| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.24891101431238333, | |
| "eval_steps": 10, | |
| "global_step": 200, | |
| "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 | |
| } | |
| ], | |
| "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": 6.23461881872384e+16, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |