| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0019596315892612187, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.919263178522438e-05, | |
| "eval_loss": 2.9300684928894043, | |
| "eval_runtime": 416.4401, | |
| "eval_samples_per_second": 25.8, | |
| "eval_steps_per_second": 12.9, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001959631589261219, | |
| "grad_norm": 0.554083526134491, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7355, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003919263178522438, | |
| "grad_norm": 0.6002002954483032, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8307, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003919263178522438, | |
| "eval_loss": 2.883746862411499, | |
| "eval_runtime": 411.3043, | |
| "eval_samples_per_second": 26.122, | |
| "eval_steps_per_second": 13.061, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005878894767783657, | |
| "grad_norm": 0.5967435240745544, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7021, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007838526357044876, | |
| "grad_norm": 0.7131651639938354, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7578, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007838526357044876, | |
| "eval_loss": 2.6993062496185303, | |
| "eval_runtime": 409.5738, | |
| "eval_samples_per_second": 26.232, | |
| "eval_steps_per_second": 13.116, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009798157946306093, | |
| "grad_norm": 0.7737033367156982, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.6032, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011757789535567313, | |
| "grad_norm": 0.6557625532150269, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5433, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0011757789535567313, | |
| "eval_loss": 2.614881992340088, | |
| "eval_runtime": 407.1458, | |
| "eval_samples_per_second": 26.389, | |
| "eval_steps_per_second": 13.194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013717421124828531, | |
| "grad_norm": 0.7806957960128784, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5803, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0015677052714089751, | |
| "grad_norm": 0.8234419822692871, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.5542, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0015677052714089751, | |
| "eval_loss": 2.580919027328491, | |
| "eval_runtime": 411.7251, | |
| "eval_samples_per_second": 26.095, | |
| "eval_steps_per_second": 13.048, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001763668430335097, | |
| "grad_norm": 0.8764637112617493, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.5428, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0019596315892612187, | |
| "grad_norm": 0.7842684388160706, | |
| "learning_rate": 0.0, | |
| "loss": 2.6029, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0019596315892612187, | |
| "eval_loss": 2.575305223464966, | |
| "eval_runtime": 414.8734, | |
| "eval_samples_per_second": 25.897, | |
| "eval_steps_per_second": 12.949, | |
| "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 | |
| } | |