|
{ |
|
"best_metric": 0.03957173973321915, |
|
"best_model_checkpoint": "./text2sql/codellama_instruct_pt_text2sql/checkpoint-4000", |
|
"epoch": 0.4455893615539929, |
|
"eval_steps": 2000, |
|
"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": 1.1139992573338283e-07, |
|
"loss": 1.2191, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.00011139992573338284, |
|
"loss": 0.2684, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00022279985146676567, |
|
"loss": 0.0693, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"eval_loss": 0.05887996032834053, |
|
"eval_runtime": 171.127, |
|
"eval_samples_per_second": 11.687, |
|
"eval_steps_per_second": 1.461, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.00029781686301467276, |
|
"loss": 0.0565, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.0002907056676227274, |
|
"loss": 0.047, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"eval_loss": 0.03957173973321915, |
|
"eval_runtime": 171.3682, |
|
"eval_samples_per_second": 11.671, |
|
"eval_steps_per_second": 1.459, |
|
"step": 4000 |
|
} |
|
], |
|
"logging_steps": 1000, |
|
"max_steps": 44880, |
|
"num_train_epochs": 5, |
|
"save_steps": 2000, |
|
"total_flos": 1.9453438627102065e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|