DanielSc4's picture
End of training
25acc3f
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6410256410256411,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 2.9999999999999997e-05,
"loss": 3.2268,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 5.9999999999999995e-05,
"loss": 2.9252,
"step": 20
},
{
"epoch": 0.13,
"learning_rate": 8.999999999999999e-05,
"loss": 2.3646,
"step": 30
},
{
"epoch": 0.17,
"learning_rate": 0.00011999999999999999,
"loss": 2.1557,
"step": 40
},
{
"epoch": 0.21,
"learning_rate": 0.00015,
"loss": 2.0691,
"step": 50
},
{
"epoch": 0.26,
"learning_rate": 0.00017999999999999998,
"loss": 2.0406,
"step": 60
},
{
"epoch": 0.3,
"learning_rate": 0.00020999999999999998,
"loss": 1.9427,
"step": 70
},
{
"epoch": 0.34,
"learning_rate": 0.00023999999999999998,
"loss": 1.9141,
"step": 80
},
{
"epoch": 0.38,
"learning_rate": 0.00027,
"loss": 1.847,
"step": 90
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 1.8292,
"step": 100
},
{
"epoch": 0.47,
"learning_rate": 0.00029501661129568106,
"loss": 1.7893,
"step": 110
},
{
"epoch": 0.51,
"learning_rate": 0.0002900332225913621,
"loss": 1.7282,
"step": 120
},
{
"epoch": 0.56,
"learning_rate": 0.0002850498338870432,
"loss": 1.7105,
"step": 130
},
{
"epoch": 0.6,
"learning_rate": 0.0002800664451827242,
"loss": 1.6879,
"step": 140
},
{
"epoch": 0.64,
"learning_rate": 0.0002750830564784053,
"loss": 1.6557,
"step": 150
}
],
"max_steps": 702,
"num_train_epochs": 3,
"total_flos": 4.419104855723213e+16,
"trial_name": null,
"trial_params": null
}