|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.9702970297029703, |
|
"global_step": 150, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 3.3333333333333333e-06, |
|
"loss": 1.6064, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 6.666666666666667e-06, |
|
"loss": 1.6143, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1e-05, |
|
"loss": 1.6016, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.3333333333333333e-05, |
|
"loss": 1.5439, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.6666666666666667e-05, |
|
"loss": 1.418, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2e-05, |
|
"loss": 1.3711, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.999762027079909e-05, |
|
"loss": 1.5273, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.999048221581858e-05, |
|
"loss": 1.3262, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 1.9978589232386036e-05, |
|
"loss": 1.3193, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.9961946980917457e-05, |
|
"loss": 1.2812, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.9940563382223196e-05, |
|
"loss": 1.2598, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 1.9914448613738107e-05, |
|
"loss": 1.2188, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 1.988361510467761e-05, |
|
"loss": 1.251, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1.9848077530122083e-05, |
|
"loss": 1.2041, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1.9807852804032306e-05, |
|
"loss": 1.2031, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 1.9762960071199334e-05, |
|
"loss": 1.1963, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 1.9713420698132614e-05, |
|
"loss": 1.1914, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 1.9659258262890683e-05, |
|
"loss": 1.1611, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.960049854385929e-05, |
|
"loss": 1.1426, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.953716950748227e-05, |
|
"loss": 1.1846, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.1589336395263672, |
|
"eval_runtime": 8.8572, |
|
"eval_samples_per_second": 14.79, |
|
"eval_steps_per_second": 0.339, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.946930129495106e-05, |
|
"loss": 1.127, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.9396926207859085e-05, |
|
"loss": 1.1592, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.932007869282799e-05, |
|
"loss": 1.1309, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.9238795325112867e-05, |
|
"loss": 1.1309, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.9153114791194475e-05, |
|
"loss": 1.1318, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 1.9063077870366504e-05, |
|
"loss": 1.123, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1.8968727415326885e-05, |
|
"loss": 1.1475, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1.887010833178222e-05, |
|
"loss": 1.123, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1.876726755707508e-05, |
|
"loss": 1.1143, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 1.866025403784439e-05, |
|
"loss": 1.0967, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 1.854911870672947e-05, |
|
"loss": 1.083, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.843391445812886e-05, |
|
"loss": 1.0859, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1.8314696123025456e-05, |
|
"loss": 1.0771, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 1.819152044288992e-05, |
|
"loss": 1.1133, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 1.806444604267483e-05, |
|
"loss": 1.0762, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 1.7933533402912354e-05, |
|
"loss": 1.0674, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 1.7798844830928818e-05, |
|
"loss": 1.0791, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1.766044443118978e-05, |
|
"loss": 1.0854, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.7518398074789776e-05, |
|
"loss": 1.083, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 1.737277336810124e-05, |
|
"loss": 1.085, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"eval_loss": 1.0905295610427856, |
|
"eval_runtime": 8.5437, |
|
"eval_samples_per_second": 15.333, |
|
"eval_steps_per_second": 0.351, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.7223639620597556e-05, |
|
"loss": 1.0605, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 1.7071067811865477e-05, |
|
"loss": 1.0693, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.6915130557822698e-05, |
|
"loss": 1.0859, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 1.6755902076156606e-05, |
|
"loss": 1.083, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.659345815100069e-05, |
|
"loss": 1.1016, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 1.6427876096865394e-05, |
|
"loss": 1.0977, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1.6259234721840595e-05, |
|
"loss": 1.0693, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.608761429008721e-05, |
|
"loss": 1.0879, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 1.5913096483635827e-05, |
|
"loss": 1.0811, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 1.573576436351046e-05, |
|
"loss": 1.0742, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1.5555702330196024e-05, |
|
"loss": 1.0176, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 1.5372996083468242e-05, |
|
"loss": 0.9863, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 1.5187732581605217e-05, |
|
"loss": 0.9824, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 1.5000000000000002e-05, |
|
"loss": 0.9653, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.4809887689193878e-05, |
|
"loss": 0.9629, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.4617486132350343e-05, |
|
"loss": 0.9341, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 1.4422886902190014e-05, |
|
"loss": 0.9492, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 1.4226182617406996e-05, |
|
"loss": 0.9668, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.4027466898587375e-05, |
|
"loss": 0.9585, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 1.3826834323650899e-05, |
|
"loss": 0.9399, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"eval_loss": 1.0739504098892212, |
|
"eval_runtime": 8.5451, |
|
"eval_samples_per_second": 15.33, |
|
"eval_steps_per_second": 0.351, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.3624380382837017e-05, |
|
"loss": 0.9312, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 1.342020143325669e-05, |
|
"loss": 0.9727, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 1.3214394653031616e-05, |
|
"loss": 0.9629, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 1.300705799504273e-05, |
|
"loss": 0.9502, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 1.2798290140309924e-05, |
|
"loss": 0.9917, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 1.2588190451025209e-05, |
|
"loss": 0.9331, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.2376858923261732e-05, |
|
"loss": 0.9419, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 1.2164396139381029e-05, |
|
"loss": 0.9551, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 1.1950903220161286e-05, |
|
"loss": 0.9482, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 1.1736481776669307e-05, |
|
"loss": 0.9692, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 1.1521233861899168e-05, |
|
"loss": 0.96, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 1.130526192220052e-05, |
|
"loss": 0.9565, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 1.1088668748519646e-05, |
|
"loss": 0.9575, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 1.0871557427476585e-05, |
|
"loss": 0.957, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 1.0654031292301432e-05, |
|
"loss": 0.9331, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 1.0436193873653362e-05, |
|
"loss": 0.9536, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 1.0218148850345613e-05, |
|
"loss": 0.9302, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 1e-05, |
|
"loss": 0.9502, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 9.78185114965439e-06, |
|
"loss": 0.937, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 9.563806126346643e-06, |
|
"loss": 0.9287, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"eval_loss": 1.0581464767456055, |
|
"eval_runtime": 8.5408, |
|
"eval_samples_per_second": 15.338, |
|
"eval_steps_per_second": 0.351, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 9.34596870769857e-06, |
|
"loss": 0.9463, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 9.128442572523418e-06, |
|
"loss": 0.9336, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 8.911331251480357e-06, |
|
"loss": 0.9463, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 8.694738077799487e-06, |
|
"loss": 0.959, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 8.478766138100834e-06, |
|
"loss": 0.9297, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 8.263518223330698e-06, |
|
"loss": 0.9512, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 8.04909677983872e-06, |
|
"loss": 0.9556, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 7.835603860618973e-06, |
|
"loss": 0.9346, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 7.623141076738271e-06, |
|
"loss": 0.9341, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 7.411809548974792e-06, |
|
"loss": 0.9253, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 7.201709859690081e-06, |
|
"loss": 0.9556, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 6.992942004957271e-06, |
|
"loss": 0.9478, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 6.785605346968387e-06, |
|
"loss": 0.9346, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 6.579798566743314e-06, |
|
"loss": 0.9585, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 6.375619617162985e-06, |
|
"loss": 0.939, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 6.173165676349103e-06, |
|
"loss": 0.9351, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 5.97253310141263e-06, |
|
"loss": 0.9312, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 5.773817382593008e-06, |
|
"loss": 0.9307, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 5.5771130978099896e-06, |
|
"loss": 0.9482, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 5.382513867649663e-06, |
|
"loss": 0.9077, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"eval_loss": 1.0503339767456055, |
|
"eval_runtime": 8.5441, |
|
"eval_samples_per_second": 15.332, |
|
"eval_steps_per_second": 0.351, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 5.190112310806126e-06, |
|
"loss": 0.9731, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 5.000000000000003e-06, |
|
"loss": 0.8608, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 4.812267418394784e-06, |
|
"loss": 0.8711, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 4.627003916531761e-06, |
|
"loss": 0.8706, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 4.444297669803981e-06, |
|
"loss": 0.8618, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 4.264235636489542e-06, |
|
"loss": 0.8882, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 4.086903516364179e-06, |
|
"loss": 0.8594, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 3.912385709912794e-06, |
|
"loss": 0.8809, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 3.7407652781594094e-06, |
|
"loss": 0.8423, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 3.5721239031346067e-06, |
|
"loss": 0.8242, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 3.4065418489993118e-06, |
|
"loss": 0.8018, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 3.2440979238433977e-06, |
|
"loss": 0.854, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 3.0848694421773075e-06, |
|
"loss": 0.8452, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 2.9289321881345257e-06, |
|
"loss": 0.8564, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 2.776360379402445e-06, |
|
"loss": 0.855, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 2.6272266318987606e-06, |
|
"loss": 0.8545, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 2.4816019252102274e-06, |
|
"loss": 0.8452, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 2.339555568810221e-06, |
|
"loss": 0.855, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 2.201155169071184e-06, |
|
"loss": 0.8501, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 2.0664665970876496e-06, |
|
"loss": 0.8481, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"eval_loss": 1.067867398262024, |
|
"eval_runtime": 8.5474, |
|
"eval_samples_per_second": 15.326, |
|
"eval_steps_per_second": 0.351, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 1.9355539573251737e-06, |
|
"loss": 0.855, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 1.808479557110081e-06, |
|
"loss": 0.8335, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 1.6853038769745466e-06, |
|
"loss": 0.8462, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 1.566085541871145e-06, |
|
"loss": 0.8374, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 1.4508812932705364e-06, |
|
"loss": 0.8281, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 1.339745962155613e-06, |
|
"loss": 0.8408, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 1.2327324429249232e-06, |
|
"loss": 0.8574, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 1.129891668217783e-06, |
|
"loss": 0.8486, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 1.0312725846731174e-06, |
|
"loss": 0.8579, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 9.369221296335007e-07, |
|
"loss": 0.8604, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 8.468852088055291e-07, |
|
"loss": 0.8276, |
|
"step": 131 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 7.612046748871327e-07, |
|
"loss": 0.8398, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 6.799213071720156e-07, |
|
"loss": 0.8369, |
|
"step": 133 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 6.030737921409169e-07, |
|
"loss": 0.8555, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 5.306987050489442e-07, |
|
"loss": 0.8477, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 4.628304925177318e-07, |
|
"loss": 0.8276, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 3.99501456140714e-07, |
|
"loss": 0.8438, |
|
"step": 137 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 3.4074173710931804e-07, |
|
"loss": 0.8442, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 2.865793018673857e-07, |
|
"loss": 0.8159, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 2.370399288006664e-07, |
|
"loss": 0.8691, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"eval_loss": 1.067211389541626, |
|
"eval_runtime": 8.5453, |
|
"eval_samples_per_second": 15.33, |
|
"eval_steps_per_second": 0.351, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 1.921471959676957e-07, |
|
"loss": 0.8594, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 1.519224698779198e-07, |
|
"loss": 0.8237, |
|
"step": 142 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 1.1638489532239339e-07, |
|
"loss": 0.8335, |
|
"step": 143 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 8.555138626189619e-08, |
|
"loss": 0.8511, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 5.943661777680354e-08, |
|
"loss": 0.8413, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 3.805301908254455e-08, |
|
"loss": 0.8564, |
|
"step": 146 |
|
}, |
|
{ |
|
"epoch": 2.91, |
|
"learning_rate": 2.1410767613965212e-08, |
|
"loss": 0.8452, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 9.517784181422018e-09, |
|
"loss": 0.8452, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 2.379729200908676e-09, |
|
"loss": 0.8403, |
|
"step": 149 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 0.0, |
|
"loss": 0.8643, |
|
"step": 150 |
|
} |
|
], |
|
"max_steps": 150, |
|
"num_train_epochs": 3, |
|
"total_flos": 62211930193920.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|