| { | |
| "best_metric": 2.0006659030914307, | |
| "best_model_checkpoint": "./lora-redpajama/checkpoint-200", | |
| "epoch": 0.9153318077803204, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 5.6682, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 5.1317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.1627, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 3.1593, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00015, | |
| "loss": 2.6813, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.4024, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.3087, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.2026, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00027, | |
| "loss": 2.1257, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 2.118, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002945848375451263, | |
| "loss": 2.076, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00028916967509025267, | |
| "loss": 2.0684, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000283754512635379, | |
| "loss": 2.0212, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00027833935018050537, | |
| "loss": 2.0192, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00027292418772563177, | |
| "loss": 1.9991, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002675090252707581, | |
| "loss": 2.0075, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00026209386281588447, | |
| "loss": 2.0414, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002566787003610108, | |
| "loss": 2.0048, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00025126353790613716, | |
| "loss": 1.9604, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002458483754512635, | |
| "loss": 1.9739, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 2.0006659030914307, | |
| "eval_runtime": 83.0225, | |
| "eval_samples_per_second": 24.09, | |
| "eval_steps_per_second": 0.602, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 654, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.0791481950273536e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |