| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.994579945799458, | |
| "eval_steps": 500, | |
| "global_step": 184, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01084010840108401, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02168021680216802, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.032520325203252036, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04336043360433604, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05420054200542006, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07588075880758807, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08672086720867209, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10840108401084012, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11924119241192412, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14092140921409213, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15176151761517614, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16260162601626016, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17344173441734417, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1842818428184282, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20596205962059622, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21680216802168023, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22764227642276422, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23848238482384823, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24932249322493225, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.27100271002710025, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28184281842818426, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3035230352303523, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3143631436314363, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33604336043360433, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34688346883468835, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.35772357723577236, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3685636856368564, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3794037940379404, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4010840108401084, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.41192411924119243, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.42276422764227645, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.43360433604336046, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45528455284552843, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.46612466124661245, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.47696476964769646, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4986449864498645, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5094850948509485, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5203252032520326, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5311653116531165, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5420054200542005, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5528455284552846, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5636856368563685, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5745257452574526, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.300000000000001e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5962059620596206, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6070460704607046, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6178861788617886, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6287262872628726, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6395663956639567, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6612466124661247, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.1e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6720867208672087, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.3e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6937669376693767, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7046070460704607, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7154471544715447, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7262872628726287, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7371273712737128, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7479674796747967, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.9e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7588075880758808, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7696476964769647, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.1e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7913279132791328, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8021680216802168, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.8130081300813008, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8238482384823849, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8346883468834688, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.7e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8455284552845529, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8563685636856369, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.8672086720867209, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.1e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.8997289972899729, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.3e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9105691056910569, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9214092140921409, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9322493224932249, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.943089430894309, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.7e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9539295392953929, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.964769647696477, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.986449864498645, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.1e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.997289972899729, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.997289972899729, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.9622, | |
| "eval_samples_per_second": 79.505, | |
| "eval_steps_per_second": 19.876, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.008130081300813, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.300000000000001e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.018970189701897, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.029810298102981, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.040650406504065, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.051490514905149, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.7e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.062330623306233, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.084010840108401, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.094850948509485, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996503523941994e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.1056910569105691, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986018985905901e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.1165311653116532, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.127371273712737, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.944154131125642e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.1382113821138211, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.912832366166442e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1490514905149052, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.1598915989159893, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.777864028930705e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.1815718157181572, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.1924119241192412, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.654368743221022e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.203252032520325, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.582811279349882e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.2140921409214092, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.2249322493224932, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.420576967523049e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.2357723577235773, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.2466124661246614, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.2574525745257452, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.131193871579975e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.022988898833342e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.2791327913279134, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.2899728997289972, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.789858615727265e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.3008130081300813, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.665259359149132e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3116531165311653, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.3224932249322494, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.400863688854597e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.261437056390606e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.3441734417344173, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.3550135501355014, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.969100927867507e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.81660029031811e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.3766937669376693, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.3875338753387534, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.3983739837398375, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.33634314136531e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.4092140921409215, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4200542005420054, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.999460121598704e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.4308943089430894, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.826705121831976e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.4417344173441735, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.4525745257452574, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.473775872054521e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.4742547425474255, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.4850948509485096, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9295580358145744e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.4959349593495934, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.745211330880872e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.5067750677506775, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.5176151761517616, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.373650467932122e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.5284552845528454, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.18695597138163e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.5392953929539295, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.5501355013550135, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.813044028618373e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.626349532067879e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.5718157181571817, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.5826558265582655, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.254788669119127e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.5934959349593496, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0704419641854274e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.6043360433604335, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.6151761517615175, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.6260162601626016, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5262241279454785e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6368563685636857, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.6476964769647697, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.173294878168025e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.000539878401296e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.6693766937669376, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.6802168021680217, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.66365685863469e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.6910569105691056, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.7018970189701896, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.7127371273712737, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1833997096818898e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.7235772357723578, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0308990721324927e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.7344173441734418, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.7452574525745257, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.738562943609396e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.599136311145402e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.7669376693766936, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3347406408508695e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.7886178861788617, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2101413842727345e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.7994579945799458, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.8102981029810299, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.770111011666583e-06, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.821138211382114, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.688061284200266e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.8319783197831978, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.8428184281842819, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.794230324769517e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.8644986449864498, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.8753387533875339, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1718872065011904e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.886178861788618, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4563125677897932e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.897018970189702, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.907859078590786, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.221359710692961e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.91869918699187, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.9295392953929538, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.9403794037940378, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.716763383355864e-07, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.584586887435739e-07, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.962059620596206, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.97289972899729, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3981014094099353e-07, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.9837398373983741, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.496476058006959e-08, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.994579945799458, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 184 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 184, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 239, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.369284617535488e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |