| { | |
| "best_metric": 0.8333333333333334, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-fish/checkpoint-13", | |
| "epoch": 25.0, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.8802646398544312, | |
| "eval_runtime": 0.6371, | |
| "eval_samples_per_second": 9.418, | |
| "eval_steps_per_second": 1.57, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.843906283378601, | |
| "eval_runtime": 0.6436, | |
| "eval_samples_per_second": 9.322, | |
| "eval_steps_per_second": 1.554, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.7571700811386108, | |
| "eval_runtime": 0.4478, | |
| "eval_samples_per_second": 13.398, | |
| "eval_steps_per_second": 2.233, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.625635027885437, | |
| "eval_runtime": 0.4177, | |
| "eval_samples_per_second": 14.363, | |
| "eval_steps_per_second": 2.394, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.5081933736801147, | |
| "eval_runtime": 0.43, | |
| "eval_samples_per_second": 13.952, | |
| "eval_steps_per_second": 2.325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.4301046133041382, | |
| "eval_runtime": 0.4297, | |
| "eval_samples_per_second": 13.963, | |
| "eval_steps_per_second": 2.327, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.3379350900650024, | |
| "eval_runtime": 0.6346, | |
| "eval_samples_per_second": 9.455, | |
| "eval_steps_per_second": 1.576, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.226043701171875, | |
| "eval_runtime": 0.4425, | |
| "eval_samples_per_second": 13.56, | |
| "eval_steps_per_second": 2.26, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1071115732192993, | |
| "eval_runtime": 0.457, | |
| "eval_samples_per_second": 13.128, | |
| "eval_steps_per_second": 2.188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 4.3437418937683105, | |
| "learning_rate": 3.409090909090909e-05, | |
| "loss": 0.6539, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.9941108822822571, | |
| "eval_runtime": 0.434, | |
| "eval_samples_per_second": 13.825, | |
| "eval_steps_per_second": 2.304, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.8836026191711426, | |
| "eval_runtime": 0.4206, | |
| "eval_samples_per_second": 14.264, | |
| "eval_steps_per_second": 2.377, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.7859137654304504, | |
| "eval_runtime": 0.6517, | |
| "eval_samples_per_second": 9.206, | |
| "eval_steps_per_second": 1.534, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.7058526873588562, | |
| "eval_runtime": 0.442, | |
| "eval_samples_per_second": 13.573, | |
| "eval_steps_per_second": 2.262, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.6357579827308655, | |
| "eval_runtime": 0.4178, | |
| "eval_samples_per_second": 14.361, | |
| "eval_steps_per_second": 2.394, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.5752262473106384, | |
| "eval_runtime": 0.4294, | |
| "eval_samples_per_second": 13.972, | |
| "eval_steps_per_second": 2.329, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.5343325734138489, | |
| "eval_runtime": 0.4454, | |
| "eval_samples_per_second": 13.471, | |
| "eval_steps_per_second": 2.245, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.49941006302833557, | |
| "eval_runtime": 0.6534, | |
| "eval_samples_per_second": 9.182, | |
| "eval_steps_per_second": 1.53, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.47546982765197754, | |
| "eval_runtime": 0.4476, | |
| "eval_samples_per_second": 13.404, | |
| "eval_steps_per_second": 2.234, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.4544316232204437, | |
| "eval_runtime": 0.4503, | |
| "eval_samples_per_second": 13.326, | |
| "eval_steps_per_second": 2.221, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 4.215967655181885, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 0.2777, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.43280744552612305, | |
| "eval_runtime": 0.4355, | |
| "eval_samples_per_second": 13.776, | |
| "eval_steps_per_second": 2.296, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.41707566380500793, | |
| "eval_runtime": 0.4926, | |
| "eval_samples_per_second": 12.18, | |
| "eval_steps_per_second": 2.03, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.4065686762332916, | |
| "eval_runtime": 0.6351, | |
| "eval_samples_per_second": 9.447, | |
| "eval_steps_per_second": 1.575, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.39954474568367004, | |
| "eval_runtime": 0.4453, | |
| "eval_samples_per_second": 13.474, | |
| "eval_steps_per_second": 2.246, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.39544954895973206, | |
| "eval_runtime": 0.4307, | |
| "eval_samples_per_second": 13.93, | |
| "eval_steps_per_second": 2.322, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.3932792842388153, | |
| "eval_runtime": 0.4285, | |
| "eval_samples_per_second": 14.002, | |
| "eval_steps_per_second": 2.334, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 25, | |
| "total_flos": 2.98313540001792e+16, | |
| "train_loss": 0.40966928482055665, | |
| "train_runtime": 140.371, | |
| "train_samples_per_second": 8.549, | |
| "train_steps_per_second": 0.178 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "save_steps": 500, | |
| "total_flos": 2.98313540001792e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |