| { | |
| "best_metric": 0.10869565217391304, | |
| "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-3", | |
| "epoch": 34.285714285714285, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.95629119873047, | |
| "eval_runtime": 0.6964, | |
| "eval_samples_per_second": 66.055, | |
| "eval_steps_per_second": 4.308, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.952392578125, | |
| "eval_runtime": 0.6137, | |
| "eval_samples_per_second": 74.961, | |
| "eval_steps_per_second": 4.889, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.000125, | |
| "loss": 114.2271, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.94542694091797, | |
| "eval_runtime": 0.6086, | |
| "eval_samples_per_second": 75.578, | |
| "eval_steps_per_second": 4.929, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.93885803222656, | |
| "eval_runtime": 0.6092, | |
| "eval_samples_per_second": 75.515, | |
| "eval_steps_per_second": 4.925, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.9226303100586, | |
| "eval_runtime": 0.6577, | |
| "eval_samples_per_second": 69.945, | |
| "eval_steps_per_second": 4.562, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.0001388888888888889, | |
| "loss": 113.5566, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.89823913574219, | |
| "eval_runtime": 0.6091, | |
| "eval_samples_per_second": 75.517, | |
| "eval_steps_per_second": 4.925, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.84252166748047, | |
| "eval_runtime": 0.6192, | |
| "eval_samples_per_second": 74.295, | |
| "eval_steps_per_second": 4.845, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.7478256225586, | |
| "eval_runtime": 0.6437, | |
| "eval_samples_per_second": 71.467, | |
| "eval_steps_per_second": 4.661, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.000125, | |
| "loss": 111.6907, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.65383911132812, | |
| "eval_runtime": 0.6171, | |
| "eval_samples_per_second": 74.538, | |
| "eval_steps_per_second": 4.861, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.55889892578125, | |
| "eval_runtime": 0.6282, | |
| "eval_samples_per_second": 73.23, | |
| "eval_steps_per_second": 4.776, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.500244140625, | |
| "eval_runtime": 0.6501, | |
| "eval_samples_per_second": 70.753, | |
| "eval_steps_per_second": 4.614, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.00011111111111111109, | |
| "loss": 115.67, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.4496078491211, | |
| "eval_runtime": 0.6246, | |
| "eval_samples_per_second": 73.641, | |
| "eval_steps_per_second": 4.803, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.37518310546875, | |
| "eval_runtime": 0.6266, | |
| "eval_samples_per_second": 73.406, | |
| "eval_steps_per_second": 4.787, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.21294403076172, | |
| "eval_runtime": 0.7182, | |
| "eval_samples_per_second": 64.052, | |
| "eval_steps_per_second": 4.177, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 9.722222222222222e-05, | |
| "loss": 111.8054, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.0827865600586, | |
| "eval_runtime": 0.6252, | |
| "eval_samples_per_second": 73.582, | |
| "eval_steps_per_second": 4.799, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.88050842285156, | |
| "eval_runtime": 0.6316, | |
| "eval_samples_per_second": 72.825, | |
| "eval_steps_per_second": 4.749, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.90125274658203, | |
| "eval_runtime": 0.6246, | |
| "eval_samples_per_second": 73.642, | |
| "eval_steps_per_second": 4.803, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 112.3831, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.812255859375, | |
| "eval_runtime": 0.6547, | |
| "eval_samples_per_second": 70.263, | |
| "eval_steps_per_second": 4.582, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.01899719238281, | |
| "eval_runtime": 0.6161, | |
| "eval_samples_per_second": 74.659, | |
| "eval_steps_per_second": 4.869, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 113.1097, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 113.29285430908203, | |
| "eval_runtime": 0.6286, | |
| "eval_samples_per_second": 73.173, | |
| "eval_steps_per_second": 4.772, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.88607025146484, | |
| "eval_runtime": 0.6372, | |
| "eval_samples_per_second": 72.196, | |
| "eval_steps_per_second": 4.708, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.71536254882812, | |
| "eval_runtime": 0.6587, | |
| "eval_samples_per_second": 69.838, | |
| "eval_steps_per_second": 4.555, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 5.5555555555555545e-05, | |
| "loss": 113.3674, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.69425964355469, | |
| "eval_runtime": 0.6142, | |
| "eval_samples_per_second": 74.9, | |
| "eval_steps_per_second": 4.885, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.39366912841797, | |
| "eval_runtime": 0.6652, | |
| "eval_samples_per_second": 69.156, | |
| "eval_steps_per_second": 4.51, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.38623809814453, | |
| "eval_runtime": 0.6241, | |
| "eval_samples_per_second": 73.701, | |
| "eval_steps_per_second": 4.807, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 4.1666666666666665e-05, | |
| "loss": 113.1472, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.26931762695312, | |
| "eval_runtime": 0.6136, | |
| "eval_samples_per_second": 74.962, | |
| "eval_steps_per_second": 4.889, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.31065368652344, | |
| "eval_runtime": 0.7012, | |
| "eval_samples_per_second": 65.606, | |
| "eval_steps_per_second": 4.279, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.42163848876953, | |
| "eval_runtime": 0.6231, | |
| "eval_samples_per_second": 73.819, | |
| "eval_steps_per_second": 4.814, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 2.7777777777777772e-05, | |
| "loss": 111.3252, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.33184051513672, | |
| "eval_runtime": 0.6136, | |
| "eval_samples_per_second": 74.962, | |
| "eval_steps_per_second": 4.889, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.3516616821289, | |
| "eval_runtime": 0.6282, | |
| "eval_samples_per_second": 73.23, | |
| "eval_steps_per_second": 4.776, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.42131042480469, | |
| "eval_runtime": 0.6367, | |
| "eval_samples_per_second": 72.253, | |
| "eval_steps_per_second": 4.712, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 1.3888888888888886e-05, | |
| "loss": 112.827, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.48377227783203, | |
| "eval_runtime": 0.6321, | |
| "eval_samples_per_second": 72.768, | |
| "eval_steps_per_second": 4.746, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.44902801513672, | |
| "eval_runtime": 0.6151, | |
| "eval_samples_per_second": 74.779, | |
| "eval_steps_per_second": 4.877, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.15248107910156, | |
| "eval_runtime": 0.6382, | |
| "eval_samples_per_second": 72.082, | |
| "eval_steps_per_second": 4.701, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 112.5631, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 112.195556640625, | |
| "eval_runtime": 0.6527, | |
| "eval_samples_per_second": 70.482, | |
| "eval_steps_per_second": 4.597, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.0027429927092224e+16, | |
| "train_loss": 112.97269897460937, | |
| "train_runtime": 134.324, | |
| "train_samples_per_second": 63.429, | |
| "train_steps_per_second": 0.893 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 2.0027429927092224e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |