| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-85-fold2/checkpoint-3", | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.18181818181818182, | |
| "eval_loss": 1.3509312868118286, | |
| "eval_runtime": 0.1772, | |
| "eval_samples_per_second": 62.079, | |
| "eval_steps_per_second": 5.644, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.18181818181818182, | |
| "eval_loss": 1.2094361782073975, | |
| "eval_runtime": 0.1689, | |
| "eval_samples_per_second": 65.141, | |
| "eval_steps_per_second": 5.922, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0158594846725464, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.337, | |
| "eval_steps_per_second": 5.849, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 0.9046756625175476, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.01, | |
| "eval_steps_per_second": 5.819, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9480745196342468, | |
| "eval_runtime": 0.1778, | |
| "eval_samples_per_second": 61.88, | |
| "eval_steps_per_second": 5.625, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1336756944656372, | |
| "eval_runtime": 0.149, | |
| "eval_samples_per_second": 73.83, | |
| "eval_steps_per_second": 6.712, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2463548183441162, | |
| "eval_runtime": 0.1712, | |
| "eval_samples_per_second": 64.269, | |
| "eval_steps_per_second": 5.843, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2334860563278198, | |
| "eval_runtime": 0.1767, | |
| "eval_samples_per_second": 62.255, | |
| "eval_steps_per_second": 5.66, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1431635618209839, | |
| "eval_runtime": 0.1763, | |
| "eval_samples_per_second": 62.408, | |
| "eval_steps_per_second": 5.673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.0628985166549683, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4248, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0979338884353638, | |
| "eval_runtime": 0.1603, | |
| "eval_samples_per_second": 68.632, | |
| "eval_steps_per_second": 6.239, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1069402694702148, | |
| "eval_runtime": 0.1737, | |
| "eval_samples_per_second": 63.331, | |
| "eval_steps_per_second": 5.757, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1633254289627075, | |
| "eval_runtime": 0.1719, | |
| "eval_samples_per_second": 63.993, | |
| "eval_steps_per_second": 5.818, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1650248765945435, | |
| "eval_runtime": 0.173, | |
| "eval_samples_per_second": 63.568, | |
| "eval_steps_per_second": 5.779, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1332045793533325, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.175, | |
| "eval_steps_per_second": 5.925, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1423081159591675, | |
| "eval_runtime": 0.4904, | |
| "eval_samples_per_second": 22.43, | |
| "eval_steps_per_second": 2.039, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1207692623138428, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.559, | |
| "eval_steps_per_second": 5.869, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0566281080245972, | |
| "eval_runtime": 0.168, | |
| "eval_samples_per_second": 65.465, | |
| "eval_steps_per_second": 5.951, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0348279476165771, | |
| "eval_runtime": 0.1707, | |
| "eval_samples_per_second": 64.442, | |
| "eval_steps_per_second": 5.858, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.014626383781433, | |
| "eval_runtime": 0.1639, | |
| "eval_samples_per_second": 67.111, | |
| "eval_steps_per_second": 6.101, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.9861624836921692, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1813, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0061558485031128, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.35, | |
| "eval_steps_per_second": 6.123, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0748077630996704, | |
| "eval_runtime": 0.1707, | |
| "eval_samples_per_second": 64.453, | |
| "eval_steps_per_second": 5.859, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1673214435577393, | |
| "eval_runtime": 0.1685, | |
| "eval_samples_per_second": 65.273, | |
| "eval_steps_per_second": 5.934, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2476741075515747, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 62.536, | |
| "eval_steps_per_second": 5.685, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.245665431022644, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 64.817, | |
| "eval_steps_per_second": 5.892, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1424124240875244, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 64.814, | |
| "eval_steps_per_second": 5.892, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.043944239616394, | |
| "eval_runtime": 0.1748, | |
| "eval_samples_per_second": 62.926, | |
| "eval_steps_per_second": 5.721, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9435653686523438, | |
| "eval_runtime": 0.1743, | |
| "eval_samples_per_second": 63.12, | |
| "eval_steps_per_second": 5.738, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.8253726363182068, | |
| "eval_runtime": 0.1772, | |
| "eval_samples_per_second": 62.089, | |
| "eval_steps_per_second": 5.644, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.7962835431098938, | |
| "eval_runtime": 0.1747, | |
| "eval_samples_per_second": 62.97, | |
| "eval_steps_per_second": 5.725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.8275336027145386, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1021, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.8055173754692078, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.11, | |
| "eval_steps_per_second": 6.01, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.7733648419380188, | |
| "eval_runtime": 0.1756, | |
| "eval_samples_per_second": 62.639, | |
| "eval_steps_per_second": 5.694, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.7069463133811951, | |
| "eval_runtime": 0.1758, | |
| "eval_samples_per_second": 62.563, | |
| "eval_steps_per_second": 5.688, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.7235378623008728, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.673, | |
| "eval_steps_per_second": 5.879, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.8200042843818665, | |
| "eval_runtime": 0.1736, | |
| "eval_samples_per_second": 63.358, | |
| "eval_steps_per_second": 5.76, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.8483505249023438, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.159, | |
| "eval_steps_per_second": 5.924, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9379635453224182, | |
| "eval_runtime": 0.1692, | |
| "eval_samples_per_second": 64.997, | |
| "eval_steps_per_second": 5.909, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0583945512771606, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.501, | |
| "eval_steps_per_second": 5.864, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1802500486373901, | |
| "eval_runtime": 0.1766, | |
| "eval_samples_per_second": 62.296, | |
| "eval_steps_per_second": 5.663, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.291641354560852, | |
| "eval_runtime": 0.1764, | |
| "eval_samples_per_second": 62.358, | |
| "eval_steps_per_second": 5.669, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.7646510004997253, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0579, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3442317247390747, | |
| "eval_runtime": 0.1671, | |
| "eval_samples_per_second": 65.821, | |
| "eval_steps_per_second": 5.984, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3060342073440552, | |
| "eval_runtime": 0.1752, | |
| "eval_samples_per_second": 62.786, | |
| "eval_steps_per_second": 5.708, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2349110841751099, | |
| "eval_runtime": 0.169, | |
| "eval_samples_per_second": 65.108, | |
| "eval_steps_per_second": 5.919, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1867114305496216, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.942, | |
| "eval_steps_per_second": 5.904, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.141136884689331, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.176, | |
| "eval_steps_per_second": 5.925, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2008732557296753, | |
| "eval_runtime": 0.1724, | |
| "eval_samples_per_second": 63.801, | |
| "eval_steps_per_second": 5.8, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.236550211906433, | |
| "eval_runtime": 0.1777, | |
| "eval_samples_per_second": 61.904, | |
| "eval_steps_per_second": 5.628, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2789766788482666, | |
| "eval_runtime": 0.1771, | |
| "eval_samples_per_second": 62.109, | |
| "eval_steps_per_second": 5.646, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3572884798049927, | |
| "eval_runtime": 0.1723, | |
| "eval_samples_per_second": 63.836, | |
| "eval_steps_per_second": 5.803, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4174641370773315, | |
| "eval_runtime": 0.1745, | |
| "eval_samples_per_second": 63.047, | |
| "eval_steps_per_second": 5.732, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 2.265517473220825, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0436, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4130061864852905, | |
| "eval_runtime": 0.1691, | |
| "eval_samples_per_second": 65.056, | |
| "eval_steps_per_second": 5.914, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4464725255966187, | |
| "eval_runtime": 0.1738, | |
| "eval_samples_per_second": 63.288, | |
| "eval_steps_per_second": 5.753, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4372490644454956, | |
| "eval_runtime": 0.1735, | |
| "eval_samples_per_second": 63.41, | |
| "eval_steps_per_second": 5.765, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.420746922492981, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.674, | |
| "eval_steps_per_second": 5.879, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4134434461593628, | |
| "eval_runtime": 0.1735, | |
| "eval_samples_per_second": 63.419, | |
| "eval_steps_per_second": 5.765, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4888943433761597, | |
| "eval_runtime": 0.1703, | |
| "eval_samples_per_second": 64.591, | |
| "eval_steps_per_second": 5.872, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5350738763809204, | |
| "eval_runtime": 0.1754, | |
| "eval_samples_per_second": 62.703, | |
| "eval_steps_per_second": 5.7, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5673235654830933, | |
| "eval_runtime": 0.1759, | |
| "eval_samples_per_second": 62.526, | |
| "eval_steps_per_second": 5.684, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.580267310142517, | |
| "eval_runtime": 0.1696, | |
| "eval_samples_per_second": 64.87, | |
| "eval_steps_per_second": 5.897, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5684764385223389, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.522, | |
| "eval_steps_per_second": 5.866, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 1.111411690711975, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0325, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.54865300655365, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.2, | |
| "eval_steps_per_second": 6.018, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.488776445388794, | |
| "eval_runtime": 0.1691, | |
| "eval_samples_per_second": 65.06, | |
| "eval_steps_per_second": 5.915, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4026367664337158, | |
| "eval_runtime": 0.1761, | |
| "eval_samples_per_second": 62.458, | |
| "eval_steps_per_second": 5.678, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.296814203262329, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.105, | |
| "eval_steps_per_second": 6.01, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2914561033248901, | |
| "eval_runtime": 0.1792, | |
| "eval_samples_per_second": 61.386, | |
| "eval_steps_per_second": 5.581, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3016196489334106, | |
| "eval_runtime": 0.1765, | |
| "eval_samples_per_second": 62.313, | |
| "eval_steps_per_second": 5.665, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3871337175369263, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.022, | |
| "eval_steps_per_second": 5.82, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5019389390945435, | |
| "eval_runtime": 0.1732, | |
| "eval_samples_per_second": 63.527, | |
| "eval_steps_per_second": 5.775, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6562583446502686, | |
| "eval_runtime": 0.169, | |
| "eval_samples_per_second": 65.077, | |
| "eval_steps_per_second": 5.916, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8046096563339233, | |
| "eval_runtime": 0.1731, | |
| "eval_samples_per_second": 63.551, | |
| "eval_steps_per_second": 5.777, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 1.2039395570755005, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.028, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9155147075653076, | |
| "eval_runtime": 0.1707, | |
| "eval_samples_per_second": 64.458, | |
| "eval_steps_per_second": 5.86, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9687961339950562, | |
| "eval_runtime": 0.1739, | |
| "eval_samples_per_second": 63.265, | |
| "eval_steps_per_second": 5.751, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9570330381393433, | |
| "eval_runtime": 0.1762, | |
| "eval_samples_per_second": 62.431, | |
| "eval_steps_per_second": 5.676, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8878777027130127, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.941, | |
| "eval_steps_per_second": 5.904, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8354095220565796, | |
| "eval_runtime": 0.1682, | |
| "eval_samples_per_second": 65.394, | |
| "eval_steps_per_second": 5.945, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.781206488609314, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.897, | |
| "eval_steps_per_second": 6.082, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6799699068069458, | |
| "eval_runtime": 0.1678, | |
| "eval_samples_per_second": 65.545, | |
| "eval_steps_per_second": 5.959, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5444244146347046, | |
| "eval_runtime": 0.1745, | |
| "eval_samples_per_second": 63.051, | |
| "eval_steps_per_second": 5.732, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4488316774368286, | |
| "eval_runtime": 0.1724, | |
| "eval_samples_per_second": 63.798, | |
| "eval_steps_per_second": 5.8, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3880367279052734, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.498, | |
| "eval_steps_per_second": 5.863, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 1.4312165975570679, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0411, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3544124364852905, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.067, | |
| "eval_steps_per_second": 6.006, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.386696696281433, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.523, | |
| "eval_steps_per_second": 5.866, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4347819089889526, | |
| "eval_runtime": 0.1728, | |
| "eval_samples_per_second": 63.648, | |
| "eval_steps_per_second": 5.786, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4906073808670044, | |
| "eval_runtime": 0.1706, | |
| "eval_samples_per_second": 64.491, | |
| "eval_steps_per_second": 5.863, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5684916973114014, | |
| "eval_runtime": 0.1723, | |
| "eval_samples_per_second": 63.86, | |
| "eval_steps_per_second": 5.805, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6276227235794067, | |
| "eval_runtime": 0.1801, | |
| "eval_samples_per_second": 61.065, | |
| "eval_steps_per_second": 5.551, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.679308295249939, | |
| "eval_runtime": 0.1681, | |
| "eval_samples_per_second": 65.423, | |
| "eval_steps_per_second": 5.948, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7099226713180542, | |
| "eval_runtime": 0.1722, | |
| "eval_samples_per_second": 63.876, | |
| "eval_steps_per_second": 5.807, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.718205213546753, | |
| "eval_runtime": 0.1747, | |
| "eval_samples_per_second": 62.956, | |
| "eval_steps_per_second": 5.723, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7049400806427002, | |
| "eval_runtime": 0.1683, | |
| "eval_samples_per_second": 65.347, | |
| "eval_steps_per_second": 5.941, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.8967489004135132, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0343, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6831462383270264, | |
| "eval_runtime": 0.1594, | |
| "eval_samples_per_second": 69.006, | |
| "eval_steps_per_second": 6.273, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6695369482040405, | |
| "eval_runtime": 0.1736, | |
| "eval_samples_per_second": 63.349, | |
| "eval_steps_per_second": 5.759, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.658433198928833, | |
| "eval_runtime": 0.1691, | |
| "eval_samples_per_second": 65.059, | |
| "eval_steps_per_second": 5.914, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.646713376045227, | |
| "eval_runtime": 0.1758, | |
| "eval_samples_per_second": 62.57, | |
| "eval_steps_per_second": 5.688, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6294078826904297, | |
| "eval_runtime": 0.1779, | |
| "eval_samples_per_second": 61.827, | |
| "eval_steps_per_second": 5.621, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6146827936172485, | |
| "eval_runtime": 0.1681, | |
| "eval_samples_per_second": 65.419, | |
| "eval_steps_per_second": 5.947, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.605461835861206, | |
| "eval_runtime": 0.1733, | |
| "eval_samples_per_second": 63.486, | |
| "eval_steps_per_second": 5.771, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6026111841201782, | |
| "eval_runtime": 0.1667, | |
| "eval_samples_per_second": 65.982, | |
| "eval_steps_per_second": 5.998, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6042994260787964, | |
| "eval_runtime": 0.1716, | |
| "eval_samples_per_second": 64.086, | |
| "eval_steps_per_second": 5.826, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6039352416992188, | |
| "eval_runtime": 0.1793, | |
| "eval_samples_per_second": 61.337, | |
| "eval_steps_per_second": 5.576, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 0.7211945652961731, | |
| "learning_rate": 0.0, | |
| "loss": 0.021, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6044108867645264, | |
| "eval_runtime": 0.165, | |
| "eval_samples_per_second": 66.682, | |
| "eval_steps_per_second": 6.062, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.572150213593088e+17, | |
| "train_loss": 0.0966740246117115, | |
| "train_runtime": 401.243, | |
| "train_samples_per_second": 14.704, | |
| "train_steps_per_second": 0.249 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0158594846725464, | |
| "eval_runtime": 0.2153, | |
| "eval_samples_per_second": 51.103, | |
| "eval_steps_per_second": 4.646, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.572150213593088e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |