| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.40431266846361186, | |
| "eval_steps": 38, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026954177897574125, | |
| "grad_norm": 0.4888671256680066, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.6499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026954177897574125, | |
| "eval_loss": 2.7584831714630127, | |
| "eval_runtime": 108.9254, | |
| "eval_samples_per_second": 0.734, | |
| "eval_steps_per_second": 0.184, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005390835579514825, | |
| "grad_norm": 0.4983074714711494, | |
| "learning_rate": 5e-06, | |
| "loss": 2.5992, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008086253369272238, | |
| "grad_norm": 0.7241191448700953, | |
| "learning_rate": 7.5e-06, | |
| "loss": 2.8753, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01078167115902965, | |
| "grad_norm": 0.5260744264207279, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6477, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013477088948787063, | |
| "grad_norm": 0.36639797120190076, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2.5086, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016172506738544475, | |
| "grad_norm": 0.7809079947872807, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.8346, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018867924528301886, | |
| "grad_norm": 0.5980534435082484, | |
| "learning_rate": 1.75e-05, | |
| "loss": 2.9624, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0215633423180593, | |
| "grad_norm": 0.5798622117264719, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8441, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02425876010781671, | |
| "grad_norm": 0.7528222488078259, | |
| "learning_rate": 2.25e-05, | |
| "loss": 2.6867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026954177897574125, | |
| "grad_norm": 0.612852819847163, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.7927, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029649595687331536, | |
| "grad_norm": 0.6397459055001692, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 2.6072, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03234501347708895, | |
| "grad_norm": 0.6598580504868401, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5274, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03504043126684636, | |
| "grad_norm": 0.30737376780003156, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 2.5507, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "grad_norm": 0.14992908808228841, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.4811, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04043126684636118, | |
| "grad_norm": 0.22421462173093706, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 2.6159, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0431266846361186, | |
| "grad_norm": 0.16819168085460345, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6193, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04582210242587601, | |
| "grad_norm": 0.12218717106853527, | |
| "learning_rate": 4.25e-05, | |
| "loss": 2.7094, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04851752021563342, | |
| "grad_norm": 0.1145865395458764, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.6314, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05121293800539083, | |
| "grad_norm": 0.08821545171076035, | |
| "learning_rate": 4.75e-05, | |
| "loss": 2.4876, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05390835579514825, | |
| "grad_norm": 0.10203760270867333, | |
| "learning_rate": 5e-05, | |
| "loss": 2.622, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05660377358490566, | |
| "grad_norm": 0.07748067981259345, | |
| "learning_rate": 4.9999098771046674e-05, | |
| "loss": 2.4191, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05929919137466307, | |
| "grad_norm": 0.13225530856023926, | |
| "learning_rate": 4.999639515638348e-05, | |
| "loss": 2.642, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06199460916442048, | |
| "grad_norm": 0.07588900512747042, | |
| "learning_rate": 4.999188937259492e-05, | |
| "loss": 2.2706, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0646900269541779, | |
| "grad_norm": 0.12017105244364508, | |
| "learning_rate": 4.998558178063592e-05, | |
| "loss": 2.6609, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0673854447439353, | |
| "grad_norm": 0.13885153935053832, | |
| "learning_rate": 4.9977472885802876e-05, | |
| "loss": 2.3222, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07008086253369272, | |
| "grad_norm": 0.08273500402204699, | |
| "learning_rate": 4.996756333769319e-05, | |
| "loss": 2.2653, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07277628032345014, | |
| "grad_norm": 0.08128820734533522, | |
| "learning_rate": 4.995585393015324e-05, | |
| "loss": 2.468, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 0.11425098408554267, | |
| "learning_rate": 4.9942345601214764e-05, | |
| "loss": 2.0993, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07816711590296496, | |
| "grad_norm": 0.10026403239718774, | |
| "learning_rate": 4.992703943301973e-05, | |
| "loss": 2.4194, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08086253369272237, | |
| "grad_norm": 0.0892349090753594, | |
| "learning_rate": 4.990993665173364e-05, | |
| "loss": 2.5426, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08355795148247978, | |
| "grad_norm": 0.08905031867375157, | |
| "learning_rate": 4.989103862744732e-05, | |
| "loss": 2.4458, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0862533692722372, | |
| "grad_norm": 0.08382151700226004, | |
| "learning_rate": 4.987034687406713e-05, | |
| "loss": 2.4005, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0889487870619946, | |
| "grad_norm": 0.07624420840782331, | |
| "learning_rate": 4.984786304919372e-05, | |
| "loss": 2.3028, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09164420485175202, | |
| "grad_norm": 0.08195304711308972, | |
| "learning_rate": 4.9823588953989216e-05, | |
| "loss": 2.2564, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09433962264150944, | |
| "grad_norm": 0.08199393883574592, | |
| "learning_rate": 4.9797526533032945e-05, | |
| "loss": 2.325, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09703504043126684, | |
| "grad_norm": 0.08525060108567321, | |
| "learning_rate": 4.976967787416565e-05, | |
| "loss": 2.08, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09973045822102426, | |
| "grad_norm": 0.08829832243395126, | |
| "learning_rate": 4.974004520832223e-05, | |
| "loss": 2.3272, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10242587601078167, | |
| "grad_norm": 0.0805993575215856, | |
| "learning_rate": 4.970863090935304e-05, | |
| "loss": 2.4375, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10242587601078167, | |
| "eval_loss": 2.4220809936523438, | |
| "eval_runtime": 109.7313, | |
| "eval_samples_per_second": 0.729, | |
| "eval_steps_per_second": 0.182, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10512129380053908, | |
| "grad_norm": 0.07362914307313682, | |
| "learning_rate": 4.967543749383371e-05, | |
| "loss": 2.5666, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1078167115902965, | |
| "grad_norm": 0.07781163135663244, | |
| "learning_rate": 4.9640467620863526e-05, | |
| "loss": 2.3806, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1105121293800539, | |
| "grad_norm": 0.07965171973675265, | |
| "learning_rate": 4.9603724091852456e-05, | |
| "loss": 2.3914, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11320754716981132, | |
| "grad_norm": 0.0769658349876996, | |
| "learning_rate": 4.95652098502967e-05, | |
| "loss": 2.3622, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11590296495956873, | |
| "grad_norm": 0.07123531103603928, | |
| "learning_rate": 4.952492798154287e-05, | |
| "loss": 2.4497, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11859838274932614, | |
| "grad_norm": 0.08376895847589426, | |
| "learning_rate": 4.948288171254089e-05, | |
| "loss": 2.2966, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12129380053908356, | |
| "grad_norm": 0.06991588614283951, | |
| "learning_rate": 4.9439074411585406e-05, | |
| "loss": 2.6397, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12398921832884097, | |
| "grad_norm": 0.07115181837614266, | |
| "learning_rate": 4.9393509588046036e-05, | |
| "loss": 2.3112, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12668463611859837, | |
| "grad_norm": 0.12069809526368983, | |
| "learning_rate": 4.9346190892086174e-05, | |
| "loss": 2.6053, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1293800539083558, | |
| "grad_norm": 0.08358966882474354, | |
| "learning_rate": 4.9297122114370596e-05, | |
| "loss": 2.3594, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1320754716981132, | |
| "grad_norm": 0.07439368303284428, | |
| "learning_rate": 4.9246307185761815e-05, | |
| "loss": 2.3608, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1347708894878706, | |
| "grad_norm": 0.07077366564222114, | |
| "learning_rate": 4.919375017700515e-05, | |
| "loss": 2.1389, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13746630727762804, | |
| "grad_norm": 0.0786367422272597, | |
| "learning_rate": 4.9139455298402656e-05, | |
| "loss": 2.3726, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14016172506738545, | |
| "grad_norm": 0.07772287420711031, | |
| "learning_rate": 4.908342689947581e-05, | |
| "loss": 2.6495, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.09095569172141003, | |
| "learning_rate": 4.902566946861708e-05, | |
| "loss": 2.3952, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.14555256064690028, | |
| "grad_norm": 0.08022908718012228, | |
| "learning_rate": 4.8966187632730356e-05, | |
| "loss": 2.2133, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.14824797843665768, | |
| "grad_norm": 0.08853617116138855, | |
| "learning_rate": 4.8904986156860346e-05, | |
| "loss": 2.2795, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 0.08155234218395907, | |
| "learning_rate": 4.884206994381078e-05, | |
| "loss": 2.6322, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.15363881401617252, | |
| "grad_norm": 0.07017826282717579, | |
| "learning_rate": 4.877744403375168e-05, | |
| "loss": 2.36, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.15633423180592992, | |
| "grad_norm": 0.07787943384594204, | |
| "learning_rate": 4.871111360381562e-05, | |
| "loss": 2.4609, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.15902964959568733, | |
| "grad_norm": 0.074730895279447, | |
| "learning_rate": 4.864308396768294e-05, | |
| "loss": 2.3737, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.16172506738544473, | |
| "grad_norm": 0.0754808721924062, | |
| "learning_rate": 4.857336057515611e-05, | |
| "loss": 2.4353, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16442048517520216, | |
| "grad_norm": 0.17074429587919648, | |
| "learning_rate": 4.8501949011723144e-05, | |
| "loss": 2.3747, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.16711590296495957, | |
| "grad_norm": 0.12258858526490496, | |
| "learning_rate": 4.842885499811012e-05, | |
| "loss": 2.3253, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.16981132075471697, | |
| "grad_norm": 0.08223383099932692, | |
| "learning_rate": 4.835408438982294e-05, | |
| "loss": 2.5312, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1725067385444744, | |
| "grad_norm": 0.11131907859034289, | |
| "learning_rate": 4.827764317667825e-05, | |
| "loss": 2.6191, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1752021563342318, | |
| "grad_norm": 0.06793561987591092, | |
| "learning_rate": 4.8199537482323545e-05, | |
| "loss": 2.4681, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1778975741239892, | |
| "grad_norm": 0.07850381171278048, | |
| "learning_rate": 4.811977356374667e-05, | |
| "loss": 2.4868, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.18059299191374664, | |
| "grad_norm": 0.08512994202655803, | |
| "learning_rate": 4.803835781077455e-05, | |
| "loss": 2.6481, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.18328840970350405, | |
| "grad_norm": 0.0846518039690973, | |
| "learning_rate": 4.795529674556129e-05, | |
| "loss": 2.4295, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.18598382749326145, | |
| "grad_norm": 0.08031185133795576, | |
| "learning_rate": 4.7870597022065724e-05, | |
| "loss": 2.4132, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.18867924528301888, | |
| "grad_norm": 0.11316780608440431, | |
| "learning_rate": 4.7784265425518365e-05, | |
| "loss": 2.4341, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.19137466307277629, | |
| "grad_norm": 0.0781705228710772, | |
| "learning_rate": 4.769630887187782e-05, | |
| "loss": 2.4258, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1940700808625337, | |
| "grad_norm": 0.09475565364886825, | |
| "learning_rate": 4.760673440727678e-05, | |
| "loss": 2.6535, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1967654986522911, | |
| "grad_norm": 0.0936468075339049, | |
| "learning_rate": 4.751554920745755e-05, | |
| "loss": 2.4902, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.19946091644204852, | |
| "grad_norm": 0.07028228522733242, | |
| "learning_rate": 4.7422760577197226e-05, | |
| "loss": 2.3132, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.20215633423180593, | |
| "grad_norm": 0.087359632341199, | |
| "learning_rate": 4.7328375949722476e-05, | |
| "loss": 2.3678, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.20485175202156333, | |
| "grad_norm": 0.07567735863088498, | |
| "learning_rate": 4.72324028861141e-05, | |
