| { | |
| "best_metric": 3.0470073223114014, | |
| "best_model_checkpoint": "output/6ix9ine/checkpoint-84", | |
| "epoch": 2.0, | |
| "global_step": 84, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.742060843007589e-06, | |
| "loss": 3.316, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.8312641592473922e-05, | |
| "loss": 3.5414, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.88355754965355e-05, | |
| "loss": 3.3994, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.347351557997133e-05, | |
| "loss": 3.2221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.882020496458803e-05, | |
| "loss": 3.2784, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00011137140040750911, | |
| "loss": 3.376, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00012800934269961248, | |
| "loss": 3.0065, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0001364337946790438, | |
| "loss": 3.118, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.159865617752075, | |
| "eval_runtime": 2.6213, | |
| "eval_samples_per_second": 20.982, | |
| "eval_steps_per_second": 2.67, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001354800547756731, | |
| "loss": 3.1208, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00012527997991807724, | |
| "loss": 2.8559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00010724375598316453, | |
| "loss": 2.9927, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 8.386493606940326e-05, | |
| "loss": 2.9799, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5.8375700540314535e-05, | |
| "loss": 2.9474, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.4300000000000054e-05, | |
| "loss": 2.8929, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.496636030269317e-05, | |
| "loss": 2.821, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.04770552307078e-06, | |
| "loss": 2.7814, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.0470073223114014, | |
| "eval_runtime": 2.6251, | |
| "eval_samples_per_second": 20.952, | |
| "eval_steps_per_second": 2.667, | |
| "step": 84 | |
| } | |
| ], | |
| "max_steps": 84, | |
| "num_train_epochs": 2, | |
| "total_flos": 86226370560000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |