| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7960199004975125, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003980099502487562, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003980099502487562, | |
| "eval_loss": NaN, | |
| "eval_runtime": 50.8172, | |
| "eval_samples_per_second": 8.324, | |
| "eval_steps_per_second": 2.086, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007960199004975124, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011940298507462687, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015920398009950248, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01990049751243781, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023880597014925373, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027860696517412936, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.031840796019900496, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03582089552238806, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03980099502487562, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04378109452736319, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001099924817745858, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04776119402985075, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010996992915375093, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.051741293532338306, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010993234830315676, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05572139303482587, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001098797494970326, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010981214711536684, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06368159203980099, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010972955963997563, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06766169154228856, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010963200964945011, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07164179104477612, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010951952381298364, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07562189054726368, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010939213288308077, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07960199004975124, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010924987168714973, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08358208955223881, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010909277911798103, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08756218905472637, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010892089812311451, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09154228855721393, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010873427569309797, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0955223880597015, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010853296284864032, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09950248756218906, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010831701462666318, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10348258706467661, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010808649006525419, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10746268656716418, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010784145218752665, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11144278606965174, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010758196798438968, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1154228855721393, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010730810839623346, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001070199482935349, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12338308457711443, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010671756645638888, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12736318407960198, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010640104555297034, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13134328358208955, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010607047211693389, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13532338308457711, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010572593652375616, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13930348258706468, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010536753296602816, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14328358208955225, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010499535942770394, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1472636815920398, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010460951765731275, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15124378109452735, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000104210113140142, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15522388059701492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010379725506939865, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15920398009950248, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001033710563163569, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16318407960199005, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010293163339950024, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16716417910447762, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010247910645266658, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17114427860696518, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010201359919220464, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17512437810945275, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010153523888315144, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010104415630443907, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18308457711442785, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001005404857131411, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18706467661691542, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010002436480776809, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.191044776119403, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.949593469062211e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19502487562189055, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.895533982922087e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.19900497512437812, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.840272801680165e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19900497512437812, | |
| "eval_loss": NaN, | |
| "eval_runtime": 47.1967, | |
| "eval_samples_per_second": 8.962, | |
| "eval_steps_per_second": 2.246, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20298507462686566, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.783825033191619e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.20696517412935322, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.726206109712725e-05, | |
| "loss": 4.2627, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.2109452736318408, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.667431783681842e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.21492537313432836, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.607518123412847e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.21890547263681592, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.546481508702224e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2228855721393035, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.48433862635099e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.22686567164179106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.421106465602684e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2308457711442786, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.356802313498687e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.23482587064676616, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.291443750152112e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.225048643941577e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2427860696517413, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.157635146626164e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.24676616915422886, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.089221688382928e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2507462686567164, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.019826972768242e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.25472636815920396, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.949469971604454e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.25870646766169153, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.878169919793173e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2626865671641791, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.805946310056638e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.732818887608602e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.27064676616915423, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.65880764475619e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2746268656716418, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.583932815434201e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.27860696517412936, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.50821486967335e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28258706467661693, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.431674508003966e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2865671641791045, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.354332655796683e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.29054726368159206, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.276210457541642e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2945273631840796, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.197329271067796e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.117710661703905e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3024875621890547, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.037376396382784e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.30646766169154227, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.956348437690437e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.31044776119402984, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.87464893786171e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3144278606965174, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.792300232724097e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.31840796019900497, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.709324835591332e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32238805970149254, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.625745431108487e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3263681592039801, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.541584869050213e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.33034825870646767, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.456866158073842e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.33432835820895523, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.371612459429037e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3383084577114428, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.28584708062576e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.34228855721393037, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.19959346906221e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.34626865671641793, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.112875205614558e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.3502487562189055, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.025715998190145e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.354228855721393, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.938139675246009e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.850170179274395e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36218905472636814, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.761831560257134e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3661691542288557, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.673147969090608e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3701492537313433, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.584143650983141e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.37412935323383084, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.494842938826605e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3781094527363184, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.405270246544037e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.382089552238806, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.31545006241513e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.38606965174129354, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.22540694238138e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3900497512437811, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.135165503332725e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3940298507462687, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0447504163775465e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.39800995024875624, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.954186400097829e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39800995024875624, | |
| "eval_loss": NaN, | |
| "eval_runtime": 44.9001, | |
| "eval_samples_per_second": 9.421, | |
| "eval_steps_per_second": 2.361, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4019900497512438, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8634982137913465e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4059701492537313, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.772710650702723e-05, | |
