| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1044776119402986, | |
| "eval_steps": 25, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 187.5657196044922, | |
| "learning_rate": 9.869238178417235e-05, | |
| "loss": 268.6396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "eval_loss": 7.768074989318848, | |
| "eval_runtime": 3.7944, | |
| "eval_samples_per_second": 13.177, | |
| "eval_steps_per_second": 3.426, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 197.3665771484375, | |
| "learning_rate": 9.484552115439445e-05, | |
| "loss": 250.5417, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 231.86390686035156, | |
| "learning_rate": 8.868298366769954e-05, | |
| "loss": 216.0356, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 239.8871612548828, | |
| "learning_rate": 8.056291360290201e-05, | |
| "loss": 174.3789, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 211.5499267578125, | |
| "learning_rate": 7.095721991691411e-05, | |
| "loss": 138.662, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 164.4355926513672, | |
| "learning_rate": 6.042415061148954e-05, | |
| "loss": 117.3982, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 123.97122955322266, | |
| "learning_rate": 4.9575849388510473e-05, | |
| "loss": 99.5028, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 116.63461303710938, | |
| "learning_rate": 3.904278008308589e-05, | |
| "loss": 83.9796, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.1492537313432836, | |
| "grad_norm": 91.13107299804688, | |
| "learning_rate": 2.9437086397097995e-05, | |
| "loss": 76.7865, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.388059701492537, | |
| "grad_norm": 104.27659606933594, | |
| "learning_rate": 2.1317016332300447e-05, | |
| "loss": 67.7161, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.626865671641791, | |
| "grad_norm": 113.9940414428711, | |
| "learning_rate": 1.515447884560556e-05, | |
| "loss": 60.085, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.8656716417910446, | |
| "grad_norm": 109.60016632080078, | |
| "learning_rate": 1.130761821582766e-05, | |
| "loss": 55.9485, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.1044776119402986, | |
| "grad_norm": 108.47245788574219, | |
| "learning_rate": 1e-05, | |
| "loss": 52.9041, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.367380642014167e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |