| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023980815347721823, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007993605115907274, | |
| "eval_loss": 10.378289222717285, | |
| "eval_runtime": 3.8659, | |
| "eval_samples_per_second": 136.318, | |
| "eval_steps_per_second": 68.289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002398081534772182, | |
| "grad_norm": 0.02134803868830204, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004796163069544364, | |
| "grad_norm": 0.023500343784689903, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3787, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006394884092725819, | |
| "eval_loss": 10.378135681152344, | |
| "eval_runtime": 3.8579, | |
| "eval_samples_per_second": 136.602, | |
| "eval_steps_per_second": 68.43, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007194244604316547, | |
| "grad_norm": 0.023381192237138748, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3798, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009592326139088728, | |
| "grad_norm": 0.021697159856557846, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3783, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011990407673860911, | |
| "grad_norm": 0.023643912747502327, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3788, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012789768185451638, | |
| "eval_loss": 10.377732276916504, | |
| "eval_runtime": 3.896, | |
| "eval_samples_per_second": 135.266, | |
| "eval_steps_per_second": 67.762, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014388489208633094, | |
| "grad_norm": 0.027424972504377365, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3787, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016786570743405275, | |
| "grad_norm": 0.023296209052205086, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 10.3789, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019184652278177457, | |
| "grad_norm": 0.023096146062016487, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.3793, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.019184652278177457, | |
| "eval_loss": 10.377493858337402, | |
| "eval_runtime": 3.8926, | |
| "eval_samples_per_second": 135.384, | |
| "eval_steps_per_second": 67.821, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02158273381294964, | |
| "grad_norm": 0.023451387882232666, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 10.3782, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023980815347721823, | |
| "grad_norm": 0.025783749297261238, | |
| "learning_rate": 0.0, | |
| "loss": 10.3769, | |
| "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": 1170267242496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |