| { |
| "best_metric": 0.05505308136343956, |
| "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": 1.4792640209197998, |
| "learning_rate": 0.00019230769230769233, |
| "loss": 0.8119, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 2.9676215648651123, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.3373, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.8012326955795288, |
| "learning_rate": 0.00017692307692307693, |
| "loss": 0.2303, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 5.820324420928955, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.1909, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 2.3705620765686035, |
| "learning_rate": 0.00016153846153846155, |
| "loss": 0.1838, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 1.2660043239593506, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 0.1773, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 0.2861775755882263, |
| "learning_rate": 0.00014615384615384615, |
| "loss": 0.0627, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.14893679320812225, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 0.0513, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 8.233551979064941, |
| "learning_rate": 0.00013076923076923077, |
| "loss": 0.0376, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 1.9747097492218018, |
| "learning_rate": 0.0001230769230769231, |
| "loss": 0.0637, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.0613524354994297, |
| "eval_runtime": 1.3714, |
| "eval_samples_per_second": 96.984, |
| "eval_steps_per_second": 12.396, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 1.3859927654266357, |
| "learning_rate": 0.00011538461538461538, |
| "loss": 0.1434, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 0.19647906720638275, |
| "learning_rate": 0.0001076923076923077, |
| "loss": 0.1165, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.09611102193593979, |
| "learning_rate": 0.0001, |
| "loss": 0.094, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 0.10484049469232559, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.0988, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.12751205265522003, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.0679, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 5.338469505310059, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.0736, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 0.078900046646595, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.0255, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 0.0799761489033699, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.0167, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 1.509344220161438, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.0616, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 0.06765936315059662, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.0322, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "eval_accuracy": 0.9849624060150376, |
| "eval_loss": 0.05505308136343956, |
| "eval_runtime": 1.3775, |
| "eval_samples_per_second": 96.553, |
| "eval_steps_per_second": 12.341, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.230769230769231, |
| "grad_norm": 0.10183589905500412, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.0148, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "grad_norm": 0.06187231093645096, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.0123, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.5384615384615383, |
| "grad_norm": 0.06384636461734772, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.0115, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "grad_norm": 0.06626074016094208, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.0114, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "grad_norm": 0.06165216863155365, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.0114, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.7294643521308899, |
| "learning_rate": 0.0, |
| "loss": 0.0156, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 260, |
| "total_flos": 3.205097416476426e+17, |
| "train_loss": 0.11361430327479656, |
| "train_runtime": 89.027, |
| "train_samples_per_second": 46.458, |
| "train_steps_per_second": 2.92 |
| } |
| ], |
| "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 |
| } |
|
|
