| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0031799872800508796, | |
| "eval_steps": 2, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021199915200339198, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021199915200339198, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.7903, | |
| "eval_samples_per_second": 111.69, | |
| "eval_steps_per_second": 55.873, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042399830400678397, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042399830400678397, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.3023, | |
| "eval_samples_per_second": 121.884, | |
| "eval_steps_per_second": 60.973, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006359974560101759, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008479966080135679, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008479966080135679, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.3327, | |
| "eval_samples_per_second": 121.658, | |
| "eval_steps_per_second": 60.86, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00105999576001696, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012719949120203519, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012719949120203519, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0984, | |
| "eval_samples_per_second": 123.428, | |
| "eval_steps_per_second": 61.745, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001483994064023744, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016959932160271359, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0016959932160271359, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2618, | |
| "eval_samples_per_second": 122.188, | |
| "eval_steps_per_second": 61.125, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019079923680305278, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00211999152003392, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00211999152003392, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.3665, | |
| "eval_samples_per_second": 121.407, | |
| "eval_steps_per_second": 60.734, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002331990672037312, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0025439898240407037, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0025439898240407037, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.138, | |
| "eval_samples_per_second": 123.126, | |
| "eval_steps_per_second": 61.594, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002755988976044096, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002967988128047488, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002967988128047488, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1354, | |
| "eval_samples_per_second": 123.146, | |
| "eval_steps_per_second": 61.604, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0031799872800508796, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 58580762886144.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |