| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.449438202247191, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.5262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8831, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.6531, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 3e-05, | |
| "loss": 1.6833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.7288, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5015, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.6876, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6648, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.998766400914329e-05, | |
| "loss": 1.8044, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.995066821070679e-05, | |
| "loss": 1.6566, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.9889049115077005e-05, | |
| "loss": 1.6917, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.980286753286195e-05, | |
| "loss": 1.6271, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 1.7478, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.9557181268217227e-05, | |
| "loss": 1.606, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.939791904846869e-05, | |
| "loss": 1.6176, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 1.7205, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.900734214192358e-05, | |
| "loss": 1.5682, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 1.6807, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.852201922385564e-05, | |
| "loss": 1.6137, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.8244412147206284e-05, | |
| "loss": 1.6352, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.794386564209953e-05, | |
| "loss": 1.5979, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.762067631165049e-05, | |
| "loss": 1.6163, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.72751631047092e-08, | |
| "loss": 1.6513, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.5667160778366258e-05, | |
| "loss": 1.5181, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 110, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "total_flos": 8.938661976735744e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |