| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7565011820330969, | |
| "eval_steps": 10, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0252167060677699, | |
| "grad_norm": 0.1355619877576828, | |
| "learning_rate": 5e-05, | |
| "loss": 11.932, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0252167060677699, | |
| "eval_loss": 11.934293746948242, | |
| "eval_runtime": 3.4042, | |
| "eval_samples_per_second": 78.727, | |
| "eval_steps_per_second": 19.682, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0504334121355398, | |
| "grad_norm": 0.1327255219221115, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9325, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07565011820330969, | |
| "grad_norm": 0.14952348172664642, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 11.9329, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1008668242710796, | |
| "grad_norm": 0.1367342323064804, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 11.9322, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12608353033884948, | |
| "grad_norm": 0.14394749701023102, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 11.9321, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15130023640661938, | |
| "grad_norm": 0.13902953267097473, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 11.9303, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1765169424743893, | |
| "grad_norm": 0.16207095980644226, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 11.929, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2017336485421592, | |
| "grad_norm": 0.17109227180480957, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 11.9289, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 0.18327724933624268, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 11.9282, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25216706067769895, | |
| "grad_norm": 0.17470045387744904, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 11.9248, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25216706067769895, | |
| "eval_loss": 11.928186416625977, | |
| "eval_runtime": 2.9094, | |
| "eval_samples_per_second": 92.116, | |
| "eval_steps_per_second": 23.029, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2773837667454689, | |
| "grad_norm": 0.1625070571899414, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 11.9293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.30260047281323876, | |
| "grad_norm": 0.18875440955162048, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 11.9261, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.32781717888100864, | |
| "grad_norm": 0.17575034499168396, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 11.9265, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3530338849487786, | |
| "grad_norm": 0.19419781863689423, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 11.9246, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.37825059101654845, | |
| "grad_norm": 0.2197292596101761, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 11.925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4034672970843184, | |
| "grad_norm": 0.21017210185527802, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 11.923, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.42868400315208827, | |
| "grad_norm": 0.2026052176952362, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 11.924, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": 0.23036272823810577, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 11.9226, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4791174152876281, | |
| "grad_norm": 0.22065575420856476, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 11.9186, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5043341213553979, | |
| "grad_norm": 0.24293360114097595, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 11.92, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5043341213553979, | |
| "eval_loss": 11.920666694641113, | |
| "eval_runtime": 2.907, | |
| "eval_samples_per_second": 92.192, | |
| "eval_steps_per_second": 23.048, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5295508274231678, | |
| "grad_norm": 0.23226885497570038, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9191, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5547675334909378, | |
| "grad_norm": 0.23677287995815277, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 11.9191, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5799842395587076, | |
| "grad_norm": 0.24115414917469025, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 11.9169, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6052009456264775, | |
| "grad_norm": 0.23872853815555573, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 11.9193, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6304176516942475, | |
| "grad_norm": 0.24184449017047882, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 11.9191, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6556343577620173, | |
| "grad_norm": 0.2603144645690918, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 11.9174, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 0.26540812849998474, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 11.916, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7060677698975572, | |
| "grad_norm": 0.2523845136165619, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 11.9157, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.731284475965327, | |
| "grad_norm": 0.24367552995681763, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 11.9162, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "grad_norm": 0.25121253728866577, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 11.9183, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7565011820330969, | |
| "eval_loss": 11.915938377380371, | |
| "eval_runtime": 2.9116, | |
| "eval_samples_per_second": 92.045, | |
| "eval_steps_per_second": 23.011, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 487493216501760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |