| { | |
| "best_metric": 0.895, | |
| "best_model_checkpoint": "/content/food_model/checkpoint-186", | |
| "epoch": 2.976, | |
| "global_step": 186, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 4.5912, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.970059880239521e-05, | |
| "loss": 4.331, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.670658682634731e-05, | |
| "loss": 3.7662, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.3712574850299406e-05, | |
| "loss": 3.3298, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.07185628742515e-05, | |
| "loss": 2.9877, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.7724550898203595e-05, | |
| "loss": 2.7035, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.838, | |
| "eval_loss": 2.518724203109741, | |
| "eval_runtime": 16.8835, | |
| "eval_samples_per_second": 59.229, | |
| "eval_steps_per_second": 3.731, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.473053892215569e-05, | |
| "loss": 2.4774, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1736526946107784e-05, | |
| "loss": 2.3063, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.874251497005988e-05, | |
| "loss": 2.1392, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.5748502994011976e-05, | |
| "loss": 2.013, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.275449101796407e-05, | |
| "loss": 1.9096, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.9760479041916168e-05, | |
| "loss": 1.8477, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.886, | |
| "eval_loss": 1.758641004562378, | |
| "eval_runtime": 16.9689, | |
| "eval_samples_per_second": 58.931, | |
| "eval_steps_per_second": 3.713, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.6766467065868263e-05, | |
| "loss": 1.7657, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.377245508982036e-05, | |
| "loss": 1.7272, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.0778443113772455e-05, | |
| "loss": 1.6659, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.784431137724551e-06, | |
| "loss": 1.6114, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.7904191616766475e-06, | |
| "loss": 1.63, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.7964071856287426e-06, | |
| "loss": 1.6385, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.895, | |
| "eval_loss": 1.6015000343322754, | |
| "eval_runtime": 16.9332, | |
| "eval_samples_per_second": 59.056, | |
| "eval_steps_per_second": 3.721, | |
| "step": 186 | |
| } | |
| ], | |
| "max_steps": 186, | |
| "num_train_epochs": 3, | |
| "total_flos": 9.232831524962304e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |