| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9900990099009901, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0049504950495049506, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0049504950495049506, | |
| "eval_loss": NaN, | |
| "eval_runtime": 83.6818, | |
| "eval_samples_per_second": 4.063, | |
| "eval_steps_per_second": 1.016, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009900990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01485148514851485, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024752475247524754, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0297029702970297, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.034653465346534656, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.039603960396039604, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04455445544554455, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.900000000000001e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04950495049504951, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.054455445544554455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001099924817745858, | |
| "loss": 1.6191, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0594059405940594, | |
| "grad_norm": 14.079827308654785, | |
| "learning_rate": 0.00010996992915375093, | |
| "loss": 3.5174, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06435643564356436, | |
| "grad_norm": 9.411308288574219, | |
| "learning_rate": 0.00010993234830315676, | |
| "loss": 3.3808, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06930693069306931, | |
| "grad_norm": 8.690550804138184, | |
| "learning_rate": 0.0001098797494970326, | |
| "loss": 2.488, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07425742574257425, | |
| "grad_norm": 6.69142484664917, | |
| "learning_rate": 0.00010981214711536684, | |
| "loss": 2.4855, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 7.557561874389648, | |
| "learning_rate": 0.00010972955963997563, | |
| "loss": 2.3552, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08415841584158416, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010963200964945011, | |
| "loss": 4.993, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0891089108910891, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010951952381298364, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09405940594059406, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010939213288308077, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09900990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010924987168714973, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10396039603960396, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010909277911798103, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10891089108910891, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010892089812311451, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11386138613861387, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010873427569309797, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1188118811881188, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010853296284864032, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12376237623762376, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010831701462666318, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12871287128712872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010808649006525419, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13366336633663367, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010784145218752665, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13861386138613863, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010758196798438968, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14356435643564355, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010730810839623346, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1485148514851485, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001070199482935349, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15346534653465346, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010671756645638888, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010640104555297034, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16336633663366337, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010607047211693389, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16831683168316833, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010572593652375616, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.17326732673267325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010536753296602816, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1782178217821782, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010499535942770394, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18316831683168316, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010460951765731275, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.18811881188118812, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000104210113140142, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19306930693069307, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010379725506939865, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19801980198019803, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001033710563163569, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20297029702970298, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010293163339950024, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2079207920792079, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010247910645266658, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.21287128712871287, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010201359919220464, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.21782178217821782, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010153523888315144, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.22277227722772278, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010104415630443907, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22772277227722773, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001005404857131411, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.23267326732673269, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010002436480776809, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.949593469062211e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24257425742574257, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.895533982922087e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.24752475247524752, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.840272801680165e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24752475247524752, | |
| "eval_loss": NaN, | |
| "eval_runtime": 79.3841, | |
| "eval_samples_per_second": 4.283, | |
| "eval_steps_per_second": 1.071, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2524752475247525, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.783825033191619e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.25742574257425743, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.726206109712725e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.2623762376237624, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.667431783681842e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.26732673267326734, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.607518123412847e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2722772277227723, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.546481508702224e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.27722772277227725, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.48433862635099e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.28217821782178215, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.421106465602684e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2871287128712871, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.356802313498687e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.29207920792079206, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.291443750152112e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.297029702970297, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.225048643941577e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.30198019801980197, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.157635146626164e-05, | |
| "loss": 0.7247, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3069306930693069, | |
| "grad_norm": 6.580938339233398, | |
| "learning_rate": 9.089221688382928e-05, | |
| "loss": 2.585, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3118811881188119, | |
| "grad_norm": 8.055264472961426, | |
| "learning_rate": 9.019826972768242e-05, | |
| "loss": 2.949, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 8.093265533447266, | |
| "learning_rate": 8.949469971604454e-05, | |
| "loss": 2.7531, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3217821782178218, | |
| "grad_norm": 7.130252838134766, | |
| "learning_rate": 8.878169919793173e-05, | |
| "loss": 2.4377, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.32673267326732675, | |
| "grad_norm": 6.8993306159973145, | |
| "learning_rate": 8.805946310056638e-05, | |
| "loss": 2.6607, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3316831683168317, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.732818887608602e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.33663366336633666, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.65880764475619e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3415841584158416, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.583932815434201e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3465346534653465, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.50821486967335e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.35148514851485146, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.431674508003966e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3564356435643564, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.354332655796683e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3613861386138614, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.276210457541642e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.36633663366336633, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.197329271067796e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3712871287128713, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.117710661703905e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.37623762376237624, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.037376396382784e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3811881188118812, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.956348437690437e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.38613861386138615, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.87464893786171e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3910891089108911, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.792300232724097e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.709324835591332e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.400990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.625745431108487e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.40594059405940597, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.541584869050213e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.41089108910891087, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.456866158073842e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.4158415841584158, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.371612459429037e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.4207920792079208, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.28584708062576e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.42574257425742573, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.19959346906221e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.4306930693069307, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.112875205614558e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.43564356435643564, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.025715998190145e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.4405940594059406, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.938139675246009e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.44554455445544555, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.850170179274395e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4504950495049505, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.761831560257134e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.45544554455445546, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.673147969090608e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.4603960396039604, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.584143650983141e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.46534653465346537, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.494842938826605e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.47029702970297027, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.405270246544037e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.31545006241513e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4801980198019802, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.22540694238138e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.48514851485148514, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.135165503332725e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4900990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0447504163775465e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.954186400097829e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49504950495049505, | |
| "eval_loss": NaN, | |
| "eval_runtime": 84.4545, | |
| "eval_samples_per_second": 4.026, | |
| "eval_steps_per_second": 1.006, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8634982137913465e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.504950495049505, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.772710650702723e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.5099009900990099, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.681848531245195e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.5148514851485149, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.590936696214972e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.5198019801980198, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5247524752475248, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.409063303785029e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.5297029702970297, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.318151468754805e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.5346534653465347, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.227289349297277e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.5396039603960396, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.136501786208654e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.5445544554455446, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.045813599902173e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5495049504950495, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.955249583622455e-05, | |
| "loss": 2.2827, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": 6.830944538116455, | |
| "learning_rate": 4.8648344966672767e-05, | |
| "loss": 2.7697, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.5594059405940595, | |
| "grad_norm": 6.300211429595947, | |
| "learning_rate": 4.774593057618621e-05, | |
| "loss": 2.8706, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.5643564356435643, | |
| "grad_norm": 6.06986141204834, | |
| "learning_rate": 4.6845499375848686e-05, | |
| "loss": 2.5056, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.5693069306930693, | |
| "grad_norm": 5.525240421295166, | |
| "learning_rate": 4.5947297534559625e-05, | |
| "loss": 2.5763, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5742574257425742, | |
| "grad_norm": 5.942731857299805, | |
| "learning_rate": 4.5051570611733976e-05, | |
| "loss": 2.5812, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.5792079207920792, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415856349016859e-05, | |
| "loss": 5.42, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.5841584158415841, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.326852030909393e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5891089108910891, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.238168439742867e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.594059405940594, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.149829820725605e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.599009900990099, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0618603247539916e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.6039603960396039, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9742840018098564e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.6089108910891089, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.887124794385445e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.6138613861386139, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.80040653093779e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.6188118811881188, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.714152919374241e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6237623762376238, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.628387540570963e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.6287128712871287, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.543133841926159e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.458415130949785e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.6386138613861386, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.374254568891514e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.6435643564356436, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.290675164408669e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6485148514851485, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.207699767275904e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.6534653465346535, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12535106213829e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.6584158415841584, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0436515623095647e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.6633663366336634, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.962623603617218e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.6683168316831684, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8822893382960955e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6732673267326733, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.802670728932207e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.6782178217821783, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.723789542458361e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.6831683168316832, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6456673442033183e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.6881188118811881, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5683254919960356e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.693069306930693, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4917851303266533e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.698019801980198, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4160671845658007e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.7029702970297029, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3411923552438105e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.7079207920792079, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2671811123913983e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.194053689943362e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.7178217821782178, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.121830080206827e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.7227722772277227, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0505300283955464e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.7277227722772277, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9801730272317585e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.7326732673267327, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.910778311617072e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.7376237623762376, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8423648533738342e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.7425742574257426, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7749513560584252e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7425742574257426, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.2602, | |
| "eval_samples_per_second": 4.236, | |
| "eval_steps_per_second": 1.059, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7475247524752475, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7085562498478883e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.7524752475247525, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6431976865013128e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.7574257425742574, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5788935343973164e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.7623762376237624, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5156613736490108e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.7673267326732673, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4535184912977763e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7722772277227723, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3924818765871553e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.7772277227722773, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3325682163181601e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.7821782178217822, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2737938902872767e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.7871287128712872, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2161749668083823e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.159727198319836e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7970297029702971, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1044660170779142e-05, | |
| "loss": 1.3311, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.801980198019802, | |
| "grad_norm": 6.492788791656494, | |
| "learning_rate": 1.0504065309377897e-05, | |
| "loss": 2.9635, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.806930693069307, | |
| "grad_norm": 6.688177108764648, | |
| "learning_rate": 9.97563519223192e-06, | |
| "loss": 3.3465, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.8118811881188119, | |
| "grad_norm": 5.766157627105713, | |
| "learning_rate": 9.459514286858898e-06, | |
| "loss": 2.4439, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.8168316831683168, | |
| "grad_norm": 5.731694221496582, | |
| "learning_rate": 8.95584369556093e-06, | |
| "loss": 2.4051, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.8217821782178217, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.464761116848546e-06, | |
| "loss": 5.7791, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.8267326732673267, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.986400807795349e-06, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.8316831683168316, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.520893547333436e-06, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.8366336633663366, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.068366600499744e-06, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.8415841584158416, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6289436836431076e-06, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8465346534653465, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.20274493060135e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.8514851485148515, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.789886859858009e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.8564356435643564, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3904823426872605e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.8613861386138614, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.004640572296062e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.8663366336633663, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.632467033971838e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.8712871287128713, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.274063476243839e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.8762376237623762, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.929527883066117e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.8811881188118812, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5989544470296595e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.8861386138613861, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.282433543611136e-06, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.8910891089108911, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.980051706465095e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8960396039603961, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.691891603766556e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.900990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4180320156103298e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.905940594059406, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.158547812473352e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.9108910891089109, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9135099347458293e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.9158415841584159, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6829853733368294e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.9207920792079208, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4670371513596842e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.9257425742574258, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2657243069020402e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.9306930693069307, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0791018768854855e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.9356435643564357, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.072208820189698e-07, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.9405940594059405, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.501283128502722e-07, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.9455445544554455, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.07867116919233e-07, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.804761870163643e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.9554455445544554, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6799035054990215e-07, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.9603960396039604, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.704403600243721e-07, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.9653465346534653, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.878528846331584e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.9702970297029703, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.202505029674006e-07, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.9752475247524752, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.765169684323947e-08, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.9801980198019802, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.007084624906731e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.9851485148514851, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.518225414204771e-09, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.9900990099009901, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9900990099009901, | |
| "eval_loss": NaN, | |
| "eval_runtime": 86.6648, | |
| "eval_samples_per_second": 3.923, | |
| "eval_steps_per_second": 0.981, | |
| "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": 3.463015181750108e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |