|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.960662525879917, |
|
"eval_steps": 500, |
|
"global_step": 180, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.16563146997929606, |
|
"grad_norm": 0.8955218195915222, |
|
"learning_rate": 5.555555555555556e-05, |
|
"loss": 0.9756, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.33126293995859213, |
|
"grad_norm": 0.37259799242019653, |
|
"learning_rate": 9.996239762521151e-05, |
|
"loss": 0.7282, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.4968944099378882, |
|
"grad_norm": 0.28891804814338684, |
|
"learning_rate": 9.865224352899119e-05, |
|
"loss": 0.6395, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.6625258799171843, |
|
"grad_norm": 0.25443747639656067, |
|
"learning_rate": 9.551814704830734e-05, |
|
"loss": 0.6083, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.8281573498964804, |
|
"grad_norm": 0.24764384329319, |
|
"learning_rate": 9.067760351314838e-05, |
|
"loss": 0.5758, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.9937888198757764, |
|
"grad_norm": 0.23618632555007935, |
|
"learning_rate": 8.43120818934367e-05, |
|
"loss": 0.5795, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.1490683229813665, |
|
"grad_norm": 0.2306116223335266, |
|
"learning_rate": 7.666022164008457e-05, |
|
"loss": 0.5475, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.3146997929606625, |
|
"grad_norm": 0.25390660762786865, |
|
"learning_rate": 6.800888624023553e-05, |
|
"loss": 0.5384, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.4803312629399585, |
|
"grad_norm": 0.25627601146698, |
|
"learning_rate": 5.868240888334653e-05, |
|
"loss": 0.5292, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.6459627329192545, |
|
"grad_norm": 0.23274940252304077, |
|
"learning_rate": 4.903043341140879e-05, |
|
"loss": 0.5279, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.8115942028985508, |
|
"grad_norm": 0.23897747695446014, |
|
"learning_rate": 3.941480638852948e-05, |
|
"loss": 0.5333, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.9772256728778468, |
|
"grad_norm": 0.2356269806623459, |
|
"learning_rate": 3.019601169804216e-05, |
|
"loss": 0.5206, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 2.132505175983437, |
|
"grad_norm": 0.23969200253486633, |
|
"learning_rate": 2.171965622567308e-05, |
|
"loss": 0.5124, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 2.298136645962733, |
|
"grad_norm": 0.24637186527252197, |
|
"learning_rate": 1.4303513272105057e-05, |
|
"loss": 0.5074, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 2.463768115942029, |
|
"grad_norm": 0.24429979920387268, |
|
"learning_rate": 8.225609429353187e-06, |
|
"loss": 0.5153, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 2.629399585921325, |
|
"grad_norm": 0.21919749677181244, |
|
"learning_rate": 3.7138015365554833e-06, |
|
"loss": 0.517, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 2.795031055900621, |
|
"grad_norm": 0.22401317954063416, |
|
"learning_rate": 9.372344686307655e-07, |
|
"loss": 0.5029, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 2.960662525879917, |
|
"grad_norm": 0.22402963042259216, |
|
"learning_rate": 0.0, |
|
"loss": 0.5117, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 2.960662525879917, |
|
"step": 180, |
|
"total_flos": 2.456263200690143e+18, |
|
"train_loss": 0.5761387454138862, |
|
"train_runtime": 2753.0677, |
|
"train_samples_per_second": 12.63, |
|
"train_steps_per_second": 0.065 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 180, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.456263200690143e+18, |
|
"train_batch_size": 6, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|