| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03912363067292645, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000782472613458529, | |
| "eval_loss": 2.958402156829834, | |
| "eval_runtime": 46.5071, | |
| "eval_samples_per_second": 11.59, | |
| "eval_steps_per_second": 5.806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003912363067292645, | |
| "grad_norm": 43.248687744140625, | |
| "learning_rate": 5e-05, | |
| "loss": 12.3132, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00782472613458529, | |
| "grad_norm": 28.396343231201172, | |
| "learning_rate": 0.0001, | |
| "loss": 9.0016, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00782472613458529, | |
| "eval_loss": 2.361903429031372, | |
| "eval_runtime": 49.2786, | |
| "eval_samples_per_second": 10.938, | |
| "eval_steps_per_second": 5.479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011737089201877934, | |
| "grad_norm": 34.012107849121094, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.6879, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "grad_norm": 23.336244583129883, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.9045, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "eval_loss": 2.1685376167297363, | |
| "eval_runtime": 50.1924, | |
| "eval_samples_per_second": 10.739, | |
| "eval_steps_per_second": 5.379, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019561815336463225, | |
| "grad_norm": 27.332406997680664, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 8.901, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023474178403755867, | |
| "grad_norm": 44.51591873168945, | |
| "learning_rate": 5e-05, | |
| "loss": 8.1831, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023474178403755867, | |
| "eval_loss": 2.0748794078826904, | |
| "eval_runtime": 50.4777, | |
| "eval_samples_per_second": 10.678, | |
| "eval_steps_per_second": 5.349, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027386541471048513, | |
| "grad_norm": 26.267230987548828, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 7.1613, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03129890453834116, | |
| "grad_norm": 26.749197006225586, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.7224, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03129890453834116, | |
| "eval_loss": 2.012913465499878, | |
| "eval_runtime": 50.7063, | |
| "eval_samples_per_second": 10.63, | |
| "eval_steps_per_second": 5.325, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.035211267605633804, | |
| "grad_norm": 30.452207565307617, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 8.1557, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03912363067292645, | |
| "grad_norm": 27.994192123413086, | |
| "learning_rate": 0.0, | |
| "loss": 7.033, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03912363067292645, | |
| "eval_loss": 2.0008180141448975, | |
| "eval_runtime": 50.7354, | |
| "eval_samples_per_second": 10.624, | |
| "eval_steps_per_second": 5.322, | |
| "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": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |