| { | |
| "best_metric": 0.0012113985139876604, | |
| "best_model_checkpoint": "convnext-large-384-22k-1k-finetuned-eurosat/checkpoint-68", | |
| "epoch": 3.868131868131868, | |
| "eval_steps": 500, | |
| "global_step": 88, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 5.727264881134033, | |
| "learning_rate": 4.936708860759494e-05, | |
| "loss": 0.701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 14.726851463317871, | |
| "learning_rate": 4.3037974683544305e-05, | |
| "loss": 0.2737, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.08488043397665024, | |
| "eval_runtime": 7.2932, | |
| "eval_samples_per_second": 13.986, | |
| "eval_steps_per_second": 1.508, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 1.7209300994873047, | |
| "learning_rate": 3.670886075949367e-05, | |
| "loss": 0.0656, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 7.18027400970459, | |
| "learning_rate": 3.0379746835443042e-05, | |
| "loss": 0.0416, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.005474980920553207, | |
| "eval_runtime": 6.2937, | |
| "eval_samples_per_second": 16.207, | |
| "eval_steps_per_second": 1.748, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 1.0882468223571777, | |
| "learning_rate": 2.4050632911392405e-05, | |
| "loss": 0.0095, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.13572758436203003, | |
| "learning_rate": 1.7721518987341772e-05, | |
| "loss": 0.0096, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 0.0012113985139876604, | |
| "eval_runtime": 6.2097, | |
| "eval_samples_per_second": 16.426, | |
| "eval_steps_per_second": 1.771, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 0.02920173481106758, | |
| "learning_rate": 1.139240506329114e-05, | |
| "loss": 0.0011, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 0.02914993278682232, | |
| "learning_rate": 5.063291139240506e-06, | |
| "loss": 0.0018, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "eval_loss": 0.002901246538385749, | |
| "eval_runtime": 6.242, | |
| "eval_samples_per_second": 16.341, | |
| "eval_steps_per_second": 1.762, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "step": 88, | |
| "total_flos": 1.8333718891462656e+18, | |
| "train_loss": 0.12722260688050566, | |
| "train_runtime": 603.2075, | |
| "train_samples_per_second": 6.034, | |
| "train_steps_per_second": 0.146 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 88, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 1.8333718891462656e+18, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |