| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0040710810755796205, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.14216215115924e-05, | |
| "eval_loss": 2.5727338790893555, | |
| "eval_runtime": 658.2171, | |
| "eval_samples_per_second": 7.858, | |
| "eval_steps_per_second": 3.929, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040710810755796204, | |
| "grad_norm": 3.0211687088012695, | |
| "learning_rate": 5e-05, | |
| "loss": 9.7985, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008142162151159241, | |
| "grad_norm": 6.464580059051514, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5411, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008142162151159241, | |
| "eval_loss": 2.4812233448028564, | |
| "eval_runtime": 659.0524, | |
| "eval_samples_per_second": 7.848, | |
| "eval_steps_per_second": 3.924, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001221324322673886, | |
| "grad_norm": 5.925446033477783, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.8945, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016284324302318482, | |
| "grad_norm": 5.2060627937316895, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 8.0616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016284324302318482, | |
| "eval_loss": 1.9567166566848755, | |
| "eval_runtime": 658.6062, | |
| "eval_samples_per_second": 7.853, | |
| "eval_steps_per_second": 3.926, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0020355405377898103, | |
| "grad_norm": 5.045373439788818, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.3318, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002442648645347772, | |
| "grad_norm": 5.303926944732666, | |
| "learning_rate": 5e-05, | |
| "loss": 6.6681, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002442648645347772, | |
| "eval_loss": 1.8020665645599365, | |
| "eval_runtime": 658.8639, | |
| "eval_samples_per_second": 7.85, | |
| "eval_steps_per_second": 3.925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002849756752905734, | |
| "grad_norm": 4.578883647918701, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.3411, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0032568648604636963, | |
| "grad_norm": 5.8388895988464355, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.4617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032568648604636963, | |
| "eval_loss": 1.772756576538086, | |
| "eval_runtime": 659.8056, | |
| "eval_samples_per_second": 7.839, | |
| "eval_steps_per_second": 3.919, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003663972968021658, | |
| "grad_norm": 5.17460823059082, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.0335, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0040710810755796205, | |
| "grad_norm": 6.099168300628662, | |
| "learning_rate": 0.0, | |
| "loss": 7.0876, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0040710810755796205, | |
| "eval_loss": 1.7677820920944214, | |
| "eval_runtime": 659.1629, | |
| "eval_samples_per_second": 7.846, | |
| "eval_steps_per_second": 3.923, | |
| "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": 8536966412894208.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |