333618, | |
| "learning_rate": 4.723247232472325e-06, | |
| "loss": 1.6374, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.46919726197884254, | |
| "grad_norm": 3.3345255851745605, | |
| "learning_rate": 4.720940959409595e-06, | |
| "loss": 1.6405, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.4704418170504045, | |
| "grad_norm": 3.0810067653656006, | |
| "learning_rate": 4.718634686346864e-06, | |
| "loss": 1.6229, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.4716863721219664, | |
| "grad_norm": 3.246685266494751, | |
| "learning_rate": 4.716328413284133e-06, | |
| "loss": 1.6262, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.4729309271935283, | |
| "grad_norm": 2.6052889823913574, | |
| "learning_rate": 4.714022140221403e-06, | |
| "loss": 1.6241, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4729309271935283, | |
| "eval_loss": 1.7957485914230347, | |
| "eval_runtime": 43.6626, | |
| "eval_samples_per_second": 22.903, | |
| "eval_steps_per_second": 0.962, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4741754822650902, | |
| "grad_norm": 3.747142791748047, | |
| "learning_rate": 4.711715867158672e-06, | |
| "loss": 1.6764, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.47542003733665217, | |
| "grad_norm": 2.8508121967315674, | |
| "learning_rate": 4.709409594095941e-06, | |
| "loss": 1.6597, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.47666459240821407, | |
| "grad_norm": 3.5615711212158203, | |
| "learning_rate": 4.70710332103321e-06, | |
| "loss": 1.6089, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.477909147479776, | |
| "grad_norm": 2.5886309146881104, | |
| "learning_rate": 4.704797047970481e-06, | |
| "loss": 1.5996, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.4791537025513379, | |
| "grad_norm": 3.3900864124298096, | |
| "learning_rate": 4.702490774907749e-06, | |
| "loss": 1.7137, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.48039825762289984, | |
| "grad_norm": 2.913641929626465, | |
| "learning_rate": 4.700184501845019e-06, | |
| "loss": 1.6512, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.48164281269446174, | |
| "grad_norm": 2.810722827911377, | |
| "learning_rate": 4.697878228782288e-06, | |
| "loss": 1.6939, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.48288736776602365, | |
| "grad_norm": 3.2701401710510254, | |
| "learning_rate": 4.6955719557195575e-06, | |
| "loss": 1.6455, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.48413192283758555, | |
| "grad_norm": 2.972931385040283, | |
| "learning_rate": 4.693265682656827e-06, | |
| "loss": 1.6272, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.48537647790914745, | |
| "grad_norm": 3.2157890796661377, | |
| "learning_rate": 4.690959409594096e-06, | |
| "loss": 1.6409, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.48537647790914745, | |
| "eval_loss": 1.7859243154525757, | |
| "eval_runtime": 45.2093, | |
| "eval_samples_per_second": 22.119, | |
| "eval_steps_per_second": 0.929, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4866210329807094, | |
| "grad_norm": 2.783360719680786, | |
| "learning_rate": 4.688653136531366e-06, | |
| "loss": 1.6303, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.4878655880522713, | |
| "grad_norm": 2.6783013343811035, | |
| "learning_rate": 4.686346863468635e-06, | |
| "loss": 1.7259, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.4891101431238332, | |
| "grad_norm": 2.899916172027588, | |
| "learning_rate": 4.6840405904059046e-06, | |
| "loss": 1.6434, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.4903546981953951, | |
| "grad_norm": 2.604377269744873, | |
| "learning_rate": 4.681734317343174e-06, | |
| "loss": 1.6838, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.4915992532669571, | |
| "grad_norm": 3.0830864906311035, | |
| "learning_rate": 4.6794280442804426e-06, | |
| "loss": 1.6053, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.492843808338519, | |
| "grad_norm": 3.1381475925445557, | |
| "learning_rate": 4.677121771217713e-06, | |
| "loss": 1.6132, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.4940883634100809, | |
| "grad_norm": 3.097426652908325, | |
| "learning_rate": 4.674815498154982e-06, | |
| "loss": 1.6237, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.4953329184816428, | |
| "grad_norm": 2.9942305088043213, | |
| "learning_rate": 4.672509225092252e-06, | |
| "loss": 1.6554, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.49657747355320475, | |
| "grad_norm": 2.834199905395508, | |
| "learning_rate": 4.67020295202952e-06, | |
| "loss": 1.6389, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.49782202862476665, | |
| "grad_norm": 3.183389902114868, | |
| "learning_rate": 4.66789667896679e-06, | |
| "loss": 1.6518, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.49782202862476665, | |
| "eval_loss": 1.781000018119812, | |
| "eval_runtime": 45.4127, | |
| "eval_samples_per_second": 22.02, | |
| "eval_steps_per_second": 0.925, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.49906658369632856, | |
| "grad_norm": 2.8186683654785156, | |
| "learning_rate": 4.66559040590406e-06, | |
| "loss": 1.669, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.5003111387678905, | |
| "grad_norm": 2.618595600128174, | |
| "learning_rate": 4.6632841328413285e-06, | |
| "loss": 1.6767, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.5015556938394524, | |
| "grad_norm": 3.080432653427124, | |
| "learning_rate": 4.660977859778598e-06, | |
| "loss": 1.7096, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.5028002489110143, | |
| "grad_norm": 2.6780874729156494, | |
| "learning_rate": 4.658671586715867e-06, | |
| "loss": 1.6576, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.5040448039825762, | |
| "grad_norm": 2.8194704055786133, | |
| "learning_rate": 4.656365313653137e-06, | |
| "loss": 1.6405, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.5052893590541382, | |
| "grad_norm": 3.2195825576782227, | |
| "learning_rate": 4.654059040590406e-06, | |
| "loss": 1.6631, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.5065339141257, | |
| "grad_norm": 2.7719528675079346, | |
| "learning_rate": 4.651752767527676e-06, | |
| "loss": 1.6036, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.507778469197262, | |
| "grad_norm": 3.186394453048706, | |
| "learning_rate": 4.649446494464945e-06, | |
| "loss": 1.6508, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.5090230242688238, | |
| "grad_norm": 2.674922227859497, | |
| "learning_rate": 4.6471402214022145e-06, | |
| "loss": 1.6033, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.5102675793403858, | |
| "grad_norm": 3.2772562503814697, | |
| "learning_rate": 4.644833948339484e-06, | |
| "loss": 1.5916, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5102675793403858, | |
| "eval_loss": 1.784346342086792, | |
| "eval_runtime": 42.2178, | |
| "eval_samples_per_second": 23.687, | |
| "eval_steps_per_second": 0.995, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5115121344119478, | |
| "grad_norm": 2.9295618534088135, | |
| "learning_rate": 4.642527675276753e-06, | |
| "loss": 1.6693, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.5127566894835096, | |
| "grad_norm": 2.8492650985717773, | |
| "learning_rate": 4.640221402214023e-06, | |
| "loss": 1.658, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.5140012445550716, | |
| "grad_norm": 2.921211004257202, | |
| "learning_rate": 4.637915129151292e-06, | |
| "loss": 1.6559, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.5152457996266335, | |
| "grad_norm": 2.583395004272461, | |
| "learning_rate": 4.635608856088562e-06, | |
| "loss": 1.6869, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.5164903546981954, | |
| "grad_norm": 2.79984712600708, | |
| "learning_rate": 4.63330258302583e-06, | |
| "loss": 1.6007, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.5177349097697573, | |
| "grad_norm": 2.872856616973877, | |
| "learning_rate": 4.6309963099631e-06, | |
| "loss": 1.6132, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.5189794648413192, | |
| "grad_norm": 2.7482125759124756, | |
| "learning_rate": 4.62869003690037e-06, | |
| "loss": 1.5805, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.5202240199128811, | |
| "grad_norm": 2.9227206707000732, | |
| "learning_rate": 4.6263837638376384e-06, | |
| "loss": 1.6362, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.5214685749844431, | |
| "grad_norm": 2.858302354812622, | |
| "learning_rate": 4.624077490774908e-06, | |
| "loss": 1.5934, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.522713130056005, | |
| "grad_norm": 3.2696762084960938, | |
| "learning_rate": 4.621771217712177e-06, | |
| "loss": 1.6215, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.522713130056005, | |
| "eval_loss": 1.7770200967788696, | |
| "eval_runtime": 46.0922, | |
| "eval_samples_per_second": 21.696, | |
| "eval_steps_per_second": 0.911, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5239576851275669, | |
| "grad_norm": 2.525740623474121, | |
| "learning_rate": 4.619464944649447e-06, | |
| "loss": 1.6193, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.5252022401991289, | |
| "grad_norm": 2.9050614833831787, | |
| "learning_rate": 4.617158671586716e-06, | |
| "loss": 1.69, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.5264467952706907, | |
| "grad_norm": 2.959547519683838, | |
| "learning_rate": 4.6148523985239856e-06, | |
| "loss": 1.6874, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.5276913503422527, | |
| "grad_norm": 2.6331565380096436, | |
| "learning_rate": 4.612546125461255e-06, | |
| "loss": 1.5795, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.5289359054138145, | |
| "grad_norm": 2.7323524951934814, | |
| "learning_rate": 4.610239852398524e-06, | |
| "loss": 1.5882, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.5301804604853765, | |
| "grad_norm": 2.8021790981292725, | |
| "learning_rate": 4.607933579335794e-06, | |
| "loss": 1.5852, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.5314250155569384, | |
| "grad_norm": 2.984299659729004, | |
| "learning_rate": 4.605627306273063e-06, | |
| "loss": 1.6168, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.5326695706285003, | |
| "grad_norm": 2.92749285697937, | |
| "learning_rate": 4.603321033210333e-06, | |
| "loss": 1.5768, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.5339141257000622, | |
| "grad_norm": 2.7681751251220703, | |
| "learning_rate": 4.601014760147602e-06, | |
