| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016931790282845556, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6931790282845557e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.6931790282845557e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1940.2475, | |
| "eval_samples_per_second": 25.633, | |
| "eval_steps_per_second": 3.204, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.3863580565691114e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.079537084853667e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.772716113138223e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.465895141422778e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010159074169707334, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001185225319799189, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00013545432226276446, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015238611254561, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00015238611254561, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1939.6486, | |
| "eval_samples_per_second": 25.641, | |
| "eval_steps_per_second": 3.205, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016931790282845557, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001862496931113011, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.999390827019096e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00020318148339414668, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00022011327367699223, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0002370450639598378, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00025397685424268337, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002709086445255289, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00028784043480837445, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00030477222509122, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00030477222509122, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1956.0542, | |
| "eval_samples_per_second": 25.426, | |
| "eval_steps_per_second": 3.178, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0003217040153740656, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00033863580565691114, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003555675959397567, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9271838545667876e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0003724993862226022, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0003894311765054478, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8987940462991673e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00040636296678829337, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004232947570711389, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00044022654735398445, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.848048096156426e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00045715833763683005, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8290375725550417e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00045715833763683005, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1939.2011, | |
| "eval_samples_per_second": 25.647, | |
| "eval_steps_per_second": 3.206, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0004740901279196756, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0004910219182025212, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.788010753606722e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0005079537084853667, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005248854987682123, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0005418172890510578, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0005587490793339034, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6946583704589973e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0005756808696167489, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0005926126598995945, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00060954445018244, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6156614753256583e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00060954445018244, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1939.6183, | |
| "eval_samples_per_second": 25.642, | |
| "eval_steps_per_second": 3.205, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0006264762404652856, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0006434080307481312, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5591929034707468e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0006603398210309767, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.529919264233205e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0006772716113138223, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006942034015966678, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.469471562785891e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0007111351918795134, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4383711467890776e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0007280669821623589, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0007449987724452045, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3746065934159123e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0007619305627280501, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0007619305627280501, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1938.6726, | |
| "eval_samples_per_second": 25.654, | |
| "eval_steps_per_second": 3.207, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0007788623530108956, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0007957941432937412, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2756373558169992e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0008127259335765867, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2419218955996677e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0008296577238594323, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0008465895141422778, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008635213044251234, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1391731009600655e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0008804530947079689, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0008973848849908146, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0697564737441254e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0009143166752736601, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0348994967025012e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0009143166752736601, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1939.1845, | |
| "eval_samples_per_second": 25.647, | |
| "eval_steps_per_second": 3.206, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0009312484655565056, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0009481802558393512, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.651005032974994e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0009651120461221967, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.302435262558748e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0009820438364050424, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0009989756266878878, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.60826899039935e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0010159074169707335, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.001032839207253579, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.92088309182241e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0010497709975364246, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.580781044003324e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.00106670278781927, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.243626441830009e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.00106670278781927, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1939.9054, | |
| "eval_samples_per_second": 25.638, | |
| "eval_steps_per_second": 3.205, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0010836345781021156, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.001100566368384961, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0011174981586678067, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.25393406584088e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0011344299489506524, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0011513617392334978, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.616288532109225e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0011682935295163435, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.305284372141095e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.001185225319799189, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0012021571100820346, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.700807357667953e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.00121908890036488, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.408070965292534e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.00121908890036488, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1939.3736, | |
| "eval_samples_per_second": 25.645, | |
| "eval_steps_per_second": 3.206, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0012360206906477256, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0012529524809305713, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8433852467434175e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0012698842712134167, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346067e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0012868160614962624, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0013037478517791078, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0534162954100264e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0013206796420619535, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8066019966134907e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.001337611432344799, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5685517452260566e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0013545432226276446, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00137147501291049, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.119892463932781e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.00137147501291049, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1938.6889, | |
| "eval_samples_per_second": 25.654, | |
| "eval_steps_per_second": 3.207, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0013884068031933356, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0014053385934761813, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.709624274449584e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.0014222703837590267, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5195190384357405e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0014392021740418724, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0014561339643247178, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1705240714107301e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0014730657546075635, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.012059537008332e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.001489997544890409, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.0015069293351732546, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.281614543321269e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.0015238611254561002, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0015238611254561002, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1940.5626, | |
| "eval_samples_per_second": 25.629, | |
| "eval_steps_per_second": 3.204, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0015407929157389456, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.894348370484648e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0015577247060217913, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8738304061681107e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.0015746564963046367, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.970427372400353e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0015915882865874824, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0016085200768703278, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.519224698779198e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0016254518671531735, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.731931258429638e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.001642383657436019, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4781046317267103e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0016593154477188646, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4359497401758026e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0016762472380017102, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.091729809042379e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0016762472380017102, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1940.5881, | |
| "eval_samples_per_second": 25.629, | |
| "eval_steps_per_second": 3.204, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0016931790282845556, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 1.30626883682304e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |