| { |
| "best_metric": 0.01533749233931303, |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-200", |
| "epoch": 4.0, |
| "eval_steps": 100, |
| "global_step": 260, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15384615384615385, |
| "grad_norm": 1.5216917991638184, |
| "learning_rate": 0.00019230769230769233, |
| "loss": 0.8157, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 2.2351748943328857, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.3243, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 2.941770553588867, |
| "learning_rate": 0.00017692307692307693, |
| "loss": 0.2718, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 1.8948721885681152, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.2155, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 0.4624975323677063, |
| "learning_rate": 0.00016153846153846155, |
| "loss": 0.1779, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.38448768854141235, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 0.2878, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 1.9322333335876465, |
| "learning_rate": 0.00014615384615384615, |
| "loss": 0.1584, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.16839705407619476, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 0.0937, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 0.784092366695404, |
| "learning_rate": 0.00013076923076923077, |
| "loss": 0.0919, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 1.2771739959716797, |
| "learning_rate": 0.0001230769230769231, |
| "loss": 0.1884, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "eval_accuracy": 0.9323308270676691, |
| "eval_loss": 0.18749678134918213, |
| "eval_runtime": 1.1823, |
| "eval_samples_per_second": 112.492, |
| "eval_steps_per_second": 14.379, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 4.073795318603516, |
| "learning_rate": 0.00011538461538461538, |
| "loss": 0.1316, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 0.12293587625026703, |
| "learning_rate": 0.0001076923076923077, |
| "loss": 0.1192, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.3345961570739746, |
| "learning_rate": 0.0001, |
| "loss": 0.048, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 0.29758933186531067, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.0756, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 3.1539885997772217, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.0255, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 0.2040480673313141, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.0313, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 0.09263844788074493, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.0543, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 0.09043588489294052, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.0151, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 0.07583910971879959, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.0151, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 0.069760762155056, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.0213, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "eval_accuracy": 1.0, |
| "eval_loss": 0.01533749233931303, |
| "eval_runtime": 1.1637, |
| "eval_samples_per_second": 114.288, |
| "eval_steps_per_second": 14.608, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.230769230769231, |
| "grad_norm": 0.0645805299282074, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.0177, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "grad_norm": 0.06892526894807816, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.0123, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.5384615384615383, |
| "grad_norm": 0.06642979383468628, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.0119, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "grad_norm": 0.06364436447620392, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.0118, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "grad_norm": 0.0647491067647934, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.0206, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.05726522207260132, |
| "learning_rate": 0.0, |
| "loss": 0.0119, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 260, |
| "total_flos": 3.205097416476426e+17, |
| "train_loss": 0.12495187549636914, |
| "train_runtime": 51.7133, |
| "train_samples_per_second": 79.979, |
| "train_steps_per_second": 5.028 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 260, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.205097416476426e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