| "loss": 1.5831, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.5351586807716241, | |
| "grad_norm": 2.965458631515503, | |
| "learning_rate": 4.5987084870848715e-06, | |
| "loss": 1.6412, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5351586807716241, | |
| "eval_loss": 1.766748070716858, | |
| "eval_runtime": 51.1098, | |
| "eval_samples_per_second": 19.566, | |
| "eval_steps_per_second": 0.822, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.536403235843186, | |
| "grad_norm": 2.681853771209717, | |
| "learning_rate": 4.59640221402214e-06, | |
| "loss": 1.6302, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.537647790914748, | |
| "grad_norm": 2.698493480682373, | |
| "learning_rate": 4.5940959409594095e-06, | |
| "loss": 1.6774, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.5388923459863099, | |
| "grad_norm": 3.1715168952941895, | |
| "learning_rate": 4.59178966789668e-06, | |
| "loss": 1.5617, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.5401369010578718, | |
| "grad_norm": 2.98128080368042, | |
| "learning_rate": 4.589483394833948e-06, | |
| "loss": 1.5901, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.5413814561294338, | |
| "grad_norm": 3.3887572288513184, | |
| "learning_rate": 4.587177121771218e-06, | |
| "loss": 1.6448, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.5426260112009956, | |
| "grad_norm": 2.647975206375122, | |
| "learning_rate": 4.584870848708487e-06, | |
| "loss": 1.6209, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.5438705662725576, | |
| "grad_norm": 2.833264112472534, | |
| "learning_rate": 4.5825645756457575e-06, | |
| "loss": 1.6875, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.5451151213441194, | |
| "grad_norm": 3.0966858863830566, | |
| "learning_rate": 4.580258302583026e-06, | |
| "loss": 1.6291, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.5463596764156814, | |
| "grad_norm": 2.768793821334839, | |
| "learning_rate": 4.5779520295202955e-06, | |
| "loss": 1.6183, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.5476042314872434, | |
| "grad_norm": 3.4009342193603516, | |
| "learning_rate": 4.575645756457565e-06, | |
| "loss": 1.6602, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5476042314872434, | |
| "eval_loss": 1.76938796043396, | |
| "eval_runtime": 46.2093, | |
| "eval_samples_per_second": 21.641, | |
| "eval_steps_per_second": 0.909, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5488487865588052, | |
| "grad_norm": 2.769113063812256, | |
| "learning_rate": 4.573339483394834e-06, | |
| "loss": 1.6453, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.5500933416303672, | |
| "grad_norm": 3.3592801094055176, | |
| "learning_rate": 4.571033210332104e-06, | |
| "loss": 1.6602, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.551337896701929, | |
| "grad_norm": 2.6817564964294434, | |
| "learning_rate": 4.568726937269373e-06, | |
| "loss": 1.5714, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.552582451773491, | |
| "grad_norm": 3.093724250793457, | |
| "learning_rate": 4.566420664206643e-06, | |
| "loss": 1.6924, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.5538270068450529, | |
| "grad_norm": 2.766580104827881, | |
| "learning_rate": 4.564114391143912e-06, | |
| "loss": 1.5714, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.5550715619166148, | |
| "grad_norm": 2.868870973587036, | |
| "learning_rate": 4.5618081180811814e-06, | |
| "loss": 1.5823, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.5563161169881767, | |
| "grad_norm": 2.8286170959472656, | |
| "learning_rate": 4.559501845018451e-06, | |
| "loss": 1.6123, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.5575606720597387, | |
| "grad_norm": 2.66096568107605, | |
| "learning_rate": 4.5571955719557194e-06, | |
| "loss": 1.6044, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.5588052271313005, | |
| "grad_norm": 2.7411820888519287, | |
| "learning_rate": 4.55488929889299e-06, | |
| "loss": 1.6361, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.5600497822028625, | |
| "grad_norm": 2.7591240406036377, | |
| "learning_rate": 4.552583025830259e-06, | |
| "loss": 1.6257, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5600497822028625, | |
| "eval_loss": 1.758321762084961, | |
| "eval_runtime": 52.9135, | |
| "eval_samples_per_second": 18.899, | |
| "eval_steps_per_second": 0.794, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5612943372744243, | |
| "grad_norm": 2.733456611633301, | |
| "learning_rate": 4.550276752767528e-06, | |
| "loss": 1.7159, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.5625388923459863, | |
| "grad_norm": 2.7318639755249023, | |
| "learning_rate": 4.547970479704797e-06, | |
| "loss": 1.6062, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.5637834474175483, | |
| "grad_norm": 2.8235232830047607, | |
| "learning_rate": 4.5456642066420666e-06, | |
| "loss": 1.6616, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.5650280024891101, | |
| "grad_norm": 2.499028444290161, | |
| "learning_rate": 4.543357933579336e-06, | |
| "loss": 1.5795, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.5662725575606721, | |
| "grad_norm": 2.7547316551208496, | |
| "learning_rate": 4.541051660516605e-06, | |
| "loss": 1.6204, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.5675171126322339, | |
| "grad_norm": 2.7086215019226074, | |
| "learning_rate": 4.538745387453875e-06, | |
| "loss": 1.5611, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.5687616677037959, | |
| "grad_norm": 2.911731719970703, | |
| "learning_rate": 4.536439114391144e-06, | |
| "loss": 1.645, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.5700062227753578, | |
| "grad_norm": 2.5553250312805176, | |
| "learning_rate": 4.534132841328414e-06, | |
| "loss": 1.6093, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.5712507778469197, | |
| "grad_norm": 2.795919895172119, | |
| "learning_rate": 4.531826568265683e-06, | |
| "loss": 1.6, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.5724953329184816, | |
| "grad_norm": 2.92104434967041, | |
| "learning_rate": 4.5295202952029525e-06, | |
| "loss": 1.6444, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5724953329184816, | |
| "eval_loss": 1.760049819946289, | |
| "eval_runtime": 48.811, | |
| "eval_samples_per_second": 20.487, | |
| "eval_steps_per_second": 0.86, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5737398879900436, | |
| "grad_norm": 2.6339287757873535, | |
| "learning_rate": 4.527214022140222e-06, | |
| "loss": 1.6133, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.5749844430616055, | |
| "grad_norm": 2.531398057937622, | |
| "learning_rate": 4.524907749077491e-06, | |
| "loss": 1.5931, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.5762289981331674, | |
| "grad_norm": 2.8858656883239746, | |
| "learning_rate": 4.522601476014761e-06, | |
| "loss": 1.6287, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.5774735532047293, | |
| "grad_norm": 2.7309634685516357, | |
| "learning_rate": 4.520295202952029e-06, | |
| "loss": 1.6102, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.5787181082762912, | |
| "grad_norm": 2.7758548259735107, | |
| "learning_rate": 4.5179889298893e-06, | |
| "loss": 1.6292, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5799626633478532, | |
| "grad_norm": 2.6181721687316895, | |
| "learning_rate": 4.515682656826569e-06, | |
| "loss": 1.6113, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.581207218419415, | |
| "grad_norm": 2.6215691566467285, | |
| "learning_rate": 4.513376383763838e-06, | |
| "loss": 1.5158, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.582451773490977, | |
| "grad_norm": 2.727487087249756, | |
| "learning_rate": 4.511070110701107e-06, | |
| "loss": 1.6212, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.583696328562539, | |
| "grad_norm": 2.6248037815093994, | |
| "learning_rate": 4.5087638376383765e-06, | |
| "loss": 1.6117, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.5849408836341008, | |
| "grad_norm": 2.714291572570801, | |
| "learning_rate": 4.506457564575646e-06, | |
| "loss": 1.612, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5849408836341008, | |
| "eval_loss": 1.7569347620010376, | |
| "eval_runtime": 51.8475, | |
| "eval_samples_per_second": 19.287, | |
| "eval_steps_per_second": 0.81, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5861854387056628, | |
| "grad_norm": 2.752577066421509, | |
| "learning_rate": 4.504151291512915e-06, | |
| "loss": 1.5969, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.5874299937772246, | |
| "grad_norm": 2.688563346862793, | |
| "learning_rate": 4.501845018450185e-06, | |
| "loss": 1.6085, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.5886745488487866, | |
| "grad_norm": 2.8581559658050537, | |
| "learning_rate": 4.499538745387454e-06, | |
| "loss": 1.6688, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.5899191039203485, | |
| "grad_norm": 2.8520970344543457, | |
| "learning_rate": 4.497232472324724e-06, | |
| "loss": 1.6034, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.5911636589919104, | |
| "grad_norm": 2.8052237033843994, | |
| "learning_rate": 4.494926199261993e-06, | |
| "loss": 1.5656, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5924082140634723, | |
| "grad_norm": 2.619663953781128, | |
| "learning_rate": 4.4926199261992624e-06, | |
| "loss": 1.5543, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.5936527691350342, | |
| "grad_norm": 2.604964017868042, | |
| "learning_rate": 4.490313653136532e-06, | |
| "loss": 1.5671, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.5948973242065961, | |
| "grad_norm": 2.985004186630249, | |
| "learning_rate": 4.488007380073801e-06, | |
| "loss": 1.5681, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.5961418792781581, | |
| "grad_norm": 2.8348851203918457, | |
| "learning_rate": 4.485701107011071e-06, | |
| "loss": 1.6214, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.5973864343497199, | |
| "grad_norm": 2.580967664718628, | |
| "learning_rate": 4.483394833948339e-06, | |
| "loss": 1.5753, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5973864343497199, | |
| "eval_loss": 1.7542102336883545, | |
| "eval_runtime": 49.5092, | |
| "eval_samples_per_second": 20.198, | |
| "eval_steps_per_second": 0.848, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5986309894212819, | |
| "grad_norm": 3.0104517936706543, | |
| "learning_rate": 4.4810885608856096e-06, | |
| "loss": 1.6282, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.5998755444928439, | |
| "grad_norm": 2.9261820316314697, | |
| "learning_rate": 4.478782287822879e-06, | |
| "loss": 1.5811, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.6011200995644057, | |
| "grad_norm": 2.9920477867126465, | |
| "learning_rate": 4.4764760147601476e-06, | |
| "loss": 1.5905, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.6023646546359677, | |
| "grad_norm": 3.046887159347534, | |
| "learning_rate": 4.474169741697417e-06, | |
| "loss": 1.6587, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.6036092097075295, | |
| "grad_norm": 2.9660050868988037, | |
| "learning_rate": 4.471863468634686e-06, | |
| "loss": 1.5888, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.6048537647790915, | |
| "grad_norm": 2.770362377166748, | |
| "learning_rate": 4.469557195571957e-06, | |
| "loss": 1.5925, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.6060983198506534, | |
| "grad_norm": 2.621699094772339, | |
| "learning_rate": 4.467250922509225e-06, | |
| "loss": 1.5671, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.6073428749222153, | |
| "grad_norm": 2.749340295791626, | |
| "learning_rate": 4.464944649446495e-06, | |
| "loss": 1.5672, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.6085874299937772, | |
| "grad_norm": 3.091601848602295, | |
| "learning_rate": 4.462638376383764e-06, | |
| "loss": 1.5965, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.6098319850653391, | |
| "grad_norm": 2.6989245414733887, | |
| "learning_rate": 4.4603321033210335e-06, | |
| "loss": 1.5845, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6098319850653391, | |
| "eval_loss": 1.7461379766464233, | |
| "eval_runtime": 52.879, | |
| "eval_samples_per_second": 18.911, | |
| "eval_steps_per_second": 0.794, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.611076540136901, | |
| "grad_norm": 2.8998405933380127, | |
| "learning_rate": 4.458025830258303e-06, | |
| "loss": 1.5764, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.612321095208463, | |
| "grad_norm": 2.6035947799682617, | |
| "learning_rate": 4.455719557195572e-06, | |
| "loss": 1.5988, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.6135656502800249, | |
| "grad_norm": 2.712857484817505, | |
| "learning_rate": 4.453413284132842e-06, | |
| "loss": 1.6276, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.6148102053515868, | |
| "grad_norm": 2.73052978515625, | |
| "learning_rate": 4.451107011070111e-06, | |
| "loss": 1.5907, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.6160547604231488, | |
| "grad_norm": 2.8072566986083984, | |
| "learning_rate": 4.448800738007381e-06, | |
| "loss": 1.5771, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.6172993154947106, | |
| "grad_norm": 2.6016132831573486, | |
| "learning_rate": 4.446494464944649e-06, | |
| "loss": 1.5983, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.6185438705662726, | |
| "grad_norm": 2.9697721004486084, | |
| "learning_rate": 4.4441881918819195e-06, | |
| "loss": 1.5974, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.6197884256378344, | |
| "grad_norm": 2.6966018676757812, | |
| "learning_rate": 4.441881918819189e-06, | |
| "loss": 1.6042, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.6210329807093964, | |
| "grad_norm": 2.871964931488037, | |
| "learning_rate": 4.439575645756458e-06, | |
| "loss": 1.5668, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.6222775357809583, | |
| "grad_norm": 2.791602611541748, | |
| "learning_rate": 4.437269372693727e-06, | |
| "loss": 1.5222, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6222775357809583, | |
| "eval_loss": 1.756259799003601, | |
| "eval_runtime": 53.0959, | |
| "eval_samples_per_second": 18.834, | |
| "eval_steps_per_second": 0.791, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6235220908525202, | |
| "grad_norm": 2.6534979343414307, | |
| "learning_rate": 4.434963099630996e-06, | |
| "loss": 1.5618, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.6247666459240822, | |
| "grad_norm": 3.0166008472442627, | |
| "learning_rate": 4.432656826568267e-06, | |
| "loss": 1.639, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.6260112009956441, | |
| "grad_norm": 2.7879786491394043, | |
| "learning_rate": 4.430350553505535e-06, | |
| "loss": 1.5521, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.627255756067206, | |
| "grad_norm": 2.695650339126587, | |
| "learning_rate": 4.428044280442805e-06, | |
| "loss": 1.6086, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.6285003111387679, | |
| "grad_norm": 2.8340883255004883, | |
| "learning_rate": 4.425738007380074e-06, | |
| "loss": 1.583, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.6297448662103298, | |
| "grad_norm": 2.872870683670044, | |
| "learning_rate": 4.4234317343173434e-06, | |
| "loss": 1.5633, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.6309894212818917, | |
| "grad_norm": 2.840087652206421, | |
| "learning_rate": 4.421125461254613e-06, | |
| "loss": 1.603, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.6322339763534537, | |
| "grad_norm": 2.86578631401062, | |
| "learning_rate": 4.418819188191882e-06, | |
| "loss": 1.6031, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.6334785314250155, | |
| "grad_norm": 2.419501543045044, | |
| "learning_rate": 4.416512915129152e-06, | |
| "loss": 1.5975, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.6347230864965775, | |
| "grad_norm": 2.6204769611358643, | |
| "learning_rate": 4.414206642066421e-06, | |
| "loss": 1.608, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6347230864965775, | |
| "eval_loss": 1.7449734210968018, | |
| "eval_runtime": 44.3185, | |
| "eval_samples_per_second": 22.564, | |
| "eval_steps_per_second": 0.948, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6359676415681393, | |
| "grad_norm": 2.837980270385742, | |
| "learning_rate": 4.4119003690036905e-06, | |
| "loss": 1.625, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.6372121966397013, | |
| "grad_norm": 2.589782238006592, | |
| "learning_rate": 4.40959409594096e-06, | |
| "loss": 1.5976, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.6384567517112633, | |
| "grad_norm": 2.596064567565918, | |
| "learning_rate": 4.407287822878229e-06, | |
| "loss": 1.5568, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.6397013067828251, | |
| "grad_norm": 3.031325578689575, | |
| "learning_rate": 4.404981549815499e-06, | |
| "loss": 1.5744, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.6409458618543871, | |
| "grad_norm": 2.581284761428833, | |
| "learning_rate": 4.402675276752768e-06, | |
| "loss": 1.5822, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.642190416925949, | |
| "grad_norm": 2.7712416648864746, | |
| "learning_rate": 4.400369003690037e-06, | |
| "loss": 1.606, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.6434349719975109, | |
| "grad_norm": 2.5830018520355225, | |
| "learning_rate": 4.398062730627306e-06, | |
| "loss": 1.5845, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.6446795270690728, | |
| "grad_norm": 2.6646499633789062, | |
| "learning_rate": 4.3957564575645765e-06, | |
| "loss": 1.6323, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.6459240821406347, | |
| "grad_norm": 2.614750862121582, | |
| "learning_rate": 4.393450184501845e-06, | |
| "loss": 1.5447, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.6471686372121966, | |
| "grad_norm": 2.6826741695404053, | |
| "learning_rate": 4.3911439114391145e-06, | |
| "loss": 1.6081, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6471686372121966, | |
| "eval_loss": 1.7463606595993042, | |
| "eval_runtime": 45.7383, | |
| "eval_samples_per_second": 21.864, | |
| "eval_steps_per_second": 0.918, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6484131922837586, | |
| "grad_norm": 2.9165496826171875, | |
| "learning_rate": 4.388837638376384e-06, | |
| "loss": 1.5853, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.6496577473553204, | |
| "grad_norm": 2.789862871170044, | |
| "learning_rate": 4.386531365313653e-06, | |
| "loss": 1.6115, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.6509023024268824, | |
| "grad_norm": 2.690093994140625, | |
| "learning_rate": 4.384225092250923e-06, | |
| "loss": 1.5625, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.6521468574984443, | |
| "grad_norm": 2.660036087036133, | |
| "learning_rate": 4.381918819188192e-06, | |
| "loss": 1.6065, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.6533914125700062, | |
| "grad_norm": 2.5939362049102783, | |
| "learning_rate": 4.379612546125462e-06, | |
| "loss": 1.5593, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.6546359676415682, | |
| "grad_norm": 2.6998841762542725, | |
| "learning_rate": 4.377306273062731e-06, | |
| "loss": 1.6168, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.65588052271313, | |
| "grad_norm": 2.5756912231445312, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 1.528, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.657125077784692, | |
| "grad_norm": 2.6959640979766846, | |
| "learning_rate": 4.37269372693727e-06, | |
| "loss": 1.5987, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.6583696328562539, | |
| "grad_norm": 2.773494005203247, | |
| "learning_rate": 4.370387453874539e-06, | |
| "loss": 1.6018, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.6596141879278158, | |
| "grad_norm": 2.8194501399993896, | |
| "learning_rate": 4.368081180811809e-06, | |
| "loss": 1.6082, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6596141879278158, | |
| "eval_loss": 1.7327930927276611, | |
| "eval_runtime": 46.7893, | |
| "eval_samples_per_second": 21.372, | |
| "eval_steps_per_second": 0.898, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6608587429993777, | |
| "grad_norm": 2.721564292907715, | |
| "learning_rate": 4.365774907749078e-06, | |
| "loss": 1.5549, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.6621032980709396, | |
| "grad_norm": 2.6635236740112305, | |
| "learning_rate": 4.363468634686347e-06, | |
| "loss": 1.6016, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.6633478531425016, | |
| "grad_norm": 2.6541085243225098, | |
| "learning_rate": 4.361162361623616e-06, | |
| "loss": 1.5574, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.6645924082140635, | |
| "grad_norm": 2.9270925521850586, | |
| "learning_rate": 4.3588560885608864e-06, | |
| "loss": 1.5722, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.6658369632856254, | |
| "grad_norm": 2.6041259765625, | |
| "learning_rate": 4.356549815498156e-06, | |
| "loss": 1.6181, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.6670815183571873, | |
| "grad_norm": 2.7029967308044434, | |
| "learning_rate": 4.354243542435424e-06, | |
| "loss": 1.5576, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.6683260734287492, | |
| "grad_norm": 2.805567979812622, | |
| "learning_rate": 4.351937269372694e-06, | |
| "loss": 1.6279, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.6695706285003111, | |
| "grad_norm": 2.6513259410858154, | |
| "learning_rate": 4.349630996309963e-06, | |
| "loss": 1.5626, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.6708151835718731, | |
| "grad_norm": 2.7320876121520996, | |
| "learning_rate": 4.347324723247233e-06, | |
| "loss": 1.6, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.6720597386434349, | |
| "grad_norm": 2.9504754543304443, | |
| "learning_rate": 4.345018450184502e-06, | |
| "loss": 1.6755, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6720597386434349, | |
| "eval_loss": 1.733923077583313, | |
| "eval_runtime": 45.4809, | |
| "eval_samples_per_second": 21.987, | |
| "eval_steps_per_second": 0.923, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6733042937149969, | |
| "grad_norm": 2.7561354637145996, | |
| "learning_rate": 4.3427121771217715e-06, | |
| "loss": 1.5624, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.6745488487865589, | |
| "grad_norm": 2.612337827682495, | |
| "learning_rate": 4.340405904059041e-06, | |
| "loss": 1.5806, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.6757934038581207, | |
| "grad_norm": 3.2763278484344482, | |
| "learning_rate": 4.33809963099631e-06, | |
| "loss": 1.5939, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.6770379589296827, | |
| "grad_norm": 2.632627248764038, | |
| "learning_rate": 4.33579335793358e-06, | |
| "loss": 1.564, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.6782825140012445, | |
| "grad_norm": 2.9776413440704346, | |
| "learning_rate": 4.333487084870848e-06, | |
| "loss": 1.5624, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.6795270690728065, | |
| "grad_norm": 3.083935260772705, | |
| "learning_rate": 4.331180811808119e-06, | |
| "loss": 1.5957, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.6807716241443684, | |
| "grad_norm": 2.8425586223602295, | |
| "learning_rate": 4.328874538745388e-06, | |
| "loss": 1.5559, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.6820161792159303, | |
| "grad_norm": 3.0011188983917236, | |
| "learning_rate": 4.3265682656826575e-06, | |
| "loss": 1.5308, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.6832607342874922, | |
| "grad_norm": 2.7645163536071777, | |
| "learning_rate": 4.324261992619926e-06, | |
| "loss": 1.6114, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.6845052893590542, | |
| "grad_norm": 2.8784844875335693, | |
| "learning_rate": 4.321955719557196e-06, | |
| "loss": 1.5591, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6845052893590542, | |
| "eval_loss": 1.7328442335128784, | |
| "eval_runtime": 45.5776, | |
| "eval_samples_per_second": 21.941, | |
| "eval_steps_per_second": 0.922, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.685749844430616, | |
| "grad_norm": 3.1323604583740234, | |
| "learning_rate": 4.319649446494466e-06, | |
| "loss": 1.5626, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.686994399502178, | |
| "grad_norm": 2.7367660999298096, | |
| "learning_rate": 4.317343173431734e-06, | |
| "loss": 1.5914, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.6882389545737398, | |
| "grad_norm": 3.056155204772949, | |
| "learning_rate": 4.315036900369004e-06, | |
| "loss": 1.6014, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.6894835096453018, | |
| "grad_norm": 2.7824926376342773, | |
| "learning_rate": 4.312730627306273e-06, | |
| "loss": 1.5508, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.6907280647168638, | |
| "grad_norm": 2.629610538482666, | |
| "learning_rate": 4.310424354243543e-06, | |
| "loss": 1.5385, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.6919726197884256, | |
| "grad_norm": 2.753021240234375, | |
| "learning_rate": 4.308118081180812e-06, | |
| "loss": 1.6211, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.6932171748599876, | |
| "grad_norm": 2.8113718032836914, | |
| "learning_rate": 4.3058118081180815e-06, | |
| "loss": 1.5904, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.6944617299315494, | |
| "grad_norm": 2.849471092224121, | |
| "learning_rate": 4.303505535055351e-06, | |
| "loss": 1.6126, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.6957062850031114, | |
| "grad_norm": 2.6744682788848877, | |
| "learning_rate": 4.30119926199262e-06, | |
| "loss": 1.5743, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.6969508400746733, | |
| "grad_norm": 2.7900655269622803, | |
| "learning_rate": 4.29889298892989e-06, | |
| "loss": 1.5865, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6969508400746733, | |
| "eval_loss": 1.724618673324585, | |
| "eval_runtime": 44.2181, | |
| "eval_samples_per_second": 22.615, | |
| "eval_steps_per_second": 0.95, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6981953951462352, | |
| "grad_norm": 2.7363393306732178, | |
| "learning_rate": 4.296586715867159e-06, | |
| "loss": 1.5347, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.6994399502177971, | |
| "grad_norm": 2.696748733520508, | |
| "learning_rate": 4.2942804428044286e-06, | |
| "loss": 1.5463, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.7006845052893591, | |
| "grad_norm": 2.5793895721435547, | |
| "learning_rate": 4.291974169741698e-06, | |
| "loss": 1.6231, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.701929060360921, | |
| "grad_norm": 2.576230764389038, | |
| "learning_rate": 4.289667896678967e-06, | |
| "loss": 1.5663, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.7031736154324829, | |
| "grad_norm": 2.718759298324585, | |
| "learning_rate": 4.287361623616236e-06, | |
| "loss": 1.5316, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.7044181705040448, | |
| "grad_norm": 2.651751756668091, | |
| "learning_rate": 4.285055350553506e-06, | |
| "loss": 1.5777, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.7056627255756067, | |
| "grad_norm": 2.931264638900757, | |
| "learning_rate": 4.282749077490776e-06, | |
| "loss": 1.5647, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.7069072806471687, | |
| "grad_norm": 2.8062546253204346, | |
| "learning_rate": 4.280442804428044e-06, | |
| "loss": 1.5685, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.7081518357187305, | |
| "grad_norm": 2.7551019191741943, | |
| "learning_rate": 4.278136531365314e-06, | |
| "loss": 1.5659, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.7093963907902925, | |
| "grad_norm": 2.799724578857422, | |
| "learning_rate": 4.275830258302583e-06, | |
| "loss": 1.5917, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.7093963907902925, | |
| "eval_loss": 1.7217484712600708, | |
| "eval_runtime": 44.5312, | |
| "eval_samples_per_second": 22.456, | |
| "eval_steps_per_second": 0.943, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.7106409458618543, | |
| "grad_norm": 2.8496406078338623, | |
| "learning_rate": 4.273523985239853e-06, | |
| "loss": 1.5607, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.7118855009334163, | |
| "grad_norm": 2.5612425804138184, | |
| "learning_rate": 4.271217712177122e-06, | |
| "loss": 1.5496, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.7131300560049783, | |
| "grad_norm": 2.6605045795440674, | |
| "learning_rate": 4.268911439114391e-06, | |
| "loss": 1.5371, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.7143746110765401, | |
| "grad_norm": 2.823802947998047, | |
| "learning_rate": 4.266605166051661e-06, | |
| "loss": 1.5699, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.7156191661481021, | |
| "grad_norm": 2.8212928771972656, | |
| "learning_rate": 4.26429889298893e-06, | |
| "loss": 1.5529, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.716863721219664, | |
| "grad_norm": 2.7193386554718018, | |
| "learning_rate": 4.2619926199262e-06, | |
| "loss": 1.5723, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.7181082762912259, | |
| "grad_norm": 2.8348941802978516, | |
| "learning_rate": 4.259686346863469e-06, | |
| "loss": 1.5212, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.7193528313627878, | |
| "grad_norm": 2.7177276611328125, | |
| "learning_rate": 4.2573800738007385e-06, | |
| "loss": 1.5688, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.7205973864343497, | |
| "grad_norm": 2.675734043121338, | |
| "learning_rate": 4.255073800738008e-06, | |
| "loss": 1.5345, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.7218419415059116, | |
| "grad_norm": 2.640942335128784, | |
| "learning_rate": 4.252767527675277e-06, | |
| "loss": 1.5874, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7218419415059116, | |
| "eval_loss": 1.72821044921875, | |
| "eval_runtime": 45.9409, | |
| "eval_samples_per_second": 21.767, | |
| "eval_steps_per_second": 0.914, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7230864965774736, | |
| "grad_norm": 2.785066604614258, | |
| "learning_rate": 4.250461254612546e-06, | |
| "loss": 1.5685, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.7243310516490354, | |
| "grad_norm": 2.8149311542510986, | |
| "learning_rate": 4.248154981549816e-06, | |
| "loss": 1.5106, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.7255756067205974, | |
| "grad_norm": 2.5781238079071045, | |
| "learning_rate": 4.245848708487086e-06, | |
| "loss": 1.5895, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.7268201617921594, | |
| "grad_norm": 2.6275103092193604, | |
| "learning_rate": 4.243542435424355e-06, | |
| "loss": 1.601, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.7280647168637212, | |
| "grad_norm": 2.5282299518585205, | |
| "learning_rate": 4.241236162361624e-06, | |
| "loss": 1.5376, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.7293092719352832, | |
| "grad_norm": 2.7331771850585938, | |
| "learning_rate": 4.238929889298893e-06, | |
| "loss": 1.5855, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.730553827006845, | |
| "grad_norm": 2.6941936016082764, | |
| "learning_rate": 4.236623616236163e-06, | |
| "loss": 1.5937, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.731798382078407, | |
| "grad_norm": 2.924062728881836, | |
| "learning_rate": 4.234317343173432e-06, | |
| "loss": 1.5914, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.7330429371499689, | |
| "grad_norm": 2.687530279159546, | |
| "learning_rate": 4.232011070110701e-06, | |
| "loss": 1.5598, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.7342874922215308, | |
| "grad_norm": 2.7230913639068604, | |
| "learning_rate": 4.229704797047971e-06, | |
| "loss": 1.6048, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7342874922215308, | |
| "eval_loss": 1.7240839004516602, | |
| "eval_runtime": 46.2617, | |
| "eval_samples_per_second": 21.616, | |
| "eval_steps_per_second": 0.908, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7355320472930927, | |
| "grad_norm": 2.833481788635254, | |
| "learning_rate": 4.22739852398524e-06, | |
| "loss": 1.545, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.7367766023646546, | |
| "grad_norm": 2.7287282943725586, | |
| "learning_rate": 4.2250922509225096e-06, | |
| "loss": 1.5795, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.7380211574362165, | |
| "grad_norm": 2.847174882888794, | |
| "learning_rate": 4.222785977859779e-06, | |
| "loss": 1.5469, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.7392657125077785, | |
| "grad_norm": 2.9214589595794678, | |
| "learning_rate": 4.220479704797048e-06, | |
| "loss": 1.5791, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.7405102675793404, | |
| "grad_norm": 2.7506580352783203, | |
| "learning_rate": 4.218173431734318e-06, | |
| "loss": 1.6578, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.7417548226509023, | |
| "grad_norm": 2.7006874084472656, | |
| "learning_rate": 4.215867158671587e-06, | |
| "loss": 1.5598, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.7429993777224643, | |
| "grad_norm": 2.795417547225952, | |
| "learning_rate": 4.213560885608857e-06, | |
| "loss": 1.5862, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.7442439327940261, | |
| "grad_norm": 2.7418057918548584, | |
| "learning_rate": 4.211254612546125e-06, | |
| "loss": 1.5717, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.7454884878655881, | |
| "grad_norm": 2.884915590286255, | |
| "learning_rate": 4.2089483394833955e-06, | |
| "loss": 1.5828, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.7467330429371499, | |
| "grad_norm": 2.752328395843506, | |
| "learning_rate": 4.206642066420665e-06, | |
| "loss": 1.576, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7467330429371499, | |
| "eval_loss": 1.7281302213668823, | |
| "eval_runtime": 45.1978, | |
| "eval_samples_per_second": 22.125, | |
| "eval_steps_per_second": 0.929, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7479775980087119, | |
| "grad_norm": 2.9103147983551025, | |
| "learning_rate": 4.2043357933579335e-06, | |
| "loss": 1.4959, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.7492221530802738, | |
| "grad_norm": 2.5317649841308594, | |
| "learning_rate": 4.202029520295203e-06, | |
| "loss": 1.5092, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.7504667081518357, | |
| "grad_norm": 2.7383415699005127, | |
| "learning_rate": 4.199723247232473e-06, | |
| "loss": 1.4696, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.7517112632233977, | |
| "grad_norm": 2.890305519104004, | |
| "learning_rate": 4.197416974169742e-06, | |
| "loss": 1.511, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.7529558182949595, | |
| "grad_norm": 2.7425734996795654, | |
| "learning_rate": 4.195110701107011e-06, | |
| "loss": 1.5658, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.7542003733665215, | |
| "grad_norm": 2.657726764678955, | |
| "learning_rate": 4.192804428044281e-06, | |
| "loss": 1.5648, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.7554449284380834, | |
| "grad_norm": 3.181201696395874, | |
| "learning_rate": 4.19049815498155e-06, | |
| "loss": 1.583, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.7566894835096453, | |
| "grad_norm": 2.665555715560913, | |
| "learning_rate": 4.1881918819188195e-06, | |
| "loss": 1.5439, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.7579340385812072, | |
| "grad_norm": 2.7328009605407715, | |
| "learning_rate": 4.185885608856089e-06, | |
| "loss": 1.5264, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.7591785936527692, | |
| "grad_norm": 2.7027499675750732, | |
| "learning_rate": 4.183579335793358e-06, | |
| "loss": 1.5327, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7591785936527692, | |
| "eval_loss": 1.7161823511123657, | |
| "eval_runtime": 42.4811, | |
| "eval_samples_per_second": 23.54, | |
| "eval_steps_per_second": 0.989, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.760423148724331, | |
| "grad_norm": 2.6982595920562744, | |
| "learning_rate": 4.181273062730628e-06, | |
| "loss": 1.585, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.761667703795893, | |
| "grad_norm": 2.780768394470215, | |
| "learning_rate": 4.178966789667897e-06, | |
| "loss": 1.5754, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.7629122588674548, | |
| "grad_norm": 2.7140064239501953, | |
| "learning_rate": 4.176660516605167e-06, | |
| "loss": 1.5649, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.7641568139390168, | |
| "grad_norm": 2.60182523727417, | |
| "learning_rate": 4.174354243542435e-06, | |
| "loss": 1.5879, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.7654013690105788, | |
| "grad_norm": 2.6529550552368164, | |
| "learning_rate": 4.1720479704797054e-06, | |
| "loss": 1.5418, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.7666459240821406, | |
| "grad_norm": 2.7936999797821045, | |
| "learning_rate": 4.169741697416975e-06, | |
| "loss": 1.5993, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.7678904791537026, | |
| "grad_norm": 2.7894914150238037, | |
| "learning_rate": 4.1674354243542434e-06, | |
| "loss": 1.5962, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.7691350342252644, | |
| "grad_norm": 2.8094332218170166, | |
| "learning_rate": 4.165129151291513e-06, | |
| "loss": 1.5898, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.7703795892968264, | |
| "grad_norm": 2.9678053855895996, | |
| "learning_rate": 4.162822878228783e-06, | |
| "loss": 1.5602, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.7716241443683883, | |
| "grad_norm": 2.7238247394561768, | |
| "learning_rate": 4.1605166051660526e-06, | |
| "loss": 1.554, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7716241443683883, | |
| "eval_loss": 1.720330834388733, | |
| "eval_runtime": 47.0576, | |
| "eval_samples_per_second": 21.251, | |
| "eval_steps_per_second": 0.893, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7728686994399502, | |
| "grad_norm": 2.6484885215759277, | |
| "learning_rate": 4.158210332103321e-06, | |
| "loss": 1.5464, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.7741132545115121, | |
| "grad_norm": 2.722929000854492, | |
| "learning_rate": 4.1559040590405906e-06, | |
| "loss": 1.5471, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.7753578095830741, | |
| "grad_norm": 2.842886209487915, | |
| "learning_rate": 4.15359778597786e-06, | |
| "loss": 1.5512, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.776602364654636, | |
| "grad_norm": 2.647134780883789, | |
| "learning_rate": 4.151291512915129e-06, | |
| "loss": 1.5264, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.7778469197261979, | |
| "grad_norm": 2.763277053833008, | |
| "learning_rate": 4.148985239852399e-06, | |
| "loss": 1.5102, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.7790914747977598, | |
| "grad_norm": 2.9078922271728516, | |
| "learning_rate": 4.146678966789668e-06, | |
| "loss": 1.5538, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.7803360298693217, | |
| "grad_norm": 2.60658860206604, | |
| "learning_rate": 4.144372693726938e-06, | |
| "loss": 1.486, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.7815805849408837, | |
| "grad_norm": 2.5513789653778076, | |
| "learning_rate": 4.142066420664207e-06, | |
| "loss": 1.5323, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.7828251400124455, | |
| "grad_norm": 3.0412704944610596, | |
| "learning_rate": 4.1397601476014765e-06, | |
| "loss": 1.5835, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.7840696950840075, | |
| "grad_norm": 2.9483704566955566, | |
| "learning_rate": 4.137453874538745e-06, | |
| "loss": 1.5849, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7840696950840075, | |
| "eval_loss": 1.7138603925704956, | |
| "eval_runtime": 47.7618, | |
| "eval_samples_per_second": 20.937, | |
| "eval_steps_per_second": 0.879, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7853142501555694, | |
| "grad_norm": 2.784747362136841, | |
| "learning_rate": 4.135147601476015e-06, | |
| "loss": 1.5625, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.7865588052271313, | |
| "grad_norm": 2.775791883468628, | |
| "learning_rate": 4.132841328413285e-06, | |
| "loss": 1.5827, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.7878033602986932, | |
| "grad_norm": 2.867126226425171, | |
| "learning_rate": 4.130535055350554e-06, | |
| "loss": 1.5174, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.7890479153702551, | |
| "grad_norm": 2.7829818725585938, | |
| "learning_rate": 4.128228782287823e-06, | |
| "loss": 1.5853, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.790292470441817, | |
| "grad_norm": 2.630842924118042, | |
| "learning_rate": 4.125922509225092e-06, | |
| "loss": 1.5853, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.791537025513379, | |
| "grad_norm": 2.8100547790527344, | |
| "learning_rate": 4.1236162361623625e-06, | |
| "loss": 1.5162, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.7927815805849409, | |
| "grad_norm": 2.5983335971832275, | |
| "learning_rate": 4.121309963099631e-06, | |
| "loss": 1.5926, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.7940261356565028, | |
| "grad_norm": 2.826624870300293, | |
| "learning_rate": 4.1190036900369005e-06, | |
| "loss": 1.5527, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.7952706907280647, | |
| "grad_norm": 2.863215684890747, | |
| "learning_rate": 4.11669741697417e-06, | |
| "loss": 1.5514, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.7965152457996266, | |
| "grad_norm": 2.7492613792419434, | |
| "learning_rate": 4.114391143911439e-06, | |
| "loss": 1.5101, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7965152457996266, | |
| "eval_loss": 1.7091425657272339, | |
| "eval_runtime": 46.5279, | |
| "eval_samples_per_second": 21.492, | |
| "eval_steps_per_second": 0.903, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7977598008711886, | |
| "grad_norm": 2.9577860832214355, | |
| "learning_rate": 4.112084870848709e-06, | |
| "loss": 1.5496, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.7990043559427504, | |
| "grad_norm": 2.612668991088867, | |
| "learning_rate": 4.109778597785978e-06, | |
| "loss": 1.5204, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.8002489110143124, | |
| "grad_norm": 2.5427377223968506, | |
| "learning_rate": 4.107472324723248e-06, | |
| "loss": 1.5038, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.8014934660858744, | |
| "grad_norm": 2.7057406902313232, | |
| "learning_rate": 4.105166051660517e-06, | |
| "loss": 1.5831, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.8027380211574362, | |
| "grad_norm": 2.664353609085083, | |
| "learning_rate": 4.1028597785977864e-06, | |
| "loss": 1.555, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.8039825762289982, | |
| "grad_norm": 2.5452728271484375, | |
| "learning_rate": 4.100553505535056e-06, | |
| "loss": 1.5847, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.80522713130056, | |
| "grad_norm": 2.5370709896087646, | |
| "learning_rate": 4.098247232472325e-06, | |
| "loss": 1.5396, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.806471686372122, | |
| "grad_norm": 2.730109930038452, | |
| "learning_rate": 4.095940959409595e-06, | |
| "loss": 1.5234, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.8077162414436839, | |
| "grad_norm": 2.586108446121216, | |
| "learning_rate": 4.093634686346864e-06, | |
| "loss": 1.5885, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.8089607965152458, | |
| "grad_norm": 2.557053804397583, | |
| "learning_rate": 4.091328413284133e-06, | |
| "loss": 1.483, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8089607965152458, | |
| "eval_loss": 1.7204149961471558, | |
| "eval_runtime": 48.0041, | |
| "eval_samples_per_second": 20.832, | |
| "eval_steps_per_second": 0.875, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.8102053515868077, | |
| "grad_norm": 2.673672676086426, | |
| "learning_rate": 4.089022140221402e-06, | |
| "loss": 1.4837, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.8114499066583696, | |
| "grad_norm": 2.6465933322906494, | |
| "learning_rate": 4.086715867158672e-06, | |
| "loss": 1.5219, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.8126944617299315, | |
| "grad_norm": 2.6897783279418945, | |
| "learning_rate": 4.084409594095941e-06, | |
| "loss": 1.5116, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.8139390168014935, | |
| "grad_norm": 2.644369602203369, | |
| "learning_rate": 4.08210332103321e-06, | |
| "loss": 1.5141, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.8151835718730553, | |
| "grad_norm": 2.7475595474243164, | |
| "learning_rate": 4.07979704797048e-06, | |
| "loss": 1.5509, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.8164281269446173, | |
| "grad_norm": 2.72043514251709, | |
| "learning_rate": 4.077490774907749e-06, | |
| "loss": 1.6098, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.8176726820161793, | |
| "grad_norm": 2.648069381713867, | |
| "learning_rate": 4.075184501845019e-06, | |
| "loss": 1.5368, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.8189172370877411, | |
| "grad_norm": 2.644893169403076, | |
| "learning_rate": 4.072878228782288e-06, | |
| "loss": 1.492, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.8201617921593031, | |
| "grad_norm": 2.9441068172454834, | |
| "learning_rate": 4.0705719557195575e-06, | |
| "loss": 1.5904, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.8214063472308649, | |
| "grad_norm": 2.752913475036621, | |
| "learning_rate": 4.068265682656827e-06, | |
| "loss": 1.5544, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8214063472308649, | |
| "eval_loss": 1.709177017211914, | |
| "eval_runtime": 48.0401, | |
| "eval_samples_per_second": 20.816, | |
| "eval_steps_per_second": 0.874, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8226509023024269, | |
| "grad_norm": 2.6959197521209717, | |
| "learning_rate": 4.065959409594096e-06, | |
| "loss": 1.5553, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.8238954573739888, | |
| "grad_norm": 2.8757998943328857, | |
| "learning_rate": 4.063653136531366e-06, | |
| "loss": 1.554, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.8251400124455507, | |
| "grad_norm": 2.7723867893218994, | |
| "learning_rate": 4.061346863468635e-06, | |
| "loss": 1.5499, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.8263845675171126, | |
| "grad_norm": 2.7620463371276855, | |
| "learning_rate": 4.059040590405905e-06, | |
| "loss": 1.5962, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.8276291225886746, | |
| "grad_norm": 2.8601174354553223, | |
| "learning_rate": 4.056734317343174e-06, | |
| "loss": 1.5218, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.8288736776602365, | |
| "grad_norm": 2.81356143951416, | |
| "learning_rate": 4.054428044280443e-06, | |
| "loss": 1.5382, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.8301182327317984, | |
| "grad_norm": 2.904679298400879, | |
| "learning_rate": 4.052121771217712e-06, | |
| "loss": 1.5314, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.8313627878033603, | |
| "grad_norm": 2.798236846923828, | |
| "learning_rate": 4.049815498154982e-06, | |
| "loss": 1.5989, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.8326073428749222, | |
| "grad_norm": 2.8923728466033936, | |
| "learning_rate": 4.047509225092252e-06, | |
| "loss": 1.5475, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.8338518979464842, | |
| "grad_norm": 2.6134703159332275, | |
| "learning_rate": 4.04520295202952e-06, | |
| "loss": 1.5232, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.8338518979464842, | |
| "eval_loss": 1.7080007791519165, | |
| "eval_runtime": 52.6531, | |
| "eval_samples_per_second": 18.992, | |
| "eval_steps_per_second": 0.798, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.835096453018046, | |
| "grad_norm": 2.6788907051086426, | |
| "learning_rate": 4.04289667896679e-06, | |
| "loss": 1.5437, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.836341008089608, | |
| "grad_norm": 2.872429847717285, | |
| "learning_rate": 4.04059040590406e-06, | |
| "loss": 1.5368, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.8375855631611698, | |
| "grad_norm": 2.714857578277588, | |
| "learning_rate": 4.038284132841329e-06, | |
| "loss": 1.5404, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.8388301182327318, | |
| "grad_norm": 2.6955931186676025, | |
| "learning_rate": 4.035977859778598e-06, | |
| "loss": 1.5501, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.8400746733042938, | |
| "grad_norm": 2.7090582847595215, | |
| "learning_rate": 4.0336715867158674e-06, | |
| "loss": 1.5068, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.8413192283758556, | |
| "grad_norm": 2.8406383991241455, | |
| "learning_rate": 4.031365313653137e-06, | |
| "loss": 1.5529, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.8425637834474176, | |
| "grad_norm": 2.965557098388672, | |
| "learning_rate": 4.029059040590406e-06, | |
| "loss": 1.5847, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.8438083385189795, | |
| "grad_norm": 2.664083242416382, | |
| "learning_rate": 4.026752767527676e-06, | |
| "loss": 1.5701, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.8450528935905414, | |
| "grad_norm": 2.7362401485443115, | |
| "learning_rate": 4.024446494464945e-06, | |
| "loss": 1.5496, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.8462974486621033, | |
| "grad_norm": 2.695342540740967, | |
| "learning_rate": 4.0221402214022145e-06, | |
| "loss": 1.5009, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8462974486621033, | |
| "eval_loss": 1.7063637971878052, | |
| "eval_runtime": 52.7749, | |
| "eval_samples_per_second": 18.948, | |
| "eval_steps_per_second": 0.796, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8475420037336652, | |
| "grad_norm": 2.615994453430176, | |
| "learning_rate": 4.019833948339484e-06, | |
| "loss": 1.5281, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.8487865588052271, | |
| "grad_norm": 3.065732002258301, | |
| "learning_rate": 4.017527675276753e-06, | |
| "loss": 1.5616, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.8500311138767891, | |
| "grad_norm": 2.812166690826416, | |
| "learning_rate": 4.015221402214022e-06, | |
| "loss": 1.5573, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.8512756689483509, | |
| "grad_norm": 2.745252847671509, | |
| "learning_rate": 4.012915129151292e-06, | |
| "loss": 1.5426, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.8525202240199129, | |
| "grad_norm": 2.862264633178711, | |
| "learning_rate": 4.010608856088562e-06, | |
| "loss": 1.4973, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.8537647790914747, | |
| "grad_norm": 2.752469062805176, | |
| "learning_rate": 4.00830258302583e-06, | |
| "loss": 1.5416, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.8550093341630367, | |
| "grad_norm": 2.5692927837371826, | |
| "learning_rate": 4.0059963099631e-06, | |
| "loss": 1.5021, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.8562538892345987, | |
| "grad_norm": 2.896444320678711, | |
| "learning_rate": 4.003690036900369e-06, | |
| "loss": 1.5794, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.8574984443061605, | |
| "grad_norm": 2.7448434829711914, | |
| "learning_rate": 4.0013837638376385e-06, | |
| "loss": 1.5138, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.8587429993777225, | |
| "grad_norm": 2.8280975818634033, | |
| "learning_rate": 3.999077490774908e-06, | |
| "loss": 1.5071, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8587429993777225, | |
| "eval_loss": 1.7048547267913818, | |
| "eval_runtime": 52.8015, | |
| "eval_samples_per_second": 18.939, | |
| "eval_steps_per_second": 0.795, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8599875544492844, | |
| "grad_norm": 2.701293706893921, | |
| "learning_rate": 3.996771217712177e-06, | |
| "loss": 1.5457, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.8612321095208463, | |
| "grad_norm": 2.673452138900757, | |
| "learning_rate": 3.994464944649447e-06, | |
| "loss": 1.5355, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.8624766645924082, | |
| "grad_norm": 2.7728021144866943, | |
| "learning_rate": 3.992158671586716e-06, | |
| "loss": 1.5486, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.8637212196639701, | |
| "grad_norm": 2.747614860534668, | |
| "learning_rate": 3.989852398523986e-06, | |
| "loss": 1.5771, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.864965774735532, | |
| "grad_norm": 2.6240482330322266, | |
| "learning_rate": 3.987546125461255e-06, | |
| "loss": 1.5338, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.866210329807094, | |
| "grad_norm": 2.8253114223480225, | |
| "learning_rate": 3.9852398523985245e-06, | |
| "loss": 1.5029, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.8674548848786559, | |
| "grad_norm": 2.7980496883392334, | |
| "learning_rate": 3.982933579335794e-06, | |
| "loss": 1.5239, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.8686994399502178, | |
| "grad_norm": 2.937443971633911, | |
| "learning_rate": 3.980627306273063e-06, | |
| "loss": 1.5406, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.8699439950217797, | |
| "grad_norm": 2.714353322982788, | |
| "learning_rate": 3.978321033210332e-06, | |
| "loss": 1.5724, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.8711885500933416, | |
| "grad_norm": 2.7986929416656494, | |
| "learning_rate": 3.976014760147602e-06, | |
| "loss": 1.5687, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8711885500933416, | |
| "eval_loss": 1.6998120546340942, | |
| "eval_runtime": 46.4448, | |
| "eval_samples_per_second": 21.531, | |
| "eval_steps_per_second": 0.904, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8724331051649036, | |
| "grad_norm": 2.755740165710449, | |
| "learning_rate": 3.973708487084872e-06, | |
| "loss": 1.5047, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.8736776602364654, | |
| "grad_norm": 2.760399341583252, | |
| "learning_rate": 3.97140221402214e-06, | |
| "loss": 1.5406, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.8749222153080274, | |
| "grad_norm": 2.780214786529541, | |
| "learning_rate": 3.96909594095941e-06, | |
| "loss": 1.551, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.8761667703795893, | |
| "grad_norm": 2.669801950454712, | |
| "learning_rate": 3.966789667896679e-06, | |
| "loss": 1.5578, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.8774113254511512, | |
| "grad_norm": 2.729586362838745, | |
| "learning_rate": 3.964483394833948e-06, | |
| "loss": 1.4808, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.8786558805227132, | |
| "grad_norm": 2.608551263809204, | |
| "learning_rate": 3.962177121771218e-06, | |
| "loss": 1.4649, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.879900435594275, | |
| "grad_norm": 3.0885748863220215, | |
| "learning_rate": 3.959870848708487e-06, | |
| "loss": 1.5602, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.881144990665837, | |
| "grad_norm": 2.659917116165161, | |
| "learning_rate": 3.957564575645757e-06, | |
| "loss": 1.5341, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.8823895457373989, | |
| "grad_norm": 2.718696355819702, | |
| "learning_rate": 3.955258302583026e-06, | |
| "loss": 1.5232, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.8836341008089608, | |
| "grad_norm": 2.902811288833618, | |
| "learning_rate": 3.9529520295202955e-06, | |
| "loss": 1.517, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.8836341008089608, | |
| "eval_loss": 1.7022311687469482, | |
| "eval_runtime": 43.1291, | |
| "eval_samples_per_second": 23.186, | |
| "eval_steps_per_second": 0.974, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.8848786558805227, | |
| "grad_norm": 2.816802978515625, | |
| "learning_rate": 3.950645756457565e-06, | |
| "loss": 1.5097, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.8861232109520847, | |
| "grad_norm": 2.8189518451690674, | |
| "learning_rate": 3.948339483394834e-06, | |
| "loss": 1.5842, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.8873677660236465, | |
| "grad_norm": 2.879767417907715, | |
| "learning_rate": 3.946033210332104e-06, | |
| "loss": 1.5484, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.8886123210952085, | |
| "grad_norm": 2.8263540267944336, | |
| "learning_rate": 3.943726937269373e-06, | |
| "loss": 1.5259, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.8898568761667703, | |
| "grad_norm": 2.655139923095703, | |
| "learning_rate": 3.941420664206642e-06, | |
| "loss": 1.482, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.8911014312383323, | |
| "grad_norm": 2.63429856300354, | |
| "learning_rate": 3.939114391143912e-06, | |
| "loss": 1.512, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.8923459863098943, | |
| "grad_norm": 2.9241650104522705, | |
| "learning_rate": 3.9368081180811815e-06, | |
| "loss": 1.5347, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.8935905413814561, | |
| "grad_norm": 2.8512847423553467, | |
| "learning_rate": 3.934501845018451e-06, | |
| "loss": 1.5791, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.8948350964530181, | |
| "grad_norm": 2.5280821323394775, | |
| "learning_rate": 3.9321955719557195e-06, | |
| "loss": 1.4823, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.8960796515245799, | |
| "grad_norm": 2.6618733406066895, | |
| "learning_rate": 3.929889298892989e-06, | |
| "loss": 1.4708, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8960796515245799, | |
| "eval_loss": 1.6904946565628052, | |
| "eval_runtime": 49.3149, | |
| "eval_samples_per_second": 20.278, | |
| "eval_steps_per_second": 0.852, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8973242065961419, | |
| "grad_norm": 2.8406248092651367, | |
| "learning_rate": 3.927583025830259e-06, | |
| "loss": 1.5425, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.8985687616677038, | |
| "grad_norm": 2.807971715927124, | |
| "learning_rate": 3.925276752767528e-06, | |
| "loss": 1.5617, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.8998133167392657, | |
| "grad_norm": 2.6703925132751465, | |
| "learning_rate": 3.922970479704797e-06, | |
| "loss": 1.5544, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.9010578718108276, | |
| "grad_norm": 2.785083770751953, | |
| "learning_rate": 3.920664206642067e-06, | |
| "loss": 1.5696, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.9023024268823896, | |
| "grad_norm": 2.7778568267822266, | |
| "learning_rate": 3.918357933579336e-06, | |
| "loss": 1.5262, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.9035469819539514, | |
| "grad_norm": 2.6343681812286377, | |
| "learning_rate": 3.9160516605166055e-06, | |
| "loss": 1.5509, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.9047915370255134, | |
| "grad_norm": 2.6923940181732178, | |
| "learning_rate": 3.913745387453875e-06, | |
| "loss": 1.5425, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.9060360920970753, | |
| "grad_norm": 2.732797861099243, | |
| "learning_rate": 3.911439114391144e-06, | |
| "loss": 1.4524, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.9072806471686372, | |
| "grad_norm": 2.6365227699279785, | |
| "learning_rate": 3.909132841328414e-06, | |
| "loss": 1.5617, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.9085252022401992, | |
| "grad_norm": 2.646639823913574, | |
| "learning_rate": 3.906826568265683e-06, | |
| "loss": 1.5122, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.9085252022401992, | |
| "eval_loss": 1.6920651197433472, | |
| "eval_runtime": 48.5914, | |
| "eval_samples_per_second": 20.58, | |
| "eval_steps_per_second": 0.864, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.909769757311761, | |
| "grad_norm": 2.5834903717041016, | |
| "learning_rate": 3.9045202952029526e-06, | |
| "loss": 1.5095, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.911014312383323, | |
| "grad_norm": 2.4998092651367188, | |
| "learning_rate": 3.902214022140222e-06, | |
| "loss": 1.4376, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.9122588674548848, | |
| "grad_norm": 2.5143818855285645, | |
| "learning_rate": 3.899907749077491e-06, | |
| "loss": 1.5222, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.9135034225264468, | |
| "grad_norm": 2.7795114517211914, | |
| "learning_rate": 3.897601476014761e-06, | |
| "loss": 1.5498, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.9147479775980087, | |
| "grad_norm": 2.819859027862549, | |
| "learning_rate": 3.895295202952029e-06, | |
| "loss": 1.5288, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.9159925326695706, | |
| "grad_norm": 2.663306951522827, | |
| "learning_rate": 3.892988929889299e-06, | |
| "loss": 1.4517, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.9172370877411326, | |
| "grad_norm": 2.775521993637085, | |
| "learning_rate": 3.890682656826569e-06, | |
| "loss": 1.529, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.9184816428126945, | |
| "grad_norm": 2.761237859725952, | |
| "learning_rate": 3.888376383763838e-06, | |
| "loss": 1.4781, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.9197261978842564, | |
| "grad_norm": 2.5410993099212646, | |
| "learning_rate": 3.886070110701107e-06, | |
| "loss": 1.4205, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.9209707529558183, | |
| "grad_norm": 2.6289987564086914, | |
| "learning_rate": 3.8837638376383765e-06, | |
| "loss": 1.5253, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9209707529558183, | |
| "eval_loss": 1.700616717338562, | |
| "eval_runtime": 46.1038, | |
| "eval_samples_per_second": 21.69, | |
| "eval_steps_per_second": 0.911, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9222153080273802, | |
| "grad_norm": 2.694406270980835, | |
| "learning_rate": 3.881457564575646e-06, | |
| "loss": 1.5335, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.9234598630989421, | |
| "grad_norm": 2.597160577774048, | |
| "learning_rate": 3.879151291512915e-06, | |
| "loss": 1.5026, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.9247044181705041, | |
| "grad_norm": 2.625049114227295, | |
| "learning_rate": 3.876845018450185e-06, | |
| "loss": 1.4885, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.9259489732420659, | |
| "grad_norm": 2.5983152389526367, | |
| "learning_rate": 3.874538745387454e-06, | |
| "loss": 1.5015, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.9271935283136279, | |
| "grad_norm": 2.6912894248962402, | |
| "learning_rate": 3.872232472324724e-06, | |
| "loss": 1.5179, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.9284380833851898, | |
| "grad_norm": 2.699328899383545, | |
| "learning_rate": 3.869926199261993e-06, | |
| "loss": 1.5571, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.9296826384567517, | |
| "grad_norm": 2.7117769718170166, | |
| "learning_rate": 3.8676199261992625e-06, | |
| "loss": 1.5225, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.9309271935283137, | |
| "grad_norm": 2.785900354385376, | |
| "learning_rate": 3.865313653136532e-06, | |
| "loss": 1.5571, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.9321717485998755, | |
| "grad_norm": 2.6901021003723145, | |
| "learning_rate": 3.863007380073801e-06, | |
| "loss": 1.5108, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.9334163036714375, | |
| "grad_norm": 2.55047607421875, | |
| "learning_rate": 3.860701107011071e-06, | |
| "loss": 1.4934, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9334163036714375, | |
| "eval_loss": 1.693824291229248, | |
| "eval_runtime": 45.7403, | |
| "eval_samples_per_second": 21.863, | |
| "eval_steps_per_second": 0.918, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9346608587429994, | |
| "grad_norm": 2.7620902061462402, | |
| "learning_rate": 3.858394833948339e-06, | |
| "loss": 1.5129, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.9359054138145613, | |
| "grad_norm": 2.798583984375, | |
| "learning_rate": 3.856088560885609e-06, | |
| "loss": 1.4986, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.9371499688861232, | |
| "grad_norm": 2.5885400772094727, | |
| "learning_rate": 3.853782287822879e-06, | |
| "loss": 1.4779, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.9383945239576851, | |
| "grad_norm": 2.8280391693115234, | |
| "learning_rate": 3.851476014760148e-06, | |
| "loss": 1.6156, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.939639079029247, | |
| "grad_norm": 2.7616288661956787, | |
| "learning_rate": 3.849169741697417e-06, | |
| "loss": 1.5051, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.940883634100809, | |
| "grad_norm": 2.598370313644409, | |
| "learning_rate": 3.8468634686346865e-06, | |
| "loss": 1.5569, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.9421281891723708, | |
| "grad_norm": 2.649433135986328, | |
| "learning_rate": 3.844557195571956e-06, | |
| "loss": 1.515, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.9433727442439328, | |
| "grad_norm": 2.568361759185791, | |
| "learning_rate": 3.842250922509225e-06, | |
| "loss": 1.4926, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.9446172993154948, | |
| "grad_norm": 2.6539297103881836, | |
| "learning_rate": 3.839944649446495e-06, | |
| "loss": 1.4813, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.9458618543870566, | |
| "grad_norm": 2.6790902614593506, | |
| "learning_rate": 3.837638376383764e-06, | |
| "loss": 1.5056, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9458618543870566, | |
| "eval_loss": 1.6913493871688843, | |
| "eval_runtime": 44.5061, | |
| "eval_samples_per_second": 22.469, | |
| "eval_steps_per_second": 0.944, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9471064094586186, | |
| "grad_norm": 2.6265010833740234, | |
| "learning_rate": 3.8353321033210336e-06, | |
| "loss": 1.5421, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.9483509645301804, | |
| "grad_norm": 2.5852062702178955, | |
| "learning_rate": 3.833025830258303e-06, | |
| "loss": 1.5145, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.9495955196017424, | |
| "grad_norm": 2.6579225063323975, | |
| "learning_rate": 3.830719557195572e-06, | |
| "loss": 1.4988, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.9508400746733043, | |
| "grad_norm": 2.7944133281707764, | |
| "learning_rate": 3.828413284132842e-06, | |
| "loss": 1.5199, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.9520846297448662, | |
| "grad_norm": 2.5813052654266357, | |
| "learning_rate": 3.826107011070111e-06, | |
| "loss": 1.5072, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.9533291848164281, | |
| "grad_norm": 2.551501512527466, | |
| "learning_rate": 3.823800738007381e-06, | |
| "loss": 1.5348, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.95457373988799, | |
| "grad_norm": 2.755141496658325, | |
| "learning_rate": 3.821494464944649e-06, | |
| "loss": 1.4787, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.955818294959552, | |
| "grad_norm": 2.521984338760376, | |
| "learning_rate": 3.819188191881919e-06, | |
| "loss": 1.4778, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.9570628500311139, | |
| "grad_norm": 2.6301770210266113, | |
| "learning_rate": 3.816881918819189e-06, | |
| "loss": 1.4703, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.9583074051026758, | |
| "grad_norm": 2.972749710083008, | |
| "learning_rate": 3.814575645756458e-06, | |
| "loss": 1.5516, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.9583074051026758, | |
| "eval_loss": 1.689251184463501, | |
| "eval_runtime": 44.3352, | |
| "eval_samples_per_second": 22.555, | |
| "eval_steps_per_second": 0.947, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.9595519601742377, | |
| "grad_norm": 2.7247636318206787, | |
| "learning_rate": 3.812269372693727e-06, | |
| "loss": 1.5659, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.9607965152457997, | |
| "grad_norm": 2.6853489875793457, | |
| "learning_rate": 3.809963099630997e-06, | |
| "loss": 1.5149, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.9620410703173615, | |
| "grad_norm": 2.6767218112945557, | |
| "learning_rate": 3.8076568265682662e-06, | |
| "loss": 1.5573, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.9632856253889235, | |
| "grad_norm": 2.5949296951293945, | |
| "learning_rate": 3.8053505535055352e-06, | |
| "loss": 1.517, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.9645301804604853, | |
| "grad_norm": 2.841171979904175, | |
| "learning_rate": 3.8030442804428046e-06, | |
| "loss": 1.515, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.9657747355320473, | |
| "grad_norm": 2.7451512813568115, | |
| "learning_rate": 3.800738007380074e-06, | |
| "loss": 1.516, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.9670192906036092, | |
| "grad_norm": 2.6852564811706543, | |
| "learning_rate": 3.798431734317343e-06, | |
| "loss": 1.5187, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.9682638456751711, | |
| "grad_norm": 2.72956919670105, | |
| "learning_rate": 3.796125461254613e-06, | |
| "loss": 1.5344, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.9695084007467331, | |
| "grad_norm": 2.672933578491211, | |
| "learning_rate": 3.7938191881918823e-06, | |
| "loss": 1.5143, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.9707529558182949, | |
| "grad_norm": 2.6565003395080566, | |
| "learning_rate": 3.7915129151291518e-06, | |
| "loss": 1.4759, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9707529558182949, | |
| "eval_loss": 1.6836074590682983, | |
| "eval_runtime": 44.0331, | |
| "eval_samples_per_second": 22.71, | |
| "eval_steps_per_second": 0.954, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9719975108898569, | |
| "grad_norm": 2.665921449661255, | |
| "learning_rate": 3.7892066420664208e-06, | |
| "loss": 1.4985, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.9732420659614188, | |
| "grad_norm": 2.671757221221924, | |
| "learning_rate": 3.7869003690036906e-06, | |
| "loss": 1.5014, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.9744866210329807, | |
| "grad_norm": 2.7320780754089355, | |
| "learning_rate": 3.78459409594096e-06, | |
| "loss": 1.5052, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.9757311761045426, | |
| "grad_norm": 3.0772581100463867, | |
| "learning_rate": 3.782287822878229e-06, | |
| "loss": 1.5666, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.9769757311761046, | |
| "grad_norm": 2.651129722595215, | |
| "learning_rate": 3.7799815498154984e-06, | |
| "loss": 1.4954, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.9782202862476664, | |
| "grad_norm": 2.6942505836486816, | |
| "learning_rate": 3.777675276752768e-06, | |
| "loss": 1.5186, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.9794648413192284, | |
| "grad_norm": 2.767474412918091, | |
| "learning_rate": 3.775369003690037e-06, | |
| "loss": 1.4699, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.9807093963907902, | |
| "grad_norm": 2.728269100189209, | |
| "learning_rate": 3.7730627306273067e-06, | |
| "loss": 1.5176, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.9819539514623522, | |
| "grad_norm": 2.697984218597412, | |
| "learning_rate": 3.770756457564576e-06, | |
| "loss": 1.5327, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.9831985065339142, | |
| "grad_norm": 2.8172037601470947, | |
| "learning_rate": 3.768450184501845e-06, | |
| "loss": 1.4996, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.9831985065339142, | |
| "eval_loss": 1.7013198137283325, | |
| "eval_runtime": 44.5233, | |
| "eval_samples_per_second": 22.46, | |
| "eval_steps_per_second": 0.943, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.984443061605476, | |
| "grad_norm": 2.8202197551727295, | |
| "learning_rate": 3.7661439114391146e-06, | |
| "loss": 1.5193, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.985687616677038, | |
| "grad_norm": 2.764653444290161, | |
| "learning_rate": 3.763837638376384e-06, | |
| "loss": 1.5544, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.9869321717485999, | |
| "grad_norm": 2.6528818607330322, | |
| "learning_rate": 3.761531365313654e-06, | |
| "loss": 1.5328, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.9881767268201618, | |
| "grad_norm": 2.643666982650757, | |
| "learning_rate": 3.759225092250923e-06, | |
| "loss": 1.5279, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.9894212818917237, | |
| "grad_norm": 2.631007432937622, | |
| "learning_rate": 3.7569188191881922e-06, | |
| "loss": 1.5135, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.9906658369632856, | |
| "grad_norm": 2.6622400283813477, | |
| "learning_rate": 3.7546125461254617e-06, | |
| "loss": 1.5099, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.9919103920348475, | |
| "grad_norm": 2.5758702754974365, | |
| "learning_rate": 3.7523062730627307e-06, | |
| "loss": 1.4691, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.9931549471064095, | |
| "grad_norm": 2.822147846221924, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.4846, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.9943995021779714, | |
| "grad_norm": 3.166783571243286, | |
| "learning_rate": 3.74769372693727e-06, | |
| "loss": 1.5586, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.9956440572495333, | |
| "grad_norm": 2.931654691696167, | |
| "learning_rate": 3.745387453874539e-06, | |
| "loss": 1.4773, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9956440572495333, | |
| "eval_loss": 1.6904431581497192, | |
| "eval_runtime": 43.927, | |
| "eval_samples_per_second": 22.765, | |
| "eval_steps_per_second": 0.956, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 2409, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.493847527489536e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |