| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6886657101865137, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7274, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5e-05, | |
| "loss": 1.656, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7964, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6153, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7548, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7054, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7311, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6827, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7158, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6599, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6991, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6628, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6188, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6868, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6854, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5938, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6603, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5e-05, | |
| "loss": 1.561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6162, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6159, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6414, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6915, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6853, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6563, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6622, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5e-05, | |
| "loss": 1.638, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5e-05, | |
| "loss": 1.66, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6565, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 129, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "total_flos": 1.3296259208577024e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |