311 lines
7.4 KiB
JSON
311 lines
7.4 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 6.0,
|
|
"global_step": 9564,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.31,
|
|
"learning_rate": 4.7386030949393564e-05,
|
|
"loss": 1.4207,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.31,
|
|
"eval_accuracy": 0.9008888888888889,
|
|
"eval_loss": 0.7066789269447327,
|
|
"eval_runtime": 2.6965,
|
|
"eval_samples_per_second": 3337.621,
|
|
"eval_steps_per_second": 417.203,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"learning_rate": 4.477206189878712e-05,
|
|
"loss": 0.5086,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.63,
|
|
"eval_accuracy": 0.9516666666666667,
|
|
"eval_loss": 0.3055577874183655,
|
|
"eval_runtime": 2.6576,
|
|
"eval_samples_per_second": 3386.509,
|
|
"eval_steps_per_second": 423.314,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"learning_rate": 4.215809284818068e-05,
|
|
"loss": 0.2731,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 0.94,
|
|
"eval_accuracy": 0.9648888888888889,
|
|
"eval_loss": 0.18555375933647156,
|
|
"eval_runtime": 2.6597,
|
|
"eval_samples_per_second": 3383.793,
|
|
"eval_steps_per_second": 422.974,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"learning_rate": 3.954412379757424e-05,
|
|
"loss": 0.1976,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 1.25,
|
|
"eval_accuracy": 0.9701111111111111,
|
|
"eval_loss": 0.14159560203552246,
|
|
"eval_runtime": 2.715,
|
|
"eval_samples_per_second": 3314.86,
|
|
"eval_steps_per_second": 414.357,
|
|
"step": 2000
|
|
},
|
|
{
|
|
"epoch": 1.57,
|
|
"learning_rate": 3.69301547469678e-05,
|
|
"loss": 0.1565,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 1.57,
|
|
"eval_accuracy": 0.9738888888888889,
|
|
"eval_loss": 0.11081045866012573,
|
|
"eval_runtime": 2.6963,
|
|
"eval_samples_per_second": 3337.905,
|
|
"eval_steps_per_second": 417.238,
|
|
"step": 2500
|
|
},
|
|
{
|
|
"epoch": 1.88,
|
|
"learning_rate": 3.431618569636136e-05,
|
|
"loss": 0.128,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 1.88,
|
|
"eval_accuracy": 0.976,
|
|
"eval_loss": 0.09747562557458878,
|
|
"eval_runtime": 2.6961,
|
|
"eval_samples_per_second": 3338.209,
|
|
"eval_steps_per_second": 417.276,
|
|
"step": 3000
|
|
},
|
|
{
|
|
"epoch": 2.2,
|
|
"learning_rate": 3.170221664575492e-05,
|
|
"loss": 0.1133,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"epoch": 2.2,
|
|
"eval_accuracy": 0.9788888888888889,
|
|
"eval_loss": 0.08474569022655487,
|
|
"eval_runtime": 2.7245,
|
|
"eval_samples_per_second": 3303.375,
|
|
"eval_steps_per_second": 412.922,
|
|
"step": 3500
|
|
},
|
|
{
|
|
"epoch": 2.51,
|
|
"learning_rate": 2.9088247595148475e-05,
|
|
"loss": 0.1031,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 2.51,
|
|
"eval_accuracy": 0.9804444444444445,
|
|
"eval_loss": 0.07724875211715698,
|
|
"eval_runtime": 2.6363,
|
|
"eval_samples_per_second": 3413.847,
|
|
"eval_steps_per_second": 426.731,
|
|
"step": 4000
|
|
},
|
|
{
|
|
"epoch": 2.82,
|
|
"learning_rate": 2.6474278544542037e-05,
|
|
"loss": 0.09,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"epoch": 2.82,
|
|
"eval_accuracy": 0.9818888888888889,
|
|
"eval_loss": 0.0697416290640831,
|
|
"eval_runtime": 2.6295,
|
|
"eval_samples_per_second": 3422.689,
|
|
"eval_steps_per_second": 427.836,
|
|
"step": 4500
|
|
},
|
|
{
|
|
"epoch": 3.14,
|
|
"learning_rate": 2.386030949393559e-05,
|
|
"loss": 0.0871,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 3.14,
|
|
"eval_accuracy": 0.9815555555555555,
|
|
"eval_loss": 0.066066212952137,
|
|
"eval_runtime": 2.6946,
|
|
"eval_samples_per_second": 3340.06,
|
|
"eval_steps_per_second": 417.507,
|
|
"step": 5000
|
|
},
|
|
{
|
|
"epoch": 3.45,
|
|
"learning_rate": 2.1246340443329153e-05,
|
|
"loss": 0.0733,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"epoch": 3.45,
|
|
"eval_accuracy": 0.9822222222222222,
|
|
"eval_loss": 0.06342040002346039,
|
|
"eval_runtime": 2.6897,
|
|
"eval_samples_per_second": 3346.09,
|
|
"eval_steps_per_second": 418.261,
|
|
"step": 5500
|
|
},
|
|
{
|
|
"epoch": 3.76,
|
|
"learning_rate": 1.863237139272271e-05,
|
|
"loss": 0.0761,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 3.76,
|
|
"eval_accuracy": 0.983,
|
|
"eval_loss": 0.06072380393743515,
|
|
"eval_runtime": 2.6938,
|
|
"eval_samples_per_second": 3340.98,
|
|
"eval_steps_per_second": 417.623,
|
|
"step": 6000
|
|
},
|
|
{
|
|
"epoch": 4.08,
|
|
"learning_rate": 1.601840234211627e-05,
|
|
"loss": 0.0739,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"epoch": 4.08,
|
|
"eval_accuracy": 0.9832222222222222,
|
|
"eval_loss": 0.05795769765973091,
|
|
"eval_runtime": 2.6767,
|
|
"eval_samples_per_second": 3362.391,
|
|
"eval_steps_per_second": 420.299,
|
|
"step": 6500
|
|
},
|
|
{
|
|
"epoch": 4.39,
|
|
"learning_rate": 1.340443329150983e-05,
|
|
"loss": 0.0643,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 4.39,
|
|
"eval_accuracy": 0.9844444444444445,
|
|
"eval_loss": 0.05685265362262726,
|
|
"eval_runtime": 2.6876,
|
|
"eval_samples_per_second": 3348.672,
|
|
"eval_steps_per_second": 418.584,
|
|
"step": 7000
|
|
},
|
|
{
|
|
"epoch": 4.71,
|
|
"learning_rate": 1.0790464240903388e-05,
|
|
"loss": 0.0678,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"epoch": 4.71,
|
|
"eval_accuracy": 0.984,
|
|
"eval_loss": 0.05617769435048103,
|
|
"eval_runtime": 2.6484,
|
|
"eval_samples_per_second": 3398.278,
|
|
"eval_steps_per_second": 424.785,
|
|
"step": 7500
|
|
},
|
|
{
|
|
"epoch": 5.02,
|
|
"learning_rate": 8.176495190296946e-06,
|
|
"loss": 0.0617,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 5.02,
|
|
"eval_accuracy": 0.9853333333333333,
|
|
"eval_loss": 0.053985536098480225,
|
|
"eval_runtime": 2.672,
|
|
"eval_samples_per_second": 3368.244,
|
|
"eval_steps_per_second": 421.03,
|
|
"step": 8000
|
|
},
|
|
{
|
|
"epoch": 5.33,
|
|
"learning_rate": 5.562526139690506e-06,
|
|
"loss": 0.0571,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"epoch": 5.33,
|
|
"eval_accuracy": 0.9847777777777778,
|
|
"eval_loss": 0.05352585390210152,
|
|
"eval_runtime": 2.7082,
|
|
"eval_samples_per_second": 3323.274,
|
|
"eval_steps_per_second": 415.409,
|
|
"step": 8500
|
|
},
|
|
{
|
|
"epoch": 5.65,
|
|
"learning_rate": 2.9485570890840656e-06,
|
|
"loss": 0.0608,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 5.65,
|
|
"eval_accuracy": 0.9851111111111112,
|
|
"eval_loss": 0.053133774548769,
|
|
"eval_runtime": 2.6753,
|
|
"eval_samples_per_second": 3364.134,
|
|
"eval_steps_per_second": 420.517,
|
|
"step": 9000
|
|
},
|
|
{
|
|
"epoch": 5.96,
|
|
"learning_rate": 3.345880384776244e-07,
|
|
"loss": 0.0571,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"epoch": 5.96,
|
|
"eval_accuracy": 0.9847777777777778,
|
|
"eval_loss": 0.05344167724251747,
|
|
"eval_runtime": 2.6425,
|
|
"eval_samples_per_second": 3405.863,
|
|
"eval_steps_per_second": 425.733,
|
|
"step": 9500
|
|
},
|
|
{
|
|
"epoch": 6.0,
|
|
"step": 9564,
|
|
"total_flos": 264960533376000.0,
|
|
"train_loss": 0.1922683648263396,
|
|
"train_runtime": 134.4457,
|
|
"train_samples_per_second": 2276.012,
|
|
"train_steps_per_second": 71.137
|
|
}
|
|
],
|
|
"max_steps": 9564,
|
|
"num_train_epochs": 6,
|
|
"total_flos": 264960533376000.0,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|