| { | |
| "best_metric": 0.8130785822868347, | |
| "best_model_checkpoint": "./output/training_results/C016_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": 0.9436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 12.096153820022398, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.8831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "eval_loss": 0.9745497703552246, | |
| "eval_runtime": 0.8965, | |
| "eval_samples_per_second": 379.234, | |
| "eval_steps_per_second": 3.346, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 12.679338633930682, | |
| "learning_rate": 2.25e-06, | |
| "loss": 1.005, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 5.5871426338146755, | |
| "learning_rate": 2.865909090909091e-06, | |
| "loss": 0.8656, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "eval_loss": 0.8130785822868347, | |
| "eval_runtime": 0.8787, | |
| "eval_samples_per_second": 386.937, | |
| "eval_steps_per_second": 3.414, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 48, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 208255057920.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |