| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015167793718005435, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.055931239335145e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 58.7951, | |
| "eval_samples_per_second": 141.644, | |
| "eval_steps_per_second": 70.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015167793718005436, | |
| "grad_norm": 3.556181400199421e-05, | |
| "learning_rate": 3e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00025279656196675726, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 58.8879, | |
| "eval_samples_per_second": 141.421, | |
| "eval_steps_per_second": 70.711, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00030335587436010873, | |
| "grad_norm": 2.5178358555422164e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00045503381154016307, | |
| "grad_norm": 1.8990722310263664e-05, | |
| "learning_rate": 9e-05, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005055931239335145, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 58.7378, | |
| "eval_samples_per_second": 141.783, | |
| "eval_steps_per_second": 70.891, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006067117487202175, | |
| "grad_norm": 2.447623228363227e-05, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007583896859002717, | |
| "grad_norm": 2.218727058789227e-05, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007583896859002717, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 59.2136, | |
| "eval_samples_per_second": 140.643, | |
| "eval_steps_per_second": 70.322, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009100676230803261, | |
| "grad_norm": 4.8929170588962734e-05, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001011186247867029, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 59.2385, | |
| "eval_samples_per_second": 140.584, | |
| "eval_steps_per_second": 70.292, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010617455602603804, | |
| "grad_norm": 1.8329679733142257e-05, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001213423497440435, | |
| "grad_norm": 2.1915997422183864e-05, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 46.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0012639828098337863, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 59.078, | |
| "eval_samples_per_second": 140.966, | |
| "eval_steps_per_second": 70.483, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013651014346204892, | |
| "grad_norm": 2.4743134417803958e-05, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 46.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0015167793718005435, | |
| "grad_norm": 5.412183963926509e-05, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015167793718005435, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 59.0675, | |
| "eval_samples_per_second": 140.991, | |
| "eval_steps_per_second": 70.496, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1635739631616.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |