| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "patacoswin/checkpoint-25", | |
| "epoch": 9.6, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.40025946497917175, | |
| "eval_runtime": 0.9287, | |
| "eval_samples_per_second": 94.761, | |
| "eval_steps_per_second": 3.23, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5091, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.9886363636363636, | |
| "eval_loss": 0.13078118860721588, | |
| "eval_runtime": 0.8556, | |
| "eval_samples_per_second": 102.856, | |
| "eval_steps_per_second": 3.506, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.9886363636363636, | |
| "eval_loss": 0.052169933915138245, | |
| "eval_runtime": 0.8717, | |
| "eval_samples_per_second": 100.955, | |
| "eval_steps_per_second": 3.442, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1585, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.020312676206231117, | |
| "eval_runtime": 0.9631, | |
| "eval_samples_per_second": 91.376, | |
| "eval_steps_per_second": 3.115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.01556458417326212, | |
| "eval_runtime": 0.9689, | |
| "eval_samples_per_second": 90.827, | |
| "eval_steps_per_second": 3.096, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.019581861793994904, | |
| "eval_runtime": 1.1556, | |
| "eval_samples_per_second": 76.152, | |
| "eval_steps_per_second": 2.596, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0539, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.009469821117818356, | |
| "eval_runtime": 1.1414, | |
| "eval_samples_per_second": 77.101, | |
| "eval_steps_per_second": 2.628, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0397, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.008852038532495499, | |
| "eval_runtime": 1.1455, | |
| "eval_samples_per_second": 76.824, | |
| "eval_steps_per_second": 2.619, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.008850467391312122, | |
| "eval_runtime": 1.1217, | |
| "eval_samples_per_second": 78.454, | |
| "eval_steps_per_second": 2.675, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 0.0, | |
| "loss": 0.0378, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.008991248905658722, | |
| "eval_runtime": 0.8971, | |
| "eval_samples_per_second": 98.097, | |
| "eval_steps_per_second": 3.344, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "step": 60, | |
| "total_flos": 1.8776214079915622e+17, | |
| "train_loss": 0.14856800536314646, | |
| "train_runtime": 300.2682, | |
| "train_samples_per_second": 26.177, | |
| "train_steps_per_second": 0.2 | |
| } | |
| ], | |
| "max_steps": 60, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.8776214079915622e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |