| { | |
| "best_metric": 6389.54150390625, | |
| "best_model_checkpoint": "./coco_outputs/checkpoint-196", | |
| "epoch": 50.0, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 6398.52734375, | |
| "eval_runtime": 0.5289, | |
| "eval_samples_per_second": 15.126, | |
| "eval_steps_per_second": 1.891, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6397.9267578125, | |
| "eval_runtime": 0.5329, | |
| "eval_samples_per_second": 15.013, | |
| "eval_steps_per_second": 1.877, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.9e-05, | |
| "loss": 6175.8695, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6397.248046875, | |
| "eval_runtime": 0.5325, | |
| "eval_samples_per_second": 15.023, | |
| "eval_steps_per_second": 1.878, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 6396.56494140625, | |
| "eval_runtime": 0.5866, | |
| "eval_samples_per_second": 13.638, | |
| "eval_steps_per_second": 1.705, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.8e-05, | |
| "loss": 6292.1676, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6396.06689453125, | |
| "eval_runtime": 0.5343, | |
| "eval_samples_per_second": 14.974, | |
| "eval_steps_per_second": 1.872, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 6395.65966796875, | |
| "eval_runtime": 0.5271, | |
| "eval_samples_per_second": 15.178, | |
| "eval_steps_per_second": 1.897, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 6395.27392578125, | |
| "eval_runtime": 0.5241, | |
| "eval_samples_per_second": 15.264, | |
| "eval_steps_per_second": 1.908, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.7e-05, | |
| "loss": 6230.1191, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 6394.890625, | |
| "eval_runtime": 0.5365, | |
| "eval_samples_per_second": 14.911, | |
| "eval_steps_per_second": 1.864, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 6394.66796875, | |
| "eval_runtime": 0.5263, | |
| "eval_samples_per_second": 15.201, | |
| "eval_steps_per_second": 1.9, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 6089.0629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 6394.51513671875, | |
| "eval_runtime": 0.5595, | |
| "eval_samples_per_second": 14.298, | |
| "eval_steps_per_second": 1.787, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 6394.369140625, | |
| "eval_runtime": 0.5347, | |
| "eval_samples_per_second": 14.961, | |
| "eval_steps_per_second": 1.87, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 6394.39306640625, | |
| "eval_runtime": 0.6066, | |
| "eval_samples_per_second": 13.188, | |
| "eval_steps_per_second": 1.648, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 6266.6961, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 6394.3232421875, | |
| "eval_runtime": 0.5315, | |
| "eval_samples_per_second": 15.053, | |
| "eval_steps_per_second": 1.882, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 6394.1572265625, | |
| "eval_runtime": 0.5445, | |
| "eval_samples_per_second": 14.694, | |
| "eval_steps_per_second": 1.837, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.4e-05, | |
| "loss": 6383.0688, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 6394.15576171875, | |
| "eval_runtime": 0.5377, | |
| "eval_samples_per_second": 14.877, | |
| "eval_steps_per_second": 1.86, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 6393.953125, | |
| "eval_runtime": 0.5413, | |
| "eval_samples_per_second": 14.779, | |
| "eval_steps_per_second": 1.847, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 6393.77197265625, | |
| "eval_runtime": 0.5527, | |
| "eval_samples_per_second": 14.475, | |
| "eval_steps_per_second": 1.809, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 6323.732, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 6393.60498046875, | |
| "eval_runtime": 0.5502, | |
| "eval_samples_per_second": 14.54, | |
| "eval_steps_per_second": 1.817, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 6393.5107421875, | |
| "eval_runtime": 0.5415, | |
| "eval_samples_per_second": 14.774, | |
| "eval_steps_per_second": 1.847, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 6262.8367, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 6393.23046875, | |
| "eval_runtime": 0.5438, | |
| "eval_samples_per_second": 14.71, | |
| "eval_steps_per_second": 1.839, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 6393.0869140625, | |
| "eval_runtime": 0.5423, | |
| "eval_samples_per_second": 14.753, | |
| "eval_steps_per_second": 1.844, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 6392.791015625, | |
| "eval_runtime": 0.5523, | |
| "eval_samples_per_second": 14.486, | |
| "eval_steps_per_second": 1.811, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 6294.5953, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 6392.60791015625, | |
| "eval_runtime": 0.5553, | |
| "eval_samples_per_second": 14.407, | |
| "eval_steps_per_second": 1.801, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 6392.46337890625, | |
| "eval_runtime": 0.542, | |
| "eval_samples_per_second": 14.759, | |
| "eval_steps_per_second": 1.845, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1e-05, | |
| "loss": 6454.1902, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 6392.30859375, | |
| "eval_runtime": 0.5462, | |
| "eval_samples_per_second": 14.647, | |
| "eval_steps_per_second": 1.831, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 6392.1982421875, | |
| "eval_runtime": 0.5465, | |
| "eval_samples_per_second": 14.64, | |
| "eval_steps_per_second": 1.83, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 6391.966796875, | |
| "eval_runtime": 0.5565, | |
| "eval_samples_per_second": 14.375, | |
| "eval_steps_per_second": 1.797, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 9e-06, | |
| "loss": 6325.2328, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 6391.6533203125, | |
| "eval_runtime": 0.5394, | |
| "eval_samples_per_second": 14.833, | |
| "eval_steps_per_second": 1.854, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 6391.34814453125, | |
| "eval_runtime": 0.5379, | |
| "eval_samples_per_second": 14.872, | |
| "eval_steps_per_second": 1.859, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 6471.3637, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 6391.04736328125, | |
| "eval_runtime": 0.5998, | |
| "eval_samples_per_second": 13.338, | |
| "eval_steps_per_second": 1.667, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 6390.94091796875, | |
| "eval_runtime": 0.5467, | |
| "eval_samples_per_second": 14.632, | |
| "eval_steps_per_second": 1.829, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 6390.81982421875, | |
| "eval_runtime": 0.5421, | |
| "eval_samples_per_second": 14.759, | |
| "eval_steps_per_second": 1.845, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 7e-06, | |
| "loss": 6308.2656, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 6390.673828125, | |
| "eval_runtime": 0.5411, | |
| "eval_samples_per_second": 14.785, | |
| "eval_steps_per_second": 1.848, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 6390.6689453125, | |
| "eval_runtime": 0.5495, | |
| "eval_samples_per_second": 14.56, | |
| "eval_steps_per_second": 1.82, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6e-06, | |
| "loss": 6352.0371, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 6390.62451171875, | |
| "eval_runtime": 0.5561, | |
| "eval_samples_per_second": 14.385, | |
| "eval_steps_per_second": 1.798, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 6390.5791015625, | |
| "eval_runtime": 0.5601, | |
| "eval_samples_per_second": 14.282, | |
| "eval_steps_per_second": 1.785, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 6390.419921875, | |
| "eval_runtime": 0.5447, | |
| "eval_samples_per_second": 14.686, | |
| "eval_steps_per_second": 1.836, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 5e-06, | |
| "loss": 6247.1492, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 6390.23046875, | |
| "eval_runtime": 0.5405, | |
| "eval_samples_per_second": 14.8, | |
| "eval_steps_per_second": 1.85, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 6390.07763671875, | |
| "eval_runtime": 0.5527, | |
| "eval_samples_per_second": 14.473, | |
| "eval_steps_per_second": 1.809, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 6385.748, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 6389.9873046875, | |
| "eval_runtime": 0.5425, | |
| "eval_samples_per_second": 14.746, | |
| "eval_steps_per_second": 1.843, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 6389.91845703125, | |
| "eval_runtime": 0.5483, | |
| "eval_samples_per_second": 14.591, | |
| "eval_steps_per_second": 1.824, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 6389.828125, | |
| "eval_runtime": 0.5625, | |
| "eval_samples_per_second": 14.221, | |
| "eval_steps_per_second": 1.778, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 3e-06, | |
| "loss": 6262.0703, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 6389.75, | |
| "eval_runtime": 0.5518, | |
| "eval_samples_per_second": 14.498, | |
| "eval_steps_per_second": 1.812, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 6389.67919921875, | |
| "eval_runtime": 0.5455, | |
| "eval_samples_per_second": 14.666, | |
| "eval_steps_per_second": 1.833, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 6256.2105, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 6389.6376953125, | |
| "eval_runtime": 0.5593, | |
| "eval_samples_per_second": 14.304, | |
| "eval_steps_per_second": 1.788, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 6389.6201171875, | |
| "eval_runtime": 0.555, | |
| "eval_samples_per_second": 14.413, | |
| "eval_steps_per_second": 1.802, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 6389.57275390625, | |
| "eval_runtime": 0.5436, | |
| "eval_samples_per_second": 14.718, | |
| "eval_steps_per_second": 1.84, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 6353.4496, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 6389.5517578125, | |
| "eval_runtime": 0.55, | |
| "eval_samples_per_second": 14.545, | |
| "eval_steps_per_second": 1.818, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 6389.54150390625, | |
| "eval_runtime": 0.5412, | |
| "eval_samples_per_second": 14.782, | |
| "eval_steps_per_second": 1.848, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0, | |
| "loss": 6211.1777, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 6389.552734375, | |
| "eval_runtime": 0.5488, | |
| "eval_samples_per_second": 14.577, | |
| "eval_steps_per_second": 1.822, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 200, | |
| "total_flos": 7.65002115072e+17, | |
| "train_loss": 6297.2521484375, | |
| "train_runtime": 886.6987, | |
| "train_samples_per_second": 1.804, | |
| "train_steps_per_second": 0.226 | |
| } | |
| ], | |
| "max_steps": 200, | |
| "num_train_epochs": 50, | |
| "total_flos": 7.65002115072e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |