| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026860059092130004, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005372011818426001, | |
| "eval_loss": 0.18501441180706024, | |
| "eval_runtime": 79.5189, | |
| "eval_samples_per_second": 9.859, | |
| "eval_steps_per_second": 4.93, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026860059092130005, | |
| "grad_norm": 0.7118232250213623, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6911, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005372011818426001, | |
| "grad_norm": 0.3719102740287781, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6331, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005372011818426001, | |
| "eval_loss": 0.1662459820508957, | |
| "eval_runtime": 79.9488, | |
| "eval_samples_per_second": 9.806, | |
| "eval_steps_per_second": 4.903, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008058017727639, | |
| "grad_norm": 0.5022017955780029, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6189, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010744023636852002, | |
| "grad_norm": 0.42121511697769165, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4692, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010744023636852002, | |
| "eval_loss": 0.12234125286340714, | |
| "eval_runtime": 80.4411, | |
| "eval_samples_per_second": 9.746, | |
| "eval_steps_per_second": 4.873, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013430029546065002, | |
| "grad_norm": 0.5769535303115845, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.493, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016116035455278, | |
| "grad_norm": 0.3808046877384186, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4076, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016116035455278, | |
| "eval_loss": 0.10152747482061386, | |
| "eval_runtime": 80.2919, | |
| "eval_samples_per_second": 9.764, | |
| "eval_steps_per_second": 4.882, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018802041364491002, | |
| "grad_norm": 0.31879931688308716, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3137, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.021488047273704004, | |
| "grad_norm": 0.5185353755950928, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.394, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.021488047273704004, | |
| "eval_loss": 0.0965627133846283, | |
| "eval_runtime": 80.2685, | |
| "eval_samples_per_second": 9.767, | |
| "eval_steps_per_second": 4.884, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.024174053182917002, | |
| "grad_norm": 0.3682008981704712, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3557, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026860059092130004, | |
| "grad_norm": 0.5637223124504089, | |
| "learning_rate": 0.0, | |
| "loss": 0.4302, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026860059092130004, | |
| "eval_loss": 0.09565096348524094, | |
| "eval_runtime": 80.1864, | |
| "eval_samples_per_second": 9.777, | |
| "eval_steps_per_second": 4.889, | |
| "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": 8720557088440320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |