| { |
| "best_metric": 0.04344853386282921, |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-100", |
| "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": 1.5337990522384644, |
| "learning_rate": 0.00019230769230769233, |
| "loss": 0.7844, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 1.7073242664337158, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.315, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.4248681664466858, |
| "learning_rate": 0.00017692307692307693, |
| "loss": 0.2075, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 1.390496850013733, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.249, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 2.437204360961914, |
| "learning_rate": 0.00016153846153846155, |
| "loss": 0.1996, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 3.9072976112365723, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 0.189, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 3.6122686862945557, |
| "learning_rate": 0.00014615384615384615, |
| "loss": 0.1612, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.5994962453842163, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 0.0951, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 0.2357104867696762, |
| "learning_rate": 0.00013076923076923077, |
| "loss": 0.1084, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 1.8062130212783813, |
| "learning_rate": 0.0001230769230769231, |
| "loss": 0.0803, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "eval_accuracy": 0.9924812030075187, |
| "eval_loss": 0.04344853386282921, |
| "eval_runtime": 2.1191, |
| "eval_samples_per_second": 62.762, |
| "eval_steps_per_second": 8.022, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 0.5915942192077637, |
| "learning_rate": 0.00011538461538461538, |
| "loss": 0.0858, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 3.0150363445281982, |
| "learning_rate": 0.0001076923076923077, |
| "loss": 0.1769, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.11346229910850525, |
| "learning_rate": 0.0001, |
| "loss": 0.0372, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 0.6146863102912903, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.0433, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.08208445459604263, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.0167, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 0.07619213312864304, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.015, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 0.1081862673163414, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.014, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 4.036991596221924, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.0604, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 0.06720926612615585, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.0331, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 0.05951293185353279, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.0179, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.07623247057199478, |
| "eval_runtime": 1.5021, |
| "eval_samples_per_second": 88.545, |
| "eval_steps_per_second": 11.318, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.230769230769231, |
| "grad_norm": 0.05967424437403679, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.0119, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "grad_norm": 0.05599810928106308, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.0119, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.5384615384615383, |
| "grad_norm": 0.05898129567503929, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.0132, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "grad_norm": 0.054502274841070175, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.0108, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "grad_norm": 0.06283178925514221, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.0107, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.05481337755918503, |
| "learning_rate": 0.0, |
| "loss": 0.0108, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 260, |
| "total_flos": 3.205097416476426e+17, |
| "train_loss": 0.11381071235698004, |
| "train_runtime": 147.745, |
| "train_samples_per_second": 27.994, |
| "train_steps_per_second": 1.76 |
| } |
| ], |
| "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 |
| } |
|
|
