| { | |
| "best_metric": 6395.85986328125, | |
| "best_model_checkpoint": "./coco_outputs/checkpoint-40", | |
| "epoch": 10.0, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6398.54345703125, | |
| "eval_runtime": 0.5491, | |
| "eval_samples_per_second": 14.569, | |
| "eval_steps_per_second": 1.821, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6397.9765625, | |
| "eval_runtime": 0.5423, | |
| "eval_samples_per_second": 14.751, | |
| "eval_steps_per_second": 1.844, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 6175.8828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6397.42529296875, | |
| "eval_runtime": 0.5517, | |
| "eval_samples_per_second": 14.501, | |
| "eval_steps_per_second": 1.813, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6396.962890625, | |
| "eval_runtime": 0.555, | |
| "eval_samples_per_second": 14.415, | |
| "eval_steps_per_second": 1.802, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1e-05, | |
| "loss": 6292.3258, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6396.57177734375, | |
| "eval_runtime": 0.5448, | |
| "eval_samples_per_second": 14.685, | |
| "eval_steps_per_second": 1.836, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6396.27880859375, | |
| "eval_runtime": 0.5466, | |
| "eval_samples_per_second": 14.636, | |
| "eval_steps_per_second": 1.829, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 6396.07666015625, | |
| "eval_runtime": 0.5439, | |
| "eval_samples_per_second": 14.708, | |
| "eval_steps_per_second": 1.839, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 5e-06, | |
| "loss": 6230.4844, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 6395.9599609375, | |
| "eval_runtime": 0.5536, | |
| "eval_samples_per_second": 14.451, | |
| "eval_steps_per_second": 1.806, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 6395.8671875, | |
| "eval_runtime": 0.5708, | |
| "eval_samples_per_second": 14.015, | |
| "eval_steps_per_second": 1.752, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 6089.8695, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 6395.85986328125, | |
| "eval_runtime": 0.5496, | |
| "eval_samples_per_second": 14.557, | |
| "eval_steps_per_second": 1.82, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 40, | |
| "total_flos": 1.530004230144e+17, | |
| "train_loss": 6197.140625, | |
| "train_runtime": 176.1588, | |
| "train_samples_per_second": 1.817, | |
| "train_steps_per_second": 0.227 | |
| } | |
| ], | |
| "max_steps": 40, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.530004230144e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |