| { |
| "best_metric": 0.040157876908779144, |
| "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": 0.044208526611328125, |
| "learning_rate": 0.00019230769230769233, |
| "loss": 0.0121, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 0.04534326493740082, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.0244, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.05155162885785103, |
| "learning_rate": 0.00017692307692307693, |
| "loss": 0.0488, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.03998931124806404, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.0399, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 0.24661797285079956, |
| "learning_rate": 0.00016153846153846155, |
| "loss": 0.1117, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.11398249864578247, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 0.0616, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 0.036488745361566544, |
| "learning_rate": 0.00014615384615384615, |
| "loss": 0.0087, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.046938203275203705, |
| "learning_rate": 0.00013846153846153847, |
| "loss": 0.037, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 0.03303881362080574, |
| "learning_rate": 0.00013076923076923077, |
| "loss": 0.0156, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 5.383961200714111, |
| "learning_rate": 0.0001230769230769231, |
| "loss": 0.0287, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "eval_accuracy": 0.9924812030075187, |
| "eval_loss": 0.04278860613703728, |
| "eval_runtime": 1.7823, |
| "eval_samples_per_second": 74.623, |
| "eval_steps_per_second": 9.538, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 0.8509369492530823, |
| "learning_rate": 0.00011538461538461538, |
| "loss": 0.0544, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 0.02526756376028061, |
| "learning_rate": 0.0001076923076923077, |
| "loss": 0.051, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.026110434904694557, |
| "learning_rate": 0.0001, |
| "loss": 0.0052, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 0.025369793176651, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.0184, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.02806719020009041, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.0112, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 0.0388617217540741, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.0074, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 0.20131351053714752, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.004, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 0.020867854356765747, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.0043, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 0.030307570472359657, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.0446, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "grad_norm": 0.01962350495159626, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.019, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.076923076923077, |
| "eval_accuracy": 0.9849624060150376, |
| "eval_loss": 0.040157876908779144, |
| "eval_runtime": 1.2942, |
| "eval_samples_per_second": 102.766, |
| "eval_steps_per_second": 13.135, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.230769230769231, |
| "grad_norm": 0.01973757892847061, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.0371, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.3846153846153846, |
| "grad_norm": 0.01920933835208416, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.0035, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.5384615384615383, |
| "grad_norm": 0.029205061495304108, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.0035, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.6923076923076925, |
| "grad_norm": 0.019161337986588478, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.0034, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.8461538461538463, |
| "grad_norm": 0.023118212819099426, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.0035, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.019098477438092232, |
| "learning_rate": 0.0, |
| "loss": 0.0035, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 260, |
| "total_flos": 3.205097416476426e+17, |
| "train_loss": 0.025486919613411794, |
| "train_runtime": 118.343, |
| "train_samples_per_second": 34.949, |
| "train_steps_per_second": 2.197 |
| } |
| ], |
| "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 |
| } |
|
|
