| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01615508885298869, | |
| "eval_steps": 500, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016155088852988692, | |
| "grad_norm": 19.076435089111328, | |
| "learning_rate": 0.0002, | |
| "loss": 3.6882, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032310177705977385, | |
| "grad_norm": 28.65721893310547, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 4.5343, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004846526655896607, | |
| "grad_norm": 14.999358177185059, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 2.9394, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006462035541195477, | |
| "grad_norm": 11.406822204589844, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3001, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008077544426494346, | |
| "grad_norm": 19.16295051574707, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 2.0175, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009693053311793215, | |
| "grad_norm": 24.336894989013672, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.4586, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011308562197092083, | |
| "grad_norm": 16.110315322875977, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.645, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012924071082390954, | |
| "grad_norm": 22.415464401245117, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 1.9302, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014539579967689823, | |
| "grad_norm": 15.96137523651123, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 1.5738, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01615508885298869, | |
| "grad_norm": 18.200040817260742, | |
| "learning_rate": 0.0, | |
| "loss": 2.0743, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01615508885298869, | |
| "eval_loss": 1.5772037506103516, | |
| "eval_runtime": 242.4638, | |
| "eval_samples_per_second": 1.237, | |
| "eval_steps_per_second": 1.237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01615508885298869, | |
| "step": 10, | |
| "total_flos": 27610747246080.0, | |
| "train_loss": 2.3161375403404234, | |
| "train_runtime": 548.0928, | |
| "train_samples_per_second": 0.018, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "total_flos": 27610747246080.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |