| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.037285607755406416, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003728560775540641, | |
| "grad_norm": 3.400036334991455, | |
| "learning_rate": 1e-05, | |
| "loss": 3.4355, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003728560775540641, | |
| "eval_loss": 1.8008577823638916, | |
| "eval_runtime": 349.3017, | |
| "eval_samples_per_second": 6.467, | |
| "eval_steps_per_second": 0.81, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007457121551081282, | |
| "grad_norm": 4.2858076095581055, | |
| "learning_rate": 2e-05, | |
| "loss": 4.0185, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011185682326621924, | |
| "grad_norm": 3.335254430770874, | |
| "learning_rate": 3e-05, | |
| "loss": 3.5495, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014914243102162564, | |
| "grad_norm": 3.5243070125579834, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4225, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018642803877703207, | |
| "grad_norm": 4.728586196899414, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6481, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022371364653243847, | |
| "grad_norm": 3.8031859397888184, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4865, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002609992542878449, | |
| "grad_norm": 11.639005661010742, | |
| "learning_rate": 7e-05, | |
| "loss": 3.2582, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002982848620432513, | |
| "grad_norm": 5.1528000831604, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0674, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003355704697986577, | |
| "grad_norm": 12.328182220458984, | |
| "learning_rate": 9e-05, | |
| "loss": 2.5484, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003355704697986577, | |
| "eval_loss": 1.220103144645691, | |
| "eval_runtime": 349.7658, | |
| "eval_samples_per_second": 6.459, | |
| "eval_steps_per_second": 0.809, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0037285607755406414, | |
| "grad_norm": 4.333200454711914, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5652, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004101416853094705, | |
| "grad_norm": 3.977302074432373, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.278, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0044742729306487695, | |
| "grad_norm": 4.763873100280762, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.9624, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004847129008202834, | |
| "grad_norm": 4.223742485046387, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.7555, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005219985085756898, | |
| "grad_norm": 3.9444894790649414, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.403, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005592841163310962, | |
| "grad_norm": 4.593219757080078, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.1754, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005965697240865026, | |
| "grad_norm": 4.044795036315918, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.2341, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00633855331841909, | |
| "grad_norm": 4.35222864151001, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.1048, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006711409395973154, | |
| "grad_norm": 8.187066078186035, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.2336, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006711409395973154, | |
| "eval_loss": 0.48964816331863403, | |
| "eval_runtime": 349.804, | |
| "eval_samples_per_second": 6.458, | |
| "eval_steps_per_second": 0.809, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0070842654735272185, | |
| "grad_norm": 3.0137736797332764, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.7896, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007457121551081283, | |
| "grad_norm": 3.497110366821289, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.7636, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007829977628635347, | |
| "grad_norm": 2.9445033073425293, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.844, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00820283370618941, | |
| "grad_norm": 3.898838758468628, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.6927, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008575689783743476, | |
| "grad_norm": 4.304202079772949, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.9142, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008948545861297539, | |
| "grad_norm": 2.6437668800354004, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.6335, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009321401938851604, | |
| "grad_norm": 2.6280505657196045, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7345, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009694258016405667, | |
| "grad_norm": 3.5108931064605713, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.7697, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010067114093959731, | |
| "grad_norm": 2.786745071411133, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.6532, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010067114093959731, | |
| "eval_loss": 0.3512137532234192, | |
| "eval_runtime": 350.315, | |
| "eval_samples_per_second": 6.448, | |
| "eval_steps_per_second": 0.808, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010439970171513796, | |
| "grad_norm": 2.6744167804718018, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.6797, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01081282624906786, | |
| "grad_norm": 3.1515629291534424, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.8676, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011185682326621925, | |
| "grad_norm": 3.549837350845337, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.8261, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011558538404175988, | |
| "grad_norm": 2.580272912979126, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.6165, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.011931394481730051, | |
| "grad_norm": 2.27457594871521, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.5961, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012304250559284116, | |
| "grad_norm": 2.8076517581939697, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.8511, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01267710663683818, | |
| "grad_norm": 2.766775369644165, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.806, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013049962714392245, | |
| "grad_norm": 2.7165963649749756, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.6111, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013422818791946308, | |
| "grad_norm": 2.5948312282562256, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.5564, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013422818791946308, | |
| "eval_loss": 0.3024395704269409, | |
| "eval_runtime": 349.3108, | |
| "eval_samples_per_second": 6.467, | |
| "eval_steps_per_second": 0.81, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013795674869500374, | |
| "grad_norm": 2.670243501663208, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.5966, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014168530947054437, | |
| "grad_norm": 3.616215467453003, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.6423, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0145413870246085, | |
| "grad_norm": 1.9744212627410889, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.5122, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014914243102162566, | |
| "grad_norm": 1.4423952102661133, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4379, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015287099179716629, | |
| "grad_norm": 2.110400438308716, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 0.5515, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.015659955257270694, | |
| "grad_norm": 3.1135926246643066, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.7945, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01603281133482476, | |
| "grad_norm": 1.5176160335540771, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.3795, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01640566741237882, | |
| "grad_norm": 2.0124406814575195, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.4552, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.016778523489932886, | |
| "grad_norm": 2.7162728309631348, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.5636, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.016778523489932886, | |
| "eval_loss": 0.2751654088497162, | |
| "eval_runtime": 350.8356, | |
| "eval_samples_per_second": 6.439, | |
| "eval_steps_per_second": 0.807, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01715137956748695, | |
| "grad_norm": 3.005157232284546, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.5146, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017524235645041013, | |
| "grad_norm": 2.019146680831909, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.445, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.017897091722595078, | |
| "grad_norm": 3.2905123233795166, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.5227, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018269947800149143, | |
| "grad_norm": 3.0617525577545166, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.5897, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.018642803877703208, | |
| "grad_norm": 1.9802680015563965, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.4494, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01901565995525727, | |
| "grad_norm": 3.13832688331604, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.4998, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.019388516032811335, | |
| "grad_norm": 2.606796979904175, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.4294, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0197613721103654, | |
| "grad_norm": 1.4316664934158325, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 0.3134, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.020134228187919462, | |
| "grad_norm": 2.9197375774383545, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.5238, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020134228187919462, | |
| "eval_loss": 0.25775837898254395, | |
| "eval_runtime": 350.0488, | |
| "eval_samples_per_second": 6.453, | |
| "eval_steps_per_second": 0.808, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.020507084265473527, | |
| "grad_norm": 3.15315842628479, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5633, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.020879940343027592, | |
| "grad_norm": 2.9247982501983643, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.6658, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.021252796420581657, | |
| "grad_norm": 2.133901596069336, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.438, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.02162565249813572, | |
| "grad_norm": 2.133498191833496, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.6451, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.021998508575689784, | |
| "grad_norm": 2.264512300491333, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 0.5505, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.02237136465324385, | |
| "grad_norm": 2.4721152782440186, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.5978, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02274422073079791, | |
| "grad_norm": 3.082334280014038, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.6892, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.023117076808351976, | |
| "grad_norm": 2.7716917991638184, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.5637, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.02348993288590604, | |
| "grad_norm": 2.6146810054779053, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.4898, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02348993288590604, | |
| "eval_loss": 0.24969489872455597, | |
| "eval_runtime": 350.2873, | |
| "eval_samples_per_second": 6.449, | |
| "eval_steps_per_second": 0.808, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.023862788963460103, | |
| "grad_norm": 2.5969202518463135, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.709, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.024235645041014168, | |
| "grad_norm": 2.4878087043762207, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.3157, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.024608501118568233, | |
| "grad_norm": 1.8842146396636963, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.5118, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.024981357196122298, | |
| "grad_norm": 2.019120216369629, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.4453, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.02535421327367636, | |
| "grad_norm": 2.335958480834961, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.5359, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.025727069351230425, | |
| "grad_norm": 2.2405831813812256, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.5027, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.02609992542878449, | |
| "grad_norm": 2.013742446899414, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3056, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02647278150633855, | |
| "grad_norm": 2.631866216659546, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 0.5953, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.026845637583892617, | |
| "grad_norm": 2.1605570316314697, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.5956, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.026845637583892617, | |
| "eval_loss": 0.2442958801984787, | |
| "eval_runtime": 350.3999, | |
| "eval_samples_per_second": 6.447, | |
| "eval_steps_per_second": 0.808, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.027218493661446682, | |
| "grad_norm": 2.751471757888794, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.5849, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.027591349739000747, | |
| "grad_norm": 2.0023796558380127, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.6379, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02796420581655481, | |
| "grad_norm": 2.596499443054199, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.4492, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.028337061894108874, | |
| "grad_norm": 1.6913723945617676, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.434, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.02870991797166294, | |
| "grad_norm": 2.2166502475738525, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 0.4624, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.029082774049217, | |
| "grad_norm": 2.307016372680664, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.4528, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.029455630126771066, | |
| "grad_norm": 1.4767197370529175, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.313, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.02982848620432513, | |
| "grad_norm": 1.578914999961853, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.3833, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.030201342281879196, | |
| "grad_norm": 2.2155160903930664, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.6689, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.030201342281879196, | |
| "eval_loss": 0.239990234375, | |
| "eval_runtime": 349.9999, | |
| "eval_samples_per_second": 6.454, | |
| "eval_steps_per_second": 0.809, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.030574198359433258, | |
| "grad_norm": 2.5915427207946777, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.7203, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.030947054436987323, | |
| "grad_norm": 1.803110122680664, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 0.3907, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.03131991051454139, | |
| "grad_norm": 1.5690308809280396, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.4132, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.03169276659209545, | |
| "grad_norm": 1.8381179571151733, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5006, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03206562266964952, | |
| "grad_norm": 1.5271821022033691, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.3825, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.03243847874720358, | |
| "grad_norm": 2.0599448680877686, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.5317, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.03281133482475764, | |
| "grad_norm": 2.089296817779541, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.5469, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.03318419090231171, | |
| "grad_norm": 1.8208433389663696, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 0.5791, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.03355704697986577, | |
| "grad_norm": 1.7200791835784912, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.2601, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03355704697986577, | |
| "eval_loss": 0.23744842410087585, | |
| "eval_runtime": 349.8893, | |
| "eval_samples_per_second": 6.456, | |
| "eval_steps_per_second": 0.809, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03392990305741984, | |
| "grad_norm": 2.4176998138427734, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.433, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0343027591349739, | |
| "grad_norm": 1.9613291025161743, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.4126, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.03467561521252797, | |
| "grad_norm": 1.3048509359359741, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.3782, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.035048471290082026, | |
| "grad_norm": 3.3364882469177246, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.6363, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.03542132736763609, | |
| "grad_norm": 4.332254409790039, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.3197, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.035794183445190156, | |
| "grad_norm": 1.5083318948745728, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.3794, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.03616703952274422, | |
| "grad_norm": 1.4915975332260132, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.3878, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.036539895600298286, | |
| "grad_norm": 2.383786201477051, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.7089, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.03691275167785235, | |
| "grad_norm": 3.2473056316375732, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.5106, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.03691275167785235, | |
| "eval_loss": 0.23671579360961914, | |
| "eval_runtime": 350.1701, | |
| "eval_samples_per_second": 6.451, | |
| "eval_steps_per_second": 0.808, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.037285607755406416, | |
| "grad_norm": 1.4355666637420654, | |
| "learning_rate": 0.0, | |
| "loss": 0.326, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2695579394048e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |