| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04019846943066185, | |
| "eval_steps": 500, | |
| "global_step": 239, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016819443276427552, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.2492, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033638886552855103, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005045832982928265, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006727777310571021, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008409721638213775, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001009166596585653, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011773610293499286, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013455554621142041, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015137498948784795, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001681944327642755, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018501387604070306, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002018333193171306, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021865276259355813, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002354722058699857, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025229164914641325, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026911109242284082, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028593053569926836, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003027499789756959, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0031956942225212347, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00336388865528551, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035320830880497854, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0037002775208140612, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0038684719535783366, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004036666386342612, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004204860819106888, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004373055251871163, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004541249684635438, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004709444117399714, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00487763855016399, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005045832982928265, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005214027415692541, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0053822218484568165, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005550416281221091, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005718610713985367, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005886805146749643, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006054999579513918, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006223194012278194, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0063913884450424695, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006559582877806744, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00672777731057102, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006895971743335296, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007064166176099571, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007232360608863847, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0074005550416281225, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007568749474392397, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007736943907156673, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007905138339920948, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008073332772685224, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0082415272054495, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008409721638213775, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008577916070978051, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008746110503742325, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.008914304936506601, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.300000000000001e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.009082499369270877, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.009250693802035153, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009418888234799428, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009587082667563704, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6999999999999996e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00975527710032798, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.009923471533092254, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.01009166596585653, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010259860398620806, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.1e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.010428054831385081, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.010596249264149357, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.3e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.010764443696913633, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.010932638129677907, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.011100832562442183, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.011269026995206459, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.011437221427970734, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.01160541586073501, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.9e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.011773610293499286, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01194180472626356, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.1e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.012109999159027836, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.012278193591792112, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.012446388024556387, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.012614582457320663, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.012782776890084939, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.012950971322849213, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.7e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.013119165755613489, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.013287360188377765, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.01345555462114204, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013623749053906316, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.1e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.013791943486670592, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.013960137919434866, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.3e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.014128332352199142, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.014296526784963418, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.014464721217727693, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.014632915650491969, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.7e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.014801110083256245, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.014969304516020519, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.015137498948784795, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01530569338154907, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.1e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.015473887814313346, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.01564208224707762, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.300000000000001e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.015810276679841896, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.015978471112606172, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.016146665545370448, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.016314859978134724, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.7e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.016483054410899, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.016651248843663275, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.01681944327642755, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016987637709191827, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999999277778003e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.017155832141956102, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999997111112216e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.017324026574720378, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999993500003267e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.01749222100748465, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999988444452199e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.017660415440248926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999981944460473e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.017828609873013202, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999974000029966e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.017996804305777478, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999964611162974e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.018164998738541754, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999953777862207e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.01833319317130603, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999941500130797e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.018501387604070305, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99992777797229e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01866958203683458, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999912611390651e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.018837776469598857, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999896000390261e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.019005970902363133, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999877944975917e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.01917416533512741, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999858445152839e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.019342359767891684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999837500926656e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.01951055420065596, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99981511230342e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.019678748633420232, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999791279289601e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.019846943066184508, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999766001892081e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.020015137498948784, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999739280118163e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.02018333193171306, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999711113975568e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.020351526364477335, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999681503472433e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.02051972079724161, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99965044861731e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.020687915230005887, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999617949419174e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.020856109662770163, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999584005887407e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.02102430409553444, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999548618031823e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.021192498528298714, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99951178586264e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.02136069296106299, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.9994735093905e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.021528887393827266, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999433788626461e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.02169708182659154, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999392623581997e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.021865276259355814, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999350014269e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02203347069212009, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999305960699781e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.022201665124884366, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999260462887064e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.02236985955764864, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999213520843994e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.022538053990412917, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999165134584133e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.022706248423177193, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999115304121457e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02287444285594147, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999064029470366e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.023042637288705745, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999011310645668e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.02321083172147002, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998957147662594e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.023379026154234296, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998901540536792e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.023547220586998572, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998844489284327e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.023715415019762844, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998785993921678e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.02388360945252712, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998726054465744e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.024051803885291396, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998664670933844e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.02421999831805567, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998601843343707e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.024388192750819947, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998537571713487e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.024556387183584223, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998471856061747e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.0247245816163485, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998404696407476e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.024892776049112775, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998336092770073e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.02506097048187705, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998266045169356e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.025229164914641326, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998194553625563e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.025397359347405602, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998121618159346e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.025565553780169878, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998047238791777e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.02573374821293415, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997971415544341e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.025901942645698426, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997894148438944e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.026070137078462702, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997815437497908e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.026238331511226978, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997735282743969e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.026406525943991253, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997653684200286e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.02657472037675553, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99757064189043e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.026742914809519805, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997486155838392e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.02691110924228408, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997400226068578e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.027079303675048357, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997312852605814e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.027247498107812632, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997224035475339e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.027415692540576908, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997133774702812e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.027583886973341184, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.997042070314309e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.027752081406105456, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996948922336323e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.027920275838869732, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996854330795761e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.028088470271634008, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996758295719951e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.028256664704398284, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996660817136636e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.02842485913716256, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996561895073976e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.028593053569926835, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996461529560553e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02876124800269111, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996359720625354e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.028929442435455387, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996256468297795e-05, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.029097636868219662, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996151772607704e-05, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.029265831300983938, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996045633585326e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.029434025733748214, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995938051261324e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02960222016651249, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995829025666775e-05, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.029770414599276766, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995718556833178e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.029938609032041038, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995606644792446e-05, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.030106803464805314, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995493289576907e-05, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.03027499789756959, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99537849121931e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.030443192330333865, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995262249752817e-05, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.03061138676309814, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995144565211012e-05, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.030779581195862417, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99502543762789e-05, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.030947775628626693, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994904867037867e-05, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.03111597006139097, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994782853475774e-05, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03128416449415524, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994659396976859e-05, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.03145235892691952, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994534497576787e-05, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.03162055335968379, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994408155311642e-05, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.03178874779244807, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994280370217922e-05, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.031956942225212344, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99415114233254e-05, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03212513665797662, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.994020471692833e-05, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.032293331090740895, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993888358336545e-05, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.032461525523505175, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993754802301847e-05, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.03262971995626945, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993619803627321e-05, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.032797914389033726, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993483362351963e-05, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.032966108821798, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993345478515194e-05, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.03313430325456227, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993206152156844e-05, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.03330249768732655, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993065383317163e-05, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.03347069212009082, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992923172036819e-05, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.0336388865528551, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992779518356896e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.033807080985619374, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99263442231889e-05, | |
| "loss": 0.0, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.03397527541838365, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99248788396472e-05, | |
| "loss": 0.0, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.034143469851147926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992339903336722e-05, | |
| "loss": 0.0, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.034311664283912205, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992190480477641e-05, | |
| "loss": 0.0, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.03447985871667648, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.992039615430648e-05, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.034648053149440756, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991887308239322e-05, | |
| "loss": 0.0, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.03481624758220503, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991733558947667e-05, | |
| "loss": 0.0, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.0349844420149693, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991578367600096e-05, | |
| "loss": 0.0, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.03515263644773358, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991421734241444e-05, | |
| "loss": 0.0, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.03532083088049785, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99126365891696e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.03548902531326213, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991104141672309e-05, | |
| "loss": 0.0, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.035657219746026404, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990943182553579e-05, | |
| "loss": 0.0, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.035825414178790684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990780781607261e-05, | |
| "loss": 0.0, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.035993608611554956, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990616938880278e-05, | |
| "loss": 0.0, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.036161803044319235, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990451654419957e-05, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.03632999747708351, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990284928274051e-05, | |
| "loss": 0.0, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.03649819190984779, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990116760490723e-05, | |
| "loss": 0.0, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.03666638634261206, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989947151118555e-05, | |
| "loss": 0.0, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.03683458077537634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989776100206548e-05, | |
| "loss": 0.0, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.03700277520814061, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989603607804112e-05, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.03717096964090488, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98942967396108e-05, | |
| "loss": 0.0, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.03733916407366916, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989254298727702e-05, | |
| "loss": 0.0, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.037507358506433434, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.989077482154638e-05, | |
| "loss": 0.0, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.037675552939197714, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988899224292971e-05, | |
| "loss": 0.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.037843747371961986, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988719525194198e-05, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.038011941804726265, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988538384910231e-05, | |
| "loss": 0.0, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.03818013623749054, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988355803493398e-05, | |
| "loss": 0.0, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.03834833067025482, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988171780996446e-05, | |
| "loss": 0.0, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.03851652510301909, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987986317472539e-05, | |
| "loss": 0.0, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.03868471953578337, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987799412975252e-05, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.03885291396854764, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987611067558582e-05, | |
| "loss": 0.0, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.03902110840131192, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987421281276939e-05, | |
| "loss": 0.0, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.03918930283407619, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.98723005418515e-05, | |
| "loss": 0.0, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.039357497266840465, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987037386338458e-05, | |
| "loss": 0.0, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.039525691699604744, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986843277792523e-05, | |
| "loss": 0.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.039693886132369016, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986647728603422e-05, | |
| "loss": 0.0, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.039862080565133295, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986450738827646e-05, | |
| "loss": 0.0, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.04003027499789757, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986252308522101e-05, | |
| "loss": 0.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.04019846943066185, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986052437744115e-05, | |
| "loss": 0.0, | |
| "step": 239 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5945, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 239, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4501042330337280.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |