|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.08, |
|
"eval_steps": 500, |
|
"global_step": 100, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 1.1216, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 8.000000000000001e-06, |
|
"loss": 1.2115, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.2e-05, |
|
"loss": 1.089, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.6000000000000003e-05, |
|
"loss": 1.2665, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2e-05, |
|
"loss": 1.08, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.4e-05, |
|
"loss": 1.0745, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 2.8000000000000003e-05, |
|
"loss": 1.0659, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 3.2000000000000005e-05, |
|
"loss": 1.0081, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 3.6e-05, |
|
"loss": 0.8667, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4e-05, |
|
"loss": 0.905, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.4000000000000006e-05, |
|
"loss": 0.794, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.8e-05, |
|
"loss": 0.841, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 5.2000000000000004e-05, |
|
"loss": 0.7165, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 5.6000000000000006e-05, |
|
"loss": 0.7328, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6e-05, |
|
"loss": 0.7847, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6.400000000000001e-05, |
|
"loss": 0.6334, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6.800000000000001e-05, |
|
"loss": 0.6643, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 7.2e-05, |
|
"loss": 0.601, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 7.6e-05, |
|
"loss": 0.6247, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 8e-05, |
|
"loss": 0.5676, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 8.4e-05, |
|
"loss": 0.5716, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 8.800000000000001e-05, |
|
"loss": 0.5638, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 9.200000000000001e-05, |
|
"loss": 0.571, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 9.6e-05, |
|
"loss": 0.5529, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001, |
|
"loss": 0.579, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00010400000000000001, |
|
"loss": 0.5426, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00010800000000000001, |
|
"loss": 0.5065, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00011200000000000001, |
|
"loss": 0.5103, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.000116, |
|
"loss": 0.5186, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00012, |
|
"loss": 0.4906, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.000124, |
|
"loss": 0.5208, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00012800000000000002, |
|
"loss": 0.5539, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000132, |
|
"loss": 0.5014, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00013600000000000003, |
|
"loss": 0.5189, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00014, |
|
"loss": 0.5317, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000144, |
|
"loss": 0.5158, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000148, |
|
"loss": 0.5151, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000152, |
|
"loss": 0.4496, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00015600000000000002, |
|
"loss": 0.5058, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00016, |
|
"loss": 0.5394, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000164, |
|
"loss": 0.4685, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000168, |
|
"loss": 0.5078, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.000172, |
|
"loss": 0.4618, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00017600000000000002, |
|
"loss": 0.4989, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00018, |
|
"loss": 0.4492, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00018400000000000003, |
|
"loss": 0.5165, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.000188, |
|
"loss": 0.492, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.000192, |
|
"loss": 0.4992, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.000196, |
|
"loss": 0.451, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.4588, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00020400000000000003, |
|
"loss": 0.4867, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00020800000000000001, |
|
"loss": 0.451, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00021200000000000003, |
|
"loss": 0.5302, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00021600000000000002, |
|
"loss": 0.4654, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00022000000000000003, |
|
"loss": 0.511, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00022400000000000002, |
|
"loss": 0.4921, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00022799999999999999, |
|
"loss": 0.4858, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000232, |
|
"loss": 0.4373, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000236, |
|
"loss": 0.4998, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00024, |
|
"loss": 0.482, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000244, |
|
"loss": 0.4686, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000248, |
|
"loss": 0.4657, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000252, |
|
"loss": 0.5077, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00025600000000000004, |
|
"loss": 0.4893, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00026000000000000003, |
|
"loss": 0.4286, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000264, |
|
"loss": 0.4262, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.000268, |
|
"loss": 0.4851, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00027200000000000005, |
|
"loss": 0.5201, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000276, |
|
"loss": 0.4923, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00028, |
|
"loss": 0.4739, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000284, |
|
"loss": 0.4965, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000288, |
|
"loss": 0.4749, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000292, |
|
"loss": 0.5087, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000296, |
|
"loss": 0.4603, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00030000000000000003, |
|
"loss": 0.4746, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000304, |
|
"loss": 0.5176, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000308, |
|
"loss": 0.4847, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00031200000000000005, |
|
"loss": 0.448, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00031600000000000004, |
|
"loss": 0.4245, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.00032, |
|
"loss": 0.4618, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.000324, |
|
"loss": 0.4838, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000328, |
|
"loss": 0.4449, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000332, |
|
"loss": 0.4691, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000336, |
|
"loss": 0.4518, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00034, |
|
"loss": 0.4881, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000344, |
|
"loss": 0.519, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000348, |
|
"loss": 0.4908, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00035200000000000005, |
|
"loss": 0.4413, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00035600000000000003, |
|
"loss": 0.477, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00036, |
|
"loss": 0.4432, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.000364, |
|
"loss": 0.4678, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00036800000000000005, |
|
"loss": 0.4864, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00037200000000000004, |
|
"loss": 0.5048, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.000376, |
|
"loss": 0.4583, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00038, |
|
"loss": 0.465, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.000384, |
|
"loss": 0.4414, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.000388, |
|
"loss": 0.4912, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.000392, |
|
"loss": 0.4749, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00039600000000000003, |
|
"loss": 0.4773, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0004, |
|
"loss": 0.4868, |
|
"step": 100 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 1250, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"total_flos": 6.794848448387482e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|