| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.019417947037549455, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.708973518774727e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 156.1462, | |
| "eval_samples_per_second": 27.775, | |
| "eval_steps_per_second": 13.891, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009708973518774728, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9905, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019417947037549455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 10.0925, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002912692055632418, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4352, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003883589407509891, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004854486759387364, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 197.5375, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004854486759387364, | |
| "eval_loss": NaN, | |
| "eval_runtime": 154.1495, | |
| "eval_samples_per_second": 28.135, | |
| "eval_steps_per_second": 14.071, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005825384111264836, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00679628146314231, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 331.5758, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.007767178815019782, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.008738076166897256, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 5.5299, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.009708973518774727, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 1.023, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.009708973518774727, | |
| "eval_loss": NaN, | |
| "eval_runtime": 154.0904, | |
| "eval_samples_per_second": 28.146, | |
| "eval_steps_per_second": 14.076, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0106798708706522, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 6.0712, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.011650768222529672, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.217, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.012621665574407146, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4564, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01359256292628462, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 4.3601, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.014563460278162091, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 2.635, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.014563460278162091, | |
| "eval_loss": NaN, | |
| "eval_runtime": 154.1373, | |
| "eval_samples_per_second": 28.137, | |
| "eval_steps_per_second": 14.072, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.015534357630039564, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9052, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.016505254981917038, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01747615233379451, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01844704968567198, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 15.7935, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.019417947037549455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0935, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.019417947037549455, | |
| "eval_loss": NaN, | |
| "eval_runtime": 154.0929, | |
| "eval_samples_per_second": 28.145, | |
| "eval_steps_per_second": 14.076, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.166974809361613e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |