|
{ |
|
"best_metric": 2.246587038040161, |
|
"best_model_checkpoint": "clip-homer-10k/checkpoint-939", |
|
"epoch": 3.0, |
|
"global_step": 939, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 2.526189088821411, |
|
"eval_runtime": 97.3872, |
|
"eval_samples_per_second": 102.683, |
|
"eval_steps_per_second": 3.214, |
|
"step": 313 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 2.3375931842385517e-05, |
|
"loss": 2.4844, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 2.286365509033203, |
|
"eval_runtime": 96.4083, |
|
"eval_samples_per_second": 103.726, |
|
"eval_steps_per_second": 3.247, |
|
"step": 626 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 2.246587038040161, |
|
"eval_runtime": 97.3562, |
|
"eval_samples_per_second": 102.716, |
|
"eval_steps_per_second": 3.215, |
|
"step": 939 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 939, |
|
"total_flos": 3012083735040000.0, |
|
"train_loss": 1.8158518635807708, |
|
"train_runtime": 987.3035, |
|
"train_samples_per_second": 30.386, |
|
"train_steps_per_second": 0.951 |
|
} |
|
], |
|
"max_steps": 939, |
|
"num_train_epochs": 3, |
|
"total_flos": 3012083735040000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|