File size: 2,814 Bytes
e375f00 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.861635220125786,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.7290322580645161,
"eval_loss": 3.165098190307617,
"eval_runtime": 2.491,
"eval_samples_per_second": 1244.479,
"eval_steps_per_second": 26.094,
"step": 318
},
{
"epoch": 1.57,
"learning_rate": 1.685534591194969e-05,
"loss": 3.6948,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.86,
"eval_loss": 1.5545812845230103,
"eval_runtime": 2.553,
"eval_samples_per_second": 1214.257,
"eval_steps_per_second": 25.46,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.9132258064516129,
"eval_loss": 0.7676715850830078,
"eval_runtime": 2.391,
"eval_samples_per_second": 1296.531,
"eval_steps_per_second": 27.185,
"step": 954
},
{
"epoch": 3.14,
"learning_rate": 1.371069182389937e-05,
"loss": 1.3265,
"step": 1000
},
{
"epoch": 4.0,
"eval_accuracy": 0.9354838709677419,
"eval_loss": 0.45812979340553284,
"eval_runtime": 2.438,
"eval_samples_per_second": 1271.533,
"eval_steps_per_second": 26.661,
"step": 1272
},
{
"epoch": 4.72,
"learning_rate": 1.0566037735849058e-05,
"loss": 0.4291,
"step": 1500
},
{
"epoch": 5.0,
"eval_accuracy": 0.9438709677419355,
"eval_loss": 0.3298114240169525,
"eval_runtime": 2.465,
"eval_samples_per_second": 1257.608,
"eval_steps_per_second": 26.369,
"step": 1590
},
{
"epoch": 6.0,
"eval_accuracy": 0.9464516129032258,
"eval_loss": 0.27686071395874023,
"eval_runtime": 2.468,
"eval_samples_per_second": 1256.079,
"eval_steps_per_second": 26.337,
"step": 1908
},
{
"epoch": 6.29,
"learning_rate": 7.421383647798742e-06,
"loss": 0.1725,
"step": 2000
},
{
"epoch": 7.0,
"eval_accuracy": 0.947741935483871,
"eval_loss": 0.25533074140548706,
"eval_runtime": 2.557,
"eval_samples_per_second": 1212.358,
"eval_steps_per_second": 25.42,
"step": 2226
},
{
"epoch": 7.86,
"learning_rate": 4.276729559748428e-06,
"loss": 0.0911,
"step": 2500
}
],
"logging_steps": 500,
"max_steps": 3180,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 790936363356552.0,
"trial_name": null,
"trial_params": {
"alpha": 0.46699247207893385,
"num_train_epochs": 10,
"temperature": 2
}
}
|