|
{ |
|
"best_metric": 2.1928138732910156, |
|
"best_model_checkpoint": "output/kipelov/checkpoint-24", |
|
"epoch": 6.0, |
|
"global_step": 24, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 2.2656543254852295, |
|
"eval_runtime": 0.4465, |
|
"eval_samples_per_second": 20.158, |
|
"eval_steps_per_second": 4.48, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 2.009247481060283e-05, |
|
"loss": 2.4041, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 2.2449731826782227, |
|
"eval_runtime": 0.4369, |
|
"eval_samples_per_second": 20.602, |
|
"eval_steps_per_second": 4.578, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 6.860000000000001e-05, |
|
"loss": 2.2367, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 2.2337002754211426, |
|
"eval_runtime": 0.4476, |
|
"eval_samples_per_second": 20.106, |
|
"eval_steps_per_second": 4.468, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 0.0001171075251893971, |
|
"loss": 2.0169, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 2.213982343673706, |
|
"eval_runtime": 0.4433, |
|
"eval_samples_per_second": 20.301, |
|
"eval_steps_per_second": 4.511, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.0, |
|
"loss": 1.9151, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 2.219846248626709, |
|
"eval_runtime": 0.4246, |
|
"eval_samples_per_second": 21.196, |
|
"eval_steps_per_second": 4.71, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 2.1928138732910156, |
|
"eval_runtime": 0.442, |
|
"eval_samples_per_second": 20.361, |
|
"eval_steps_per_second": 4.525, |
|
"step": 24 |
|
} |
|
], |
|
"max_steps": 24, |
|
"num_train_epochs": 6, |
|
"total_flos": 20380778496000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|