| "loss": 2.5361, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.20485175202156333, | |
| "eval_loss": 2.409113645553589, | |
| "eval_runtime": 109.4094, | |
| "eval_samples_per_second": 0.731, | |
| "eval_steps_per_second": 0.183, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.20754716981132076, | |
| "grad_norm": 0.0806053756655779, | |
| "learning_rate": 4.713484907470133e-05, | |
| "loss": 2.4361, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.21024258760107817, | |
| "grad_norm": 0.08462062433959809, | |
| "learning_rate": 4.7035722330445857e-05, | |
| "loss": 2.5358, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.21293800539083557, | |
| "grad_norm": 0.08211420166838714, | |
| "learning_rate": 4.693503059431588e-05, | |
| "loss": 2.3083, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.215633423180593, | |
| "grad_norm": 0.07226082893047459, | |
| "learning_rate": 4.6832781932649884e-05, | |
| "loss": 2.468, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2183288409703504, | |
| "grad_norm": 0.08491650207069548, | |
| "learning_rate": 4.6728984536510454e-05, | |
| "loss": 2.436, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2210242587601078, | |
| "grad_norm": 0.07893280409193093, | |
| "learning_rate": 4.662364672102817e-05, | |
| "loss": 2.3986, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.22371967654986524, | |
| "grad_norm": 0.08530475722783892, | |
| "learning_rate": 4.651677692473538e-05, | |
| "loss": 2.5171, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.22641509433962265, | |
| "grad_norm": 0.0782081304914248, | |
| "learning_rate": 4.640838370889029e-05, | |
| "loss": 2.4167, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.22911051212938005, | |
| "grad_norm": 0.09010839515008441, | |
| "learning_rate": 4.629847575679107e-05, | |
| "loss": 2.3621, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.23180592991913745, | |
| "grad_norm": 0.08429756465698064, | |
| "learning_rate": 4.6187061873080264e-05, | |
| "loss": 2.5409, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.23450134770889489, | |
| "grad_norm": 0.08174597825553892, | |
| "learning_rate": 4.607415098303945e-05, | |
| "loss": 2.3467, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2371967654986523, | |
| "grad_norm": 0.08048024256086499, | |
| "learning_rate": 4.5959752131874263e-05, | |
| "loss": 2.5402, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2398921832884097, | |
| "grad_norm": 0.07839092789606332, | |
| "learning_rate": 4.5843874483989746e-05, | |
| "loss": 2.2092, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.24258760107816713, | |
| "grad_norm": 0.08207450024743052, | |
| "learning_rate": 4.572652732225625e-05, | |
| "loss": 2.4616, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.24528301886792453, | |
| "grad_norm": 0.08180483750519887, | |
| "learning_rate": 4.560772004726575e-05, | |
| "loss": 2.4805, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.24797843665768193, | |
| "grad_norm": 0.09232170138763231, | |
| "learning_rate": 4.548746217657878e-05, | |
| "loss": 2.4803, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.25067385444743934, | |
| "grad_norm": 0.08251617231525912, | |
| "learning_rate": 4.5365763343962005e-05, | |
| "loss": 2.3035, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.25336927223719674, | |
| "grad_norm": 0.08840722457592919, | |
| "learning_rate": 4.524263329861644e-05, | |
| "loss": 2.4107, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2560646900269542, | |
| "grad_norm": 0.08098547429953781, | |
| "learning_rate": 4.5118081904396504e-05, | |
| "loss": 2.5351, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2587601078167116, | |
| "grad_norm": 0.09582643101903592, | |
| "learning_rate": 4.499211913901974e-05, | |
| "loss": 2.3998, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.261455525606469, | |
| "grad_norm": 0.09325977474372174, | |
| "learning_rate": 4.486475509326759e-05, | |
| "loss": 2.6805, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.2641509433962264, | |
| "grad_norm": 0.08869290989815509, | |
| "learning_rate": 4.473599997017701e-05, | |
| "loss": 2.384, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2668463611859838, | |
| "grad_norm": 0.07911227872845064, | |
| "learning_rate": 4.460586408422308e-05, | |
| "loss": 2.4893, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2695417789757412, | |
| "grad_norm": 0.08301640398701123, | |
| "learning_rate": 4.447435786049278e-05, | |
| "loss": 2.4671, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2722371967654987, | |
| "grad_norm": 0.0959773217992077, | |
| "learning_rate": 4.434149183384977e-05, | |
| "loss": 2.5863, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.2749326145552561, | |
| "grad_norm": 0.07951557525414293, | |
| "learning_rate": 4.420727664809053e-05, | |
| "loss": 2.552, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.2776280323450135, | |
| "grad_norm": 0.07489545345156162, | |
| "learning_rate": 4.407172305509158e-05, | |
| "loss": 2.3026, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.2803234501347709, | |
| "grad_norm": 0.08339425757380002, | |
| "learning_rate": 4.3934841913948323e-05, | |
| "loss": 2.3962, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2830188679245283, | |
| "grad_norm": 0.09366852913157536, | |
| "learning_rate": 4.379664419010496e-05, | |
| "loss": 2.364, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.07982165605990695, | |
| "learning_rate": 4.3657140954476165e-05, | |
| "loss": 2.4098, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.2884097035040431, | |
| "grad_norm": 0.10046638975690705, | |
| "learning_rate": 4.351634338256017e-05, | |
| "loss": 2.3549, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.29110512129380056, | |
| "grad_norm": 0.08495800159851925, | |
| "learning_rate": 4.337426275354348e-05, | |
| "loss": 2.3466, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.29380053908355797, | |
| "grad_norm": 0.08176244120225214, | |
| "learning_rate": 4.323091044939736e-05, | |
| "loss": 2.4374, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.29649595687331537, | |
| "grad_norm": 0.0766986612060137, | |
| "learning_rate": 4.308629795396599e-05, | |
| "loss": 2.3918, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2991913746630728, | |
| "grad_norm": 0.08318997009881038, | |
| "learning_rate": 4.294043685204651e-05, | |
| "loss": 2.1499, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 0.09128600009973836, | |
| "learning_rate": 4.2793338828460984e-05, | |
| "loss": 2.3912, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.3045822102425876, | |
| "grad_norm": 0.07755181417221228, | |
| "learning_rate": 4.264501566712033e-05, | |
| "loss": 2.5428, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.30727762803234504, | |
| "grad_norm": 0.07626744119606738, | |
| "learning_rate": 4.249547925008033e-05, | |
| "loss": 2.3882, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.30727762803234504, | |
| "eval_loss": 2.4033055305480957, | |
| "eval_runtime": 108.7319, | |
| "eval_samples_per_second": 0.736, | |
| "eval_steps_per_second": 0.184, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.30997304582210244, | |
| "grad_norm": 0.10404280937654081, | |
| "learning_rate": 4.234474155658974e-05, | |
| "loss": 2.4894, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.31266846361185985, | |
| "grad_norm": 0.08349137443478906, | |
| "learning_rate": 4.219281466213066e-05, | |
| "loss": 2.3636, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.31536388140161725, | |
| "grad_norm": 0.09717978095378631, | |
| "learning_rate": 4.203971073745122e-05, | |
| "loss": 2.4826, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.31805929919137466, | |
| "grad_norm": 0.08810095937170669, | |
| "learning_rate": 4.188544204759048e-05, | |
| "loss": 2.5296, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.32075471698113206, | |
| "grad_norm": 0.09443980051741153, | |
| "learning_rate": 4.173002095089599e-05, | |
| "loss": 2.2018, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.32345013477088946, | |
| "grad_norm": 0.09464431143756959, | |
| "learning_rate": 4.157345989803375e-05, | |
| "loss": 2.4329, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3261455525606469, | |
| "grad_norm": 0.0921167133236036, | |
| "learning_rate": 4.141577143099074e-05, | |
| "loss": 2.411, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3288409703504043, | |
| "grad_norm": 0.09102913953050058, | |
| "learning_rate": 4.1256968182070275e-05, | |
| "loss": 2.6301, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.33153638814016173, | |
| "grad_norm": 0.09442024128701812, | |
| "learning_rate": 4.109706287287998e-05, | |
| "loss": 2.2963, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.33423180592991913, | |
| "grad_norm": 0.09048360971081038, | |
| "learning_rate": 4.093606831331269e-05, | |
| "loss": 2.3533, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.33692722371967654, | |
| "grad_norm": 0.09958454863765234, | |
| "learning_rate": 4.077399740052027e-05, | |
| "loss": 2.5592, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.33962264150943394, | |
| "grad_norm": 0.10352388511166186, | |
| "learning_rate": 4.06108631178804e-05, | |
| "loss": 2.5035, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3423180592991914, | |
| "grad_norm": 0.09119254602507475, | |
| "learning_rate": 4.044667853395655e-05, | |
| "loss": 2.3612, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.3450134770889488, | |
| "grad_norm": 0.11817603428015877, | |
| "learning_rate": 4.0281456801451004e-05, | |
| "loss": 2.3564, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3477088948787062, | |
| "grad_norm": 0.08282970624160388, | |
| "learning_rate": 4.011521115615123e-05, | |
| "loss": 2.3187, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.3504043126684636, | |
| "grad_norm": 0.09138997506736304, | |
| "learning_rate": 3.9947954915869565e-05, | |
| "loss": 2.4211, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.353099730458221, | |
| "grad_norm": 0.10315874858803445, | |
| "learning_rate": 3.977970147937635e-05, | |
| "loss": 2.4255, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.3557951482479784, | |
| "grad_norm": 0.12324355580259778, | |
| "learning_rate": 3.961046432532659e-05, | |
| "loss": 2.4149, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.3584905660377358, | |
| "grad_norm": 0.07993016245985274, | |
| "learning_rate": 3.944025701118009e-05, | |
| "loss": 2.1721, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.3611859838274933, | |
| "grad_norm": 0.08795688215451386, | |
| "learning_rate": 3.9269093172115496e-05, | |
| "loss": 2.3163, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3638814016172507, | |
| "grad_norm": 0.08804534236891878, | |
| "learning_rate": 3.9096986519937924e-05, | |
| "loss": 2.3146, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3665768194070081, | |
| "grad_norm": 0.08147499851736127, | |
| "learning_rate": 3.892395084198053e-05, | |
| "loss": 2.4056, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.3692722371967655, | |
| "grad_norm": 0.08190511447175075, | |
| "learning_rate": 3.875e-05, | |
| "loss": 2.3873, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.3719676549865229, | |
| "grad_norm": 0.10702441021155629, | |
| "learning_rate": 3.857514792906616e-05, | |
| "loss": 2.643, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3746630727762803, | |
| "grad_norm": 0.0785708035522026, | |
| "learning_rate": 3.839940863644556e-05, | |
| "loss": 2.5635, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 0.09362896847049527, | |
| "learning_rate": 3.822279620047943e-05, | |
| "loss": 2.377, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.38005390835579517, | |
| "grad_norm": 0.09794943329180347, | |
| "learning_rate": 3.8045324769455834e-05, | |
| "loss": 2.5292, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.38274932614555257, | |
| "grad_norm": 0.0906842624325085, | |
| "learning_rate": 3.78670085604763e-05, | |
| "loss": 2.3576, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.38544474393531, | |
| "grad_norm": 0.09335279764944357, | |
| "learning_rate": 3.7687861858316844e-05, | |
| "loss": 2.1434, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.3881401617250674, | |
| "grad_norm": 0.11106908056412888, | |
| "learning_rate": 3.7507899014283684e-05, | |
| "loss": 2.2124, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3908355795148248, | |
| "grad_norm": 0.10748379262846679, | |
| "learning_rate": 3.732713444506354e-05, | |
| "loss": 2.4934, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3935309973045822, | |
| "grad_norm": 0.08611757548383629, | |
| "learning_rate": 3.714558263156872e-05, | |
| "loss": 2.2559, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.39622641509433965, | |
| "grad_norm": 0.08579591203817094, | |
| "learning_rate": 3.696325811777709e-05, | |
| "loss": 2.3151, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.39892183288409705, | |
| "grad_norm": 0.08307902702869267, | |
| "learning_rate": 3.678017550956692e-05, | |
| "loss": 2.3902, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.40161725067385445, | |
| "grad_norm": 0.0915570030354968, | |
| "learning_rate": 3.659634947354686e-05, | |
| "loss": 2.223, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.40431266846361186, | |
| "grad_norm": 0.07897467847137554, | |
| "learning_rate": 3.6411794735881035e-05, | |
| "loss": 2.3241, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 371, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 75, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 24793369804800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |