| { | |
| "best_metric": 6387.95458984375, | |
| "best_model_checkpoint": "./coco_outputs/checkpoint-80", | |
| "epoch": 20.0, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6394.3193359375, | |
| "eval_runtime": 0.6785, | |
| "eval_samples_per_second": 11.791, | |
| "eval_steps_per_second": 1.474, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6393.3564453125, | |
| "eval_runtime": 0.625, | |
| "eval_samples_per_second": 12.799, | |
| "eval_steps_per_second": 1.6, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.000175, | |
| "loss": 6173.6062, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6390.9482421875, | |
| "eval_runtime": 0.6116, | |
| "eval_samples_per_second": 13.08, | |
| "eval_steps_per_second": 1.635, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6389.5869140625, | |
| "eval_runtime": 0.5503, | |
| "eval_samples_per_second": 14.538, | |
| "eval_steps_per_second": 1.817, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6287.2859, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6388.72802734375, | |
| "eval_runtime": 0.5904, | |
| "eval_samples_per_second": 13.55, | |
| "eval_steps_per_second": 1.694, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6388.6220703125, | |
| "eval_runtime": 0.5392, | |
| "eval_samples_per_second": 14.837, | |
| "eval_steps_per_second": 1.855, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 6388.43994140625, | |
| "eval_runtime": 0.5365, | |
| "eval_samples_per_second": 14.91, | |
| "eval_steps_per_second": 1.864, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 0.000125, | |
| "loss": 6224.3344, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 6388.2119140625, | |
| "eval_runtime": 0.5405, | |
| "eval_samples_per_second": 14.802, | |
| "eval_steps_per_second": 1.85, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 6388.544921875, | |
| "eval_runtime": 0.5344, | |
| "eval_samples_per_second": 14.971, | |
| "eval_steps_per_second": 1.871, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0001, | |
| "loss": 6083.1363, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 6388.326171875, | |
| "eval_runtime": 0.5236, | |
| "eval_samples_per_second": 15.28, | |
| "eval_steps_per_second": 1.91, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 6390.20556640625, | |
| "eval_runtime": 0.5417, | |
| "eval_samples_per_second": 14.767, | |
| "eval_steps_per_second": 1.846, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 6388.66064453125, | |
| "eval_runtime": 0.5437, | |
| "eval_samples_per_second": 14.713, | |
| "eval_steps_per_second": 1.839, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6260.7426, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 6388.1484375, | |
| "eval_runtime": 0.5303, | |
| "eval_samples_per_second": 15.086, | |
| "eval_steps_per_second": 1.886, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 6388.0478515625, | |
| "eval_runtime": 0.5365, | |
| "eval_samples_per_second": 14.913, | |
| "eval_steps_per_second": 1.864, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 5e-05, | |
| "loss": 6377.543, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 6388.0302734375, | |
| "eval_runtime": 0.5355, | |
| "eval_samples_per_second": 14.94, | |
| "eval_steps_per_second": 1.867, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 6388.1337890625, | |
| "eval_runtime": 0.5423, | |
| "eval_samples_per_second": 14.751, | |
| "eval_steps_per_second": 1.844, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 6388.0595703125, | |
| "eval_runtime": 0.5448, | |
| "eval_samples_per_second": 14.684, | |
| "eval_steps_per_second": 1.835, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 6318.3168, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 6388.01953125, | |
| "eval_runtime": 0.5448, | |
| "eval_samples_per_second": 14.685, | |
| "eval_steps_per_second": 1.836, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 6387.9638671875, | |
| "eval_runtime": 0.5362, | |
| "eval_samples_per_second": 14.918, | |
| "eval_steps_per_second": 1.865, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 6258.2133, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 6387.95458984375, | |
| "eval_runtime": 0.544, | |
| "eval_samples_per_second": 14.705, | |
| "eval_steps_per_second": 1.838, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 80, | |
| "total_flos": 3.060008460288e+17, | |
| "train_loss": 6247.897314453125, | |
| "train_runtime": 365.3078, | |
| "train_samples_per_second": 1.752, | |
| "train_steps_per_second": 0.219 | |
| } | |
| ], | |
| "max_steps": 80, | |
| "num_train_epochs": 20, | |
| "total_flos": 3.060008460288e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |