| { | |
| "best_metric": 0.8191882967948914, | |
| "best_model_checkpoint": "./output/training_results/C019_random_sample_Meta-Llama-3-8B_instruct_20240729_013421/checkpoint-10", | |
| "epoch": 0.20833333333333334, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020833333333333332, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.0289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 12.807647290251596, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.9475, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "eval_loss": 0.9170231819152832, | |
| "eval_runtime": 0.9021, | |
| "eval_samples_per_second": 376.881, | |
| "eval_steps_per_second": 3.325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 7.514247491325009, | |
| "learning_rate": 3e-06, | |
| "loss": 1.032, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 5.115521699952678, | |
| "learning_rate": 2.7988636363636366e-06, | |
| "loss": 0.8569, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "eval_loss": 0.8191882967948914, | |
| "eval_runtime": 0.8786, | |
| "eval_samples_per_second": 386.993, | |
| "eval_steps_per_second": 3.415, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 48, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 210197544960.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |