| { | |
| "best_metric": 1.0859479904174805, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-1cost\\checkpoint-92120", | |
| "epoch": 20.0, | |
| "global_step": 92120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.001736864958749e-07, | |
| "loss": 1.7758, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.3047956228256226, | |
| "eval_runtime": 202.7594, | |
| "eval_samples_per_second": 8.784, | |
| "eval_steps_per_second": 1.1, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.001953973078592e-07, | |
| "loss": 1.6314, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2280656099319458, | |
| "eval_runtime": 201.0252, | |
| "eval_samples_per_second": 8.86, | |
| "eval_steps_per_second": 1.109, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.002171081198437e-07, | |
| "loss": 1.5709, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.1943721771240234, | |
| "eval_runtime": 201.1593, | |
| "eval_samples_per_second": 8.854, | |
| "eval_steps_per_second": 1.109, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.002605297438123e-07, | |
| "loss": 1.5368, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.1701624393463135, | |
| "eval_runtime": 201.4465, | |
| "eval_samples_per_second": 8.841, | |
| "eval_steps_per_second": 1.107, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.003039513677811e-07, | |
| "loss": 1.5132, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.149705171585083, | |
| "eval_runtime": 201.015, | |
| "eval_samples_per_second": 8.86, | |
| "eval_steps_per_second": 1.109, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.003256621797655e-07, | |
| "loss": 1.4929, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.1418626308441162, | |
| "eval_runtime": 200.9658, | |
| "eval_samples_per_second": 8.862, | |
| "eval_steps_per_second": 1.11, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0036908380373426e-07, | |
| "loss": 1.4803, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.1298332214355469, | |
| "eval_runtime": 201.243, | |
| "eval_samples_per_second": 8.85, | |
| "eval_steps_per_second": 1.108, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.003907946157186e-07, | |
| "loss": 1.4703, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.1245805025100708, | |
| "eval_runtime": 200.8739, | |
| "eval_samples_per_second": 8.866, | |
| "eval_steps_per_second": 1.11, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0041250542770299e-07, | |
| "loss": 1.4655, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.1222434043884277, | |
| "eval_runtime": 200.6019, | |
| "eval_samples_per_second": 8.878, | |
| "eval_steps_per_second": 1.112, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.776378636561007e-10, | |
| "loss": 1.4625, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.122222661972046, | |
| "eval_runtime": 200.6227, | |
| "eval_samples_per_second": 8.877, | |
| "eval_steps_per_second": 1.112, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.502496743378202e-07, | |
| "loss": 1.4579, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.1178261041641235, | |
| "eval_runtime": 201.3314, | |
| "eval_samples_per_second": 8.846, | |
| "eval_steps_per_second": 1.108, | |
| "step": 50666 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.0027138514980457e-07, | |
| "loss": 1.4529, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.1085678339004517, | |
| "eval_runtime": 200.8718, | |
| "eval_samples_per_second": 8.866, | |
| "eval_steps_per_second": 1.11, | |
| "step": 55272 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.5028224055579677e-07, | |
| "loss": 1.4397, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.103363275527954, | |
| "eval_runtime": 203.7656, | |
| "eval_samples_per_second": 8.74, | |
| "eval_steps_per_second": 1.094, | |
| "step": 59878 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.003039513677811e-07, | |
| "loss": 1.4366, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.0989503860473633, | |
| "eval_runtime": 200.8632, | |
| "eval_samples_per_second": 8.867, | |
| "eval_steps_per_second": 1.11, | |
| "step": 64484 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.503256621797655e-07, | |
| "loss": 1.425, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.0942606925964355, | |
| "eval_runtime": 201.1548, | |
| "eval_samples_per_second": 8.854, | |
| "eval_steps_per_second": 1.109, | |
| "step": 69090 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.003473729917499e-07, | |
| "loss": 1.4252, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.0911729335784912, | |
| "eval_runtime": 200.7701, | |
| "eval_samples_per_second": 8.871, | |
| "eval_steps_per_second": 1.111, | |
| "step": 73696 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.5035822839774206e-07, | |
| "loss": 1.4215, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.088094711303711, | |
| "eval_runtime": 202.7396, | |
| "eval_samples_per_second": 8.785, | |
| "eval_steps_per_second": 1.1, | |
| "step": 78302 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.0037993920972644e-07, | |
| "loss": 1.4188, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.0874948501586914, | |
| "eval_runtime": 200.0402, | |
| "eval_samples_per_second": 8.903, | |
| "eval_steps_per_second": 1.115, | |
| "step": 82908 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.0390794615718624e-08, | |
| "loss": 1.4133, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.0869966745376587, | |
| "eval_runtime": 200.3439, | |
| "eval_samples_per_second": 8.89, | |
| "eval_steps_per_second": 1.113, | |
| "step": 87514 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.1250542770299607e-10, | |
| "loss": 1.4152, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.0859479904174805, | |
| "eval_runtime": 200.8626, | |
| "eval_samples_per_second": 8.867, | |
| "eval_steps_per_second": 1.11, | |
| "step": 92120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 92120, | |
| "total_flos": 1.5150120318028805e+20, | |
| "train_loss": 0.7153063927740312, | |
| "train_runtime": 28368.5894, | |
| "train_samples_per_second": 12.987, | |
| "train_steps_per_second": 3.247 | |
| } | |
| ], | |
| "max_steps": 92120, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.5150120318028805e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |