|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.6666666666666665, |
|
"eval_steps": 500, |
|
"global_step": 6, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.44, |
|
"grad_norm": 6.008237230982008, |
|
"learning_rate": 2e-05, |
|
"loss": 1.2606, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"eval_loss": 2.266657829284668, |
|
"eval_runtime": 28.2854, |
|
"eval_samples_per_second": 11.596, |
|
"eval_steps_per_second": 0.742, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"eval_loss": 1.4257351160049438, |
|
"eval_runtime": 27.8495, |
|
"eval_samples_per_second": 11.778, |
|
"eval_steps_per_second": 0.754, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"grad_norm": 21.372843769871217, |
|
"learning_rate": 1.9098300562505266e-06, |
|
"loss": 1.8405, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"eval_loss": 1.301017165184021, |
|
"eval_runtime": 27.912, |
|
"eval_samples_per_second": 11.751, |
|
"eval_steps_per_second": 0.752, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"step": 6, |
|
"total_flos": 1203933020160.0, |
|
"train_loss": 1.648087501525879, |
|
"train_runtime": 194.9727, |
|
"train_samples_per_second": 2.016, |
|
"train_steps_per_second": 0.031 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 6, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 1203933020160.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|