| "loss": 5.3772, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4099502487562189, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.681848531245195e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.41393034825870645, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.590936696214972e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4218905472636816, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.409063303785029e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.42587064676616915, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.318151468754805e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.4298507462686567, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.227289349297277e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.4338308457711443, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.136501786208654e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.43781094527363185, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.045813599902173e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4417910447761194, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.955249583622455e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.445771144278607, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8648344966672767e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.44975124378109455, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774593057618621e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.4537313432835821, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6845499375848686e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.4577114427860697, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5947297534559625e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.4616915422885572, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5051570611733976e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.46567164179104475, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415856349016859e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.4696517412935323, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.326852030909393e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.4736318407960199, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.238168439742867e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.149829820725605e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.481592039800995, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0618603247539916e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.4855721393034826, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9742840018098564e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.48955223880597015, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.887124794385445e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.4935323383084577, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.80040653093779e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.4975124378109453, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.714152919374241e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5014925373134328, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.628387540570963e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5054726368159204, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.543133841926159e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5094527363184079, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.458415130949785e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5134328358208955, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.374254568891514e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5174129353233831, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.290675164408669e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5213930348258706, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.207699767275904e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.5253731343283582, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12535106213829e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5293532338308458, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0436515623095647e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.962623603617218e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8822893382960955e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5412935323383085, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.802670728932207e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.545273631840796, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.723789542458361e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.5492537313432836, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6456673442033183e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.5532338308457712, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5683254919960356e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.5572139303482587, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4917851303266533e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5611940298507463, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4160671845658007e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.5651741293532339, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3411923552438105e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.5691542288557214, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2671811123913983e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.573134328358209, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.194053689943362e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5771144278606966, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.121830080206827e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5810945273631841, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0505300283955464e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.5850746268656717, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9801730272317585e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.5890547263681593, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.910778311617072e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.5930348258706468, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8423648533738342e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7749513560584252e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "eval_loss": NaN, | |
| "eval_runtime": 63.0605, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 1.681, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6009950248756218, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7085562498478883e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.6049751243781094, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6431976865013128e-05, | |
| "loss": 6.1151, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.608955223880597, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5788935343973164e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6129353233830845, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5156613736490108e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.6169154228855721, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4535184912977763e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6208955223880597, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3924818765871553e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6248756218905472, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3325682163181601e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.6288557213930348, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2737938902872767e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.6328358208955224, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2161749668083823e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.6368159203980099, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.159727198319836e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6407960199004975, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1044660170779142e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.6447761194029851, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0504065309377897e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.6487562189054726, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.97563519223192e-06, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.6527363184079602, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.459514286858898e-06, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.95584369556093e-06, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6606965174129353, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.464761116848546e-06, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.6646766169154229, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.986400807795349e-06, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.6686567164179105, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.520893547333436e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.672636815920398, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.068366600499744e-06, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.6766169154228856, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6289436836431076e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6805970149253732, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.20274493060135e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.6845771144278607, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.789886859858009e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.6885572139303483, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3904823426872605e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.6925373134328359, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.004640572296062e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.6965174129353234, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.632467033971838e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.700497512437811, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.274063476243839e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.7044776119402985, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.929527883066117e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.708457711442786, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5989544470296595e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.7124378109452736, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.282433543611136e-06, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.980051706465095e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7203980099502487, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.691891603766556e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.7243781094527363, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4180320156103298e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.7283582089552239, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.158547812473352e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.7323383084577114, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9135099347458293e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.736318407960199, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6829853733368294e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7402985074626866, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4670371513596842e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.7442786069651741, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2657243069020402e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.7482587064676617, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0791018768854855e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.7522388059701492, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.072208820189698e-07, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.7562189054726368, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.501283128502722e-07, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7601990049751244, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.07867116919233e-07, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.764179104477612, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.804761870163643e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.7681592039800995, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6799035054990215e-07, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.7721393034825871, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.704403600243721e-07, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.878528846331584e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7800995024875622, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.202505029674006e-07, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.7840796019900498, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.765169684323947e-08, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.7880597014925373, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.007084624906731e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.7920398009950249, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.518225414204771e-09, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.7960199004975125, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7960199004975125, | |
| "eval_loss": NaN, | |
| "eval_runtime": 53.8457, | |
| "eval_samples_per_second": 7.856, | |
| "eval_steps_per_second": 1.969, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.173851163674542e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |