| { | |
| "best_metric": 0.9477351916376306, | |
| "best_model_checkpoint": "brain-tumor-classification/checkpoint-200", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24691358024691357, | |
| "grad_norm": 11.865983009338379, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 14.611420631408691, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0649, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 14.365787506103516, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.7611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 16.896533966064453, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5761, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "eval_accuracy": 0.8432055749128919, | |
| "eval_loss": 0.41130325198173523, | |
| "eval_runtime": 2.4201, | |
| "eval_samples_per_second": 118.592, | |
| "eval_steps_per_second": 7.438, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2345679012345678, | |
| "grad_norm": 9.885971069335938, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5027, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 19.173418045043945, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.4857, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.7283950617283952, | |
| "grad_norm": 10.684455871582031, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.4252, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 11.967300415039062, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3871, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9024390243902439, | |
| "eval_loss": 0.25702860951423645, | |
| "eval_runtime": 3.0171, | |
| "eval_samples_per_second": 95.125, | |
| "eval_steps_per_second": 5.966, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 7.449192047119141, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.294, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 15.003212928771973, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3583, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.7160493827160495, | |
| "grad_norm": 12.026302337646484, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2584, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 10.30452823638916, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.2586, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.9876543209876543, | |
| "eval_accuracy": 0.9407665505226481, | |
| "eval_loss": 0.1910204291343689, | |
| "eval_runtime": 2.8228, | |
| "eval_samples_per_second": 101.672, | |
| "eval_steps_per_second": 6.377, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 3.2098765432098766, | |
| "grad_norm": 9.547262191772461, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.1965, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.45679012345679, | |
| "grad_norm": 8.193156242370605, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.2272, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "grad_norm": 6.964083671569824, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.237, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 15.732324600219727, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.2164, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9442508710801394, | |
| "eval_loss": 0.13123387098312378, | |
| "eval_runtime": 2.4291, | |
| "eval_samples_per_second": 118.153, | |
| "eval_steps_per_second": 7.41, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 4.197530864197531, | |
| "grad_norm": 7.277712821960449, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.1614, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 13.366209030151367, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.1978, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.6913580246913575, | |
| "grad_norm": 9.085039138793945, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.189, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 7.736137866973877, | |
| "learning_rate": 0.0, | |
| "loss": 0.1757, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "eval_accuracy": 0.9477351916376306, | |
| "eval_loss": 0.11578787863254547, | |
| "eval_runtime": 2.7368, | |
| "eval_samples_per_second": 104.868, | |
| "eval_steps_per_second": 6.577, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 200, | |
| "total_flos": 3.1727957353537536e+17, | |
| "train_loss": 0.41540566325187683, | |
| "train_runtime": 248.6508, | |
| "train_samples_per_second": 51.94, | |
| "train_steps_per_second": 0.804 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.1727957353537536e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |