| { | |
| "best_metric": 6787.48388671875, | |
| "best_model_checkpoint": "./coco_outputs/checkpoint-20", | |
| "epoch": 5.0, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6788.2998046875, | |
| "eval_runtime": 2.0726, | |
| "eval_samples_per_second": 15.44, | |
| "eval_steps_per_second": 1.93, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6787.97509765625, | |
| "eval_runtime": 2.0833, | |
| "eval_samples_per_second": 15.361, | |
| "eval_steps_per_second": 1.92, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1e-05, | |
| "loss": 6175.932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6787.7900390625, | |
| "eval_runtime": 2.1929, | |
| "eval_samples_per_second": 14.592, | |
| "eval_steps_per_second": 1.824, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6787.5068359375, | |
| "eval_runtime": 2.0906, | |
| "eval_samples_per_second": 15.307, | |
| "eval_steps_per_second": 1.913, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 6292.5953, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6787.48388671875, | |
| "eval_runtime": 2.2266, | |
| "eval_samples_per_second": 14.372, | |
| "eval_steps_per_second": 1.796, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 20, | |
| "total_flos": 7.65002115072e+16, | |
| "train_loss": 6234.263671875, | |
| "train_runtime": 98.3256, | |
| "train_samples_per_second": 1.627, | |
| "train_steps_per_second": 0.203 | |
| } | |
| ], | |
| "max_steps": 20, | |
| "num_train_epochs": 5, | |
| "total_flos": 7.65002115072e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |