|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.985522233712513, |
|
"eval_steps": 500, |
|
"global_step": 120, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.643, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 0.6409, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 1.2e-05, |
|
"loss": 0.5779, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 0.6641, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2e-05, |
|
"loss": 0.61, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 2.4e-05, |
|
"loss": 0.6653, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 0.6101, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 0.7479, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 3.6e-05, |
|
"loss": 0.6357, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4e-05, |
|
"loss": 0.6214, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 0.6257, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.8e-05, |
|
"loss": 0.6228, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 5.2000000000000004e-05, |
|
"loss": 0.6295, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 5.6000000000000006e-05, |
|
"loss": 0.6345, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 6e-05, |
|
"loss": 0.6282, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 6.400000000000001e-05, |
|
"loss": 0.6231, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 6.800000000000001e-05, |
|
"loss": 0.6282, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 7.2e-05, |
|
"loss": 0.6423, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 7.6e-05, |
|
"loss": 0.6055, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 8e-05, |
|
"loss": 0.6244, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 8.4e-05, |
|
"loss": 0.5443, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 8.800000000000001e-05, |
|
"loss": 0.6479, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.200000000000001e-05, |
|
"loss": 0.5565, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 9.6e-05, |
|
"loss": 0.6131, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6696, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.00010400000000000001, |
|
"loss": 0.5886, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00010800000000000001, |
|
"loss": 0.5999, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00011200000000000001, |
|
"loss": 0.7083, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.000116, |
|
"loss": 0.6178, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00012, |
|
"loss": 0.6466, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.000124, |
|
"loss": 0.5462, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.00012800000000000002, |
|
"loss": 0.6239, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 0.000132, |
|
"loss": 0.6646, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.00013600000000000003, |
|
"loss": 0.6293, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 0.00014, |
|
"loss": 0.5853, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.000144, |
|
"loss": 0.6881, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.000148, |
|
"loss": 0.6398, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 0.000152, |
|
"loss": 0.6054, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 0.00015600000000000002, |
|
"loss": 0.6332, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 0.00016, |
|
"loss": 0.5941, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.000164, |
|
"loss": 0.6127, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 0.000168, |
|
"loss": 0.6475, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.000172, |
|
"loss": 0.5668, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 0.00017600000000000002, |
|
"loss": 0.6348, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 0.00018, |
|
"loss": 0.6379, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00018400000000000003, |
|
"loss": 0.5992, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 0.000188, |
|
"loss": 0.6435, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.000192, |
|
"loss": 0.5909, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 0.000196, |
|
"loss": 0.6596, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6426, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.00020400000000000003, |
|
"loss": 0.5908, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.00020800000000000001, |
|
"loss": 0.5486, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00021200000000000003, |
|
"loss": 0.6184, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.00021600000000000002, |
|
"loss": 0.6977, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 0.00022000000000000003, |
|
"loss": 0.6308, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.00022400000000000002, |
|
"loss": 0.5394, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 0.00022799999999999999, |
|
"loss": 0.5426, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.000232, |
|
"loss": 0.5429, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 0.000236, |
|
"loss": 0.5822, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.00024, |
|
"loss": 0.5793, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 0.000244, |
|
"loss": 0.5906, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 0.000248, |
|
"loss": 0.4957, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.000252, |
|
"loss": 0.5421, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 0.00025600000000000004, |
|
"loss": 0.5444, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.00026000000000000003, |
|
"loss": 0.5618, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 0.000264, |
|
"loss": 0.5372, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.000268, |
|
"loss": 0.5701, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 0.00027200000000000005, |
|
"loss": 0.5257, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.000276, |
|
"loss": 0.5237, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.00028, |
|
"loss": 0.4729, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 0.000284, |
|
"loss": 0.5142, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 0.000288, |
|
"loss": 0.5365, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.000292, |
|
"loss": 0.5288, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 0.000296, |
|
"loss": 0.5095, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.00030000000000000003, |
|
"loss": 0.5229, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 0.000304, |
|
"loss": 0.5355, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 0.000308, |
|
"loss": 0.5626, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.00031200000000000005, |
|
"loss": 0.5548, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 0.00031600000000000004, |
|
"loss": 0.5404, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00032, |
|
"loss": 0.5686, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 0.000324, |
|
"loss": 0.5242, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.000328, |
|
"loss": 0.52, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 0.000332, |
|
"loss": 0.5481, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.000336, |
|
"loss": 0.5321, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 0.00034, |
|
"loss": 0.603, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 0.000344, |
|
"loss": 0.4836, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.000348, |
|
"loss": 0.5583, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.00035200000000000005, |
|
"loss": 0.5336, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.00035600000000000003, |
|
"loss": 0.4061, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 0.00036, |
|
"loss": 0.5555, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 0.000364, |
|
"loss": 0.5216, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.00036800000000000005, |
|
"loss": 0.4991, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.00037200000000000004, |
|
"loss": 0.5601, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.000376, |
|
"loss": 0.4857, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.00038, |
|
"loss": 0.5439, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 0.000384, |
|
"loss": 0.5817, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.000388, |
|
"loss": 0.5179, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 0.000392, |
|
"loss": 0.5464, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.00039600000000000003, |
|
"loss": 0.513, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 0.0004, |
|
"loss": 0.4899, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 0.0003998458072481446, |
|
"loss": 0.5715, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 0.0003993834667466256, |
|
"loss": 0.5312, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 0.0003986136913909853, |
|
"loss": 0.5066, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00039753766811902755, |
|
"loss": 0.5407, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 0.0003961570560806461, |
|
"loss": 0.5281, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 0.0003944739840795353, |
|
"loss": 0.4873, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.00039249104729072946, |
|
"loss": 0.5336, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.00039021130325903074, |
|
"loss": 0.4842, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.00038763826718449685, |
|
"loss": 0.5136, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.0003847759065022574, |
|
"loss": 0.5359, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.0003816286347650163, |
|
"loss": 0.4766, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 0.0003782013048376736, |
|
"loss": 0.4896, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 0.00037449920141455944, |
|
"loss": 0.4977, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 0.00037052803287081844, |
|
"loss": 0.506, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 0.0003662939224605091, |
|
"loss": 0.5442, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.0003618033988749895, |
|
"loss": 0.5445, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 0.00035706338617614897, |
|
"loss": 0.5348, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 0.0003520811931200062, |
|
"loss": 0.5331, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.0003468645018871371, |
|
"loss": 0.4697, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.0003414213562373095, |
|
"loss": 0.5119, |
|
"step": 120 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 180, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 10, |
|
"total_flos": 4.155932535422976e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|