| { |
| "best_metric": 0.04592103883624077, |
| "best_model_checkpoint": "./vit-base-beans-demo-v5/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": 1.47489595413208, |
| "learning_rate": 0.00019230769230769233, |
| "loss": 0.7807, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 2.146160125732422, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.3092, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 1.1490825414657593, |
| "learning_rate": 0.00017692307692307693, |
| "loss": 0.2205, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 3.718869924545288, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.2404, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 3.145725965499878, |
| "learning_rate": 0.00016153846153846155, |
| "loss": 0.2044, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 2.5821588039398193, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 0.1905, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 3.919996738433838, |
| "learning_rate": 0.00014615384615384615, |
| "loss": 0.1015, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.17645263671875, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 0.0932, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 0.16492128372192383, |
| "learning_rate": 0.00013076923076923077, |
| "loss": 0.1566, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 2.3894808292388916, |
| "learning_rate": 0.0001230769230769231, |
| "loss": 0.0937, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.05526537820696831, |
| "eval_runtime": 1.8744, |
| "eval_samples_per_second": 70.956, |
| "eval_steps_per_second": 9.07, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 0.48887503147125244, |
| "learning_rate": 0.00011538461538461538, |
| "loss": 0.0441, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 0.2171013355255127, |
| "learning_rate": 0.0001076923076923077, |
| "loss": 0.1127, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.10107976198196411, |
| "learning_rate": 0.0001, |
| "loss": 0.0688, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 9.199920654296875, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.051, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.0795423686504364, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.0162, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 0.09108028560876846, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.0152, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 0.08107301592826843, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.0154, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 4.5505805015563965, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.026, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 0.070733442902565, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.0267, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 0.05742541700601578, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.0117, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "eval_accuracy": 0.9924812030075187, |
| "eval_loss": 0.04592103883624077, |
| "eval_runtime": 1.2327, |
| "eval_samples_per_second": 107.896, |
| "eval_steps_per_second": 13.791, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.230769230769231, |
| "grad_norm": 0.056514862924814224, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.0108, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "grad_norm": 0.05424040928483009, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.0113, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.5384615384615383, |
| "grad_norm": 0.057043757289648056, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.0103, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "grad_norm": 0.05268687754869461, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.01, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "grad_norm": 0.056598395109176636, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.0101, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.05144289508461952, |
| "learning_rate": 0.0, |
| "loss": 0.0109, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 260, |
| "total_flos": 3.205097416476426e+17, |
| "train_loss": 0.10929785591478532, |
| "train_runtime": 90.2453, |
| "train_samples_per_second": 45.831, |
| "train_steps_per_second": 2.881 |
| } |
| ], |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.205097416476426e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
