|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.019230769230769, |
|
"eval_steps": 210, |
|
"global_step": 210, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00019427890345649585, |
|
"loss": 1.0041, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.00018831942789034566, |
|
"loss": 0.9074, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.00018235995232419546, |
|
"loss": 0.9026, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0001764004767580453, |
|
"loss": 1.0049, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.00017044100119189512, |
|
"loss": 0.722, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.00016448152562574496, |
|
"loss": 0.5386, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.00015852205005959479, |
|
"loss": 0.5596, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.00015256257449344456, |
|
"loss": 0.5727, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"eval_loss": 0.25414443016052246, |
|
"eval_runtime": 539.3917, |
|
"eval_samples_per_second": 0.384, |
|
"eval_steps_per_second": 0.048, |
|
"step": 210 |
|
} |
|
], |
|
"logging_steps": 25, |
|
"max_steps": 840, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 9, |
|
"save_steps": 210, |
|
"total_flos": 3.550781121799127e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|