| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022698899103393486, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00045397798206786973, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.1267, | |
| "eval_samples_per_second": 25.687, | |
| "eval_steps_per_second": 12.844, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022698899103393484, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004539779820678697, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004539779820678697, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.6735, | |
| "eval_samples_per_second": 26.014, | |
| "eval_steps_per_second": 13.007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0068096697310180455, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009079559641357393, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009079559641357393, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.7496, | |
| "eval_samples_per_second": 25.958, | |
| "eval_steps_per_second": 12.979, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011349449551696743, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013619339462036091, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013619339462036091, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.6909, | |
| "eval_samples_per_second": 26.001, | |
| "eval_steps_per_second": 13.001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01588922937237544, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018159119282714787, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018159119282714787, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.7175, | |
| "eval_samples_per_second": 25.982, | |
| "eval_steps_per_second": 12.991, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020429009193054137, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.022698899103393486, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022698899103393486, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.6905, | |
| "eval_samples_per_second": 26.001, | |
| "eval_steps_per_second": 13.001, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1621491292569600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |