|
{ |
|
"best_metric": 1.1020556688308716, |
|
"best_model_checkpoint": "/kaggle/output/checkpoint-4000", |
|
"epoch": 0.16297262059973924, |
|
"eval_steps": 1000, |
|
"global_step": 4000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.7777777777777777e-11, |
|
"loss": 1.2184, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.7750000000000004e-08, |
|
"loss": 1.1394, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_accuracy": 0.3327345309381238, |
|
"eval_loss": 1.1149410009384155, |
|
"eval_runtime": 20.6803, |
|
"eval_samples_per_second": 242.26, |
|
"eval_steps_per_second": 30.319, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 5.5527777777777784e-08, |
|
"loss": 1.1141, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"eval_accuracy": 0.3401197604790419, |
|
"eval_loss": 1.104099988937378, |
|
"eval_runtime": 20.8477, |
|
"eval_samples_per_second": 240.314, |
|
"eval_steps_per_second": 30.075, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 8.330555555555556e-08, |
|
"loss": 1.116, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_accuracy": 0.3407185628742515, |
|
"eval_loss": 1.1040862798690796, |
|
"eval_runtime": 20.6818, |
|
"eval_samples_per_second": 242.242, |
|
"eval_steps_per_second": 30.317, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.1108333333333333e-07, |
|
"loss": 1.1158, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"eval_accuracy": 0.32894211576846305, |
|
"eval_loss": 1.1020556688308716, |
|
"eval_runtime": 20.8541, |
|
"eval_samples_per_second": 240.241, |
|
"eval_steps_per_second": 30.066, |
|
"step": 4000 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 10000000, |
|
"num_train_epochs": 408, |
|
"save_steps": 1000, |
|
"total_flos": 2787291168768000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|