| { |
| "best_metric": 5.964588165283203, |
| "best_model_checkpoint": "flowers_image_detection/checkpoint-12118", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 12118, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0825218682950982, |
| "grad_norm": 1.8450349569320679, |
| "learning_rate": 1.9254226052369905e-07, |
| "loss": 5.9475, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1650437365901964, |
| "grad_norm": 1.7727391719818115, |
| "learning_rate": 1.842558833278091e-07, |
| "loss": 5.948, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2475656048852946, |
| "grad_norm": 1.7900820970535278, |
| "learning_rate": 1.7596950613191912e-07, |
| "loss": 5.9467, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.3300874731803928, |
| "grad_norm": 1.6870242357254028, |
| "learning_rate": 1.6768312893602916e-07, |
| "loss": 5.935, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.412609341475491, |
| "grad_norm": 1.9448150396347046, |
| "learning_rate": 1.593967517401392e-07, |
| "loss": 5.9367, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.4951312097705892, |
| "grad_norm": 1.7643060684204102, |
| "learning_rate": 1.5111037454424923e-07, |
| "loss": 5.9283, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.5776530780656874, |
| "grad_norm": 1.7454640865325928, |
| "learning_rate": 1.428239973483593e-07, |
| "loss": 5.9315, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.6601749463607856, |
| "grad_norm": 1.7440547943115234, |
| "learning_rate": 1.3453762015246935e-07, |
| "loss": 5.9237, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.7426968146558838, |
| "grad_norm": 1.7682538032531738, |
| "learning_rate": 1.262512429565794e-07, |
| "loss": 5.9265, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.825218682950982, |
| "grad_norm": 1.7519503831863403, |
| "learning_rate": 1.1796486576068942e-07, |
| "loss": 5.9222, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.9077405512460802, |
| "grad_norm": 1.7960128784179688, |
| "learning_rate": 1.0967848856479946e-07, |
| "loss": 5.9195, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.9902624195411784, |
| "grad_norm": 1.9735090732574463, |
| "learning_rate": 1.0139211136890951e-07, |
| "loss": 5.9239, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.6516635716496441, |
| "eval_loss": 5.973537445068359, |
| "eval_runtime": 1279.8379, |
| "eval_samples_per_second": 100.982, |
| "eval_steps_per_second": 12.623, |
| "step": 6059 |
| }, |
| { |
| "epoch": 1.0727842878362766, |
| "grad_norm": 1.7479947805404663, |
| "learning_rate": 9.310573417301956e-08, |
| "loss": 5.9212, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.1553061561313749, |
| "grad_norm": 1.8694578409194946, |
| "learning_rate": 8.481935697712959e-08, |
| "loss": 5.9106, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.237828024426473, |
| "grad_norm": 1.7446856498718262, |
| "learning_rate": 7.653297978123964e-08, |
| "loss": 5.919, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.320349892721571, |
| "grad_norm": 1.7331393957138062, |
| "learning_rate": 6.824660258534968e-08, |
| "loss": 5.9144, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.4028717610166694, |
| "grad_norm": 1.664704442024231, |
| "learning_rate": 5.996022538945973e-08, |
| "loss": 5.9162, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.4853936293117675, |
| "grad_norm": 1.6834096908569336, |
| "learning_rate": 5.167384819356977e-08, |
| "loss": 5.9135, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.5679154976068657, |
| "grad_norm": 1.8518224954605103, |
| "learning_rate": 4.3387470997679816e-08, |
| "loss": 5.9141, |
| "step": 9500 |
| }, |
| { |
| "epoch": 1.650437365901964, |
| "grad_norm": 1.7295408248901367, |
| "learning_rate": 3.510109380178986e-08, |
| "loss": 5.9103, |
| "step": 10000 |
| }, |
| { |
| "epoch": 1.7329592341970623, |
| "grad_norm": 1.839285135269165, |
| "learning_rate": 2.68147166058999e-08, |
| "loss": 5.9081, |
| "step": 10500 |
| }, |
| { |
| "epoch": 1.8154811024921604, |
| "grad_norm": 1.8111240863800049, |
| "learning_rate": 1.8528339410009945e-08, |
| "loss": 5.9104, |
| "step": 11000 |
| }, |
| { |
| "epoch": 1.8980029707872585, |
| "grad_norm": 1.763000249862671, |
| "learning_rate": 1.0241962214119987e-08, |
| "loss": 5.91, |
| "step": 11500 |
| }, |
| { |
| "epoch": 1.9805248390823569, |
| "grad_norm": 1.8061938285827637, |
| "learning_rate": 1.95558501823003e-09, |
| "loss": 5.9083, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6545032497678738, |
| "eval_loss": 5.964588165283203, |
| "eval_runtime": 1245.0154, |
| "eval_samples_per_second": 103.806, |
| "eval_steps_per_second": 12.976, |
| "step": 12118 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 12118, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 3.02870126573509e+19, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
