| { | |
| "best_metric": 1.7263113260269165, | |
| "best_model_checkpoint": "output/platina/checkpoint-86", | |
| "epoch": 1.0, | |
| "global_step": 86, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00013605888543050137, | |
| "loss": 2.653, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001326735050590528, | |
| "loss": 2.339, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00012715648590796197, | |
| "loss": 2.2005, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011969137173622343, | |
| "loss": 2.1397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00011052651678711246, | |
| "loss": 2.05, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.99668233786982e-05, | |
| "loss": 1.9257, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.83635982164553e-05, | |
| "loss": 1.9766, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.61028648947222e-05, | |
| "loss": 1.9569, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.359252141426174e-05, | |
| "loss": 1.9599, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.1248769967930697e-05, | |
| "loss": 1.8944, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9482270457119095e-05, | |
| "loss": 1.8734, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.8684478392724447e-05, | |
| "loss": 1.8827, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.9214621700201495e-05, | |
| "loss": 1.8779, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1387749692754382e-05, | |
| "loss": 1.776, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.464251807155671e-06, | |
| "loss": 1.8927, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6411947996634035e-06, | |
| "loss": 1.8982, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.576660180157781e-08, | |
| "loss": 1.8376, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.7263113260269165, | |
| "eval_runtime": 6.7602, | |
| "eval_samples_per_second": 21.153, | |
| "eval_steps_per_second": 2.663, | |
| "step": 86 | |
| } | |
| ], | |
| "max_steps": 86, | |
| "num_train_epochs": 1, | |
| "total_flos": 88969936896000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |