| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5627857896588111, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005627857896588111, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005627857896588111, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.1466, | |
| "eval_samples_per_second": 6.48, | |
| "eval_steps_per_second": 6.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011255715793176222, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016883573689764335, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-07, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022511431586352444, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.028139289482940557, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03376714737952867, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-07, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03939500527611678, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0500000000000001e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04502286317270489, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.050650721069293, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.35e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.056278578965881114, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06190643686246922, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.65e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06753429475905734, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07316215265564545, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.95e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07879001055223356, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08441786844882167, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09004572634540978, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09567358424199789, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.55e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.101301442138586, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10692930003517412, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8500000000000002e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11255715793176223, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11818501582835034, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.15e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12381287372493845, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12944073162152656, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4500000000000004e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13506858951811468, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14069644741470277, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.75e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1463243053112909, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.151952163207879, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.05e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15758002110446712, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1632078790010552, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.35e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16883573689764333, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17446359479423146, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.65e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18009145269081955, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18571931058740768, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.95e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19134716848399577, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1969750263805839, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.25e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.202602884277172, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2082307421737601, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.55e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.21385860007034824, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7000000000000005e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21948645796693633, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.850000000000001e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22511431586352446, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23074217376011255, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.1499999999999996e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.23637003165670067, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.3e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.24199788955328877, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.45e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2476257474498769, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.253253605346465, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.750000000000001e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2588814632430531, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.900000000000001e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2645093211396412, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.049999999999999e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.27013717903622936, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.27576503693281745, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.35e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.28139289482940555, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28139289482940555, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.5071, | |
| "eval_samples_per_second": 6.381, | |
| "eval_steps_per_second": 6.381, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28702075272599364, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.65e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2926486106225818, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.8e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.2982764685191699, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.95e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.303904326415758, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.1e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.30953218431234614, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.25e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.31516004220893423, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.32078790010552233, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.55e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3264157580021104, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.7e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3320436158986986, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.85e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.33767147379528667, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.34329933169187477, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.15e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3489271895884629, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.3e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.354555047485051, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.450000000000001e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3601829053816391, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3658107632782272, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.75e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.37143862117481535, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.9e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.37706647907140345, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.005e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.38269433696799154, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.02e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3883221948645797, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.035e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3939500527611678, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.05e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3995779106577559, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.065e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.405205768554344, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.08e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.41083362645093213, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.095e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4164614843475202, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.11e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.4220893422441083, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.125e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4277172001406965, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.43334505803728457, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1550000000000001e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.43897291593387266, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1700000000000001e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.44460077383046076, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.185e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.4502286317270489, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.455856489623637, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.215e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4614843475202251, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2299999999999999e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.46711220541681325, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.245e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.47274006331340135, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.26e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.47836792120998944, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.275e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.48399577910657754, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.29e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.4896236370031657, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.305e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.4952514948997538, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.32e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5008793527963419, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3350000000000001e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.50650721069293, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5121350685895181, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3650000000000001e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5177629264861062, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3800000000000002e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5233907843826944, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.395e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.5290186422792824, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4099999999999999e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.5346465001758706, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4249999999999999e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5402743580724587, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.44e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5459022159690468, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.455e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.5515300738656349, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.47e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.5571579317622231, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.485e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5627857896588111, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5627857896588111, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.5076, | |
| "eval_samples_per_second": 6.381, | |
| "eval_steps_per_second": 6.381, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.330495774261248e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |