| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "deit-base-distilled-patch16-224-hasta-85-fold1/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": 0.09090909090909091, | |
| "eval_loss": 1.2771788835525513, | |
| "eval_runtime": 0.1734, | |
| "eval_samples_per_second": 63.434, | |
| "eval_steps_per_second": 5.767, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.18181818181818182, | |
| "eval_loss": 1.1447755098342896, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.839, | |
| "eval_steps_per_second": 6.076, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9744274020195007, | |
| "eval_runtime": 0.1717, | |
| "eval_samples_per_second": 64.083, | |
| "eval_steps_per_second": 5.826, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9233787655830383, | |
| "eval_runtime": 0.172, | |
| "eval_samples_per_second": 63.969, | |
| "eval_steps_per_second": 5.815, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0760316848754883, | |
| "eval_runtime": 0.1729, | |
| "eval_samples_per_second": 63.616, | |
| "eval_steps_per_second": 5.783, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3222259283065796, | |
| "eval_runtime": 0.1683, | |
| "eval_samples_per_second": 65.343, | |
| "eval_steps_per_second": 5.94, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5247870683670044, | |
| "eval_runtime": 0.1317, | |
| "eval_samples_per_second": 83.521, | |
| "eval_steps_per_second": 7.593, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6138737201690674, | |
| "eval_runtime": 0.1738, | |
| "eval_samples_per_second": 63.299, | |
| "eval_steps_per_second": 5.754, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.671146035194397, | |
| "eval_runtime": 0.1801, | |
| "eval_samples_per_second": 61.094, | |
| "eval_steps_per_second": 5.554, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.1924768686294556, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3554, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7354072332382202, | |
| "eval_runtime": 0.1604, | |
| "eval_samples_per_second": 68.592, | |
| "eval_steps_per_second": 6.236, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6721187829971313, | |
| "eval_runtime": 0.1745, | |
| "eval_samples_per_second": 63.042, | |
| "eval_steps_per_second": 5.731, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5987907648086548, | |
| "eval_runtime": 0.1742, | |
| "eval_samples_per_second": 63.135, | |
| "eval_steps_per_second": 5.74, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5959930419921875, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.72, | |
| "eval_steps_per_second": 5.975, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.583227515220642, | |
| "eval_runtime": 0.1711, | |
| "eval_samples_per_second": 64.284, | |
| "eval_steps_per_second": 5.844, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.568271517753601, | |
| "eval_runtime": 0.17, | |
| "eval_samples_per_second": 64.702, | |
| "eval_steps_per_second": 5.882, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5774298906326294, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.672, | |
| "eval_steps_per_second": 5.879, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6467945575714111, | |
| "eval_runtime": 0.1692, | |
| "eval_samples_per_second": 65.014, | |
| "eval_steps_per_second": 5.91, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7090667486190796, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.178, | |
| "eval_steps_per_second": 5.925, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7276203632354736, | |
| "eval_runtime": 0.1682, | |
| "eval_samples_per_second": 65.379, | |
| "eval_steps_per_second": 5.944, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1.0401579141616821, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1335, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7052208185195923, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.92, | |
| "eval_steps_per_second": 5.993, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.642613172531128, | |
| "eval_runtime": 0.1706, | |
| "eval_samples_per_second": 64.477, | |
| "eval_steps_per_second": 5.862, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5315605401992798, | |
| "eval_runtime": 0.1679, | |
| "eval_samples_per_second": 65.515, | |
| "eval_steps_per_second": 5.956, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.401681661605835, | |
| "eval_runtime": 0.2092, | |
| "eval_samples_per_second": 52.574, | |
| "eval_steps_per_second": 4.779, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.300853967666626, | |
| "eval_runtime": 0.1638, | |
| "eval_samples_per_second": 67.161, | |
| "eval_steps_per_second": 6.106, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2863625288009644, | |
| "eval_runtime": 0.1692, | |
| "eval_samples_per_second": 64.994, | |
| "eval_steps_per_second": 5.909, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.393377423286438, | |
| "eval_runtime": 0.1719, | |
| "eval_samples_per_second": 64.001, | |
| "eval_steps_per_second": 5.818, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4435607194900513, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.321, | |
| "eval_steps_per_second": 5.847, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5751649141311646, | |
| "eval_runtime": 0.1734, | |
| "eval_samples_per_second": 63.455, | |
| "eval_steps_per_second": 5.769, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6211150884628296, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.665, | |
| "eval_steps_per_second": 5.879, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 1.1806550025939941, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0769, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5944229364395142, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.545, | |
| "eval_steps_per_second": 6.14, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5282962322235107, | |
| "eval_runtime": 0.1679, | |
| "eval_samples_per_second": 65.5, | |
| "eval_steps_per_second": 5.955, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4341241121292114, | |
| "eval_runtime": 0.1709, | |
| "eval_samples_per_second": 64.372, | |
| "eval_steps_per_second": 5.852, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.451222538948059, | |
| "eval_runtime": 0.1774, | |
| "eval_samples_per_second": 62.024, | |
| "eval_steps_per_second": 5.639, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4979816675186157, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.797, | |
| "eval_steps_per_second": 5.891, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5802719593048096, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.014, | |
| "eval_steps_per_second": 5.819, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7675877809524536, | |
| "eval_runtime": 0.1737, | |
| "eval_samples_per_second": 63.319, | |
| "eval_steps_per_second": 5.756, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8581143617630005, | |
| "eval_runtime": 0.1763, | |
| "eval_samples_per_second": 62.379, | |
| "eval_steps_per_second": 5.671, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8816009759902954, | |
| "eval_runtime": 0.1739, | |
| "eval_samples_per_second": 63.25, | |
| "eval_steps_per_second": 5.75, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8316550254821777, | |
| "eval_runtime": 0.1703, | |
| "eval_samples_per_second": 64.601, | |
| "eval_steps_per_second": 5.873, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.9434149861335754, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0505, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7445045709609985, | |
| "eval_runtime": 0.1655, | |
| "eval_samples_per_second": 66.473, | |
| "eval_steps_per_second": 6.043, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6965172290802002, | |
| "eval_runtime": 0.1727, | |
| "eval_samples_per_second": 63.702, | |
| "eval_steps_per_second": 5.791, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.721003770828247, | |
| "eval_runtime": 0.1728, | |
| "eval_samples_per_second": 63.673, | |
| "eval_steps_per_second": 5.788, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6903266906738281, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.544, | |
| "eval_steps_per_second": 5.868, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.694361925125122, | |
| "eval_runtime": 0.1732, | |
| "eval_samples_per_second": 63.528, | |
| "eval_steps_per_second": 5.775, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6923259496688843, | |
| "eval_runtime": 0.1663, | |
| "eval_samples_per_second": 66.135, | |
| "eval_steps_per_second": 6.012, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7470028400421143, | |
| "eval_runtime": 0.1683, | |
| "eval_samples_per_second": 65.348, | |
| "eval_steps_per_second": 5.941, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7501949071884155, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.8, | |
| "eval_steps_per_second": 5.982, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7738779783248901, | |
| "eval_runtime": 0.174, | |
| "eval_samples_per_second": 63.224, | |
| "eval_steps_per_second": 5.748, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7819253206253052, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.658, | |
| "eval_steps_per_second": 5.878, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 0.3251829743385315, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0255, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8199766874313354, | |
| "eval_runtime": 0.1617, | |
| "eval_samples_per_second": 68.041, | |
| "eval_steps_per_second": 6.186, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8121682405471802, | |
| "eval_runtime": 0.1715, | |
| "eval_samples_per_second": 64.129, | |
| "eval_steps_per_second": 5.83, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7939274311065674, | |
| "eval_runtime": 0.1789, | |
| "eval_samples_per_second": 61.501, | |
| "eval_steps_per_second": 5.591, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7736003398895264, | |
| "eval_runtime": 0.1717, | |
| "eval_samples_per_second": 64.058, | |
| "eval_steps_per_second": 5.823, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7411243915557861, | |
| "eval_runtime": 0.17, | |
| "eval_samples_per_second": 64.709, | |
| "eval_steps_per_second": 5.883, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6772898435592651, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.013, | |
| "eval_steps_per_second": 5.819, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6555858850479126, | |
| "eval_runtime": 0.172, | |
| "eval_samples_per_second": 63.951, | |
| "eval_steps_per_second": 5.814, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6766685247421265, | |
| "eval_runtime": 0.1687, | |
| "eval_samples_per_second": 65.223, | |
| "eval_steps_per_second": 5.929, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6623153686523438, | |
| "eval_runtime": 0.1813, | |
| "eval_samples_per_second": 60.676, | |
| "eval_steps_per_second": 5.516, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6553212404251099, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.947, | |
| "eval_steps_per_second": 5.904, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.4616081416606903, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0227, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6682250499725342, | |
| "eval_runtime": 0.1787, | |
| "eval_samples_per_second": 61.567, | |
| "eval_steps_per_second": 5.597, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.62090265750885, | |
| "eval_runtime": 0.1815, | |
| "eval_samples_per_second": 60.623, | |
| "eval_steps_per_second": 5.511, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6187800168991089, | |
| "eval_runtime": 0.1699, | |
| "eval_samples_per_second": 64.734, | |
| "eval_steps_per_second": 5.885, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6919440031051636, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.021, | |
| "eval_steps_per_second": 5.82, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7957440614700317, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.31, | |
| "eval_steps_per_second": 5.846, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8749808073043823, | |
| "eval_runtime": 0.1689, | |
| "eval_samples_per_second": 65.119, | |
| "eval_steps_per_second": 5.92, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9156414270401, | |
| "eval_runtime": 0.1703, | |
| "eval_samples_per_second": 64.59, | |
| "eval_steps_per_second": 5.872, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9163463115692139, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.174, | |
| "eval_steps_per_second": 5.743, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8968899250030518, | |
| "eval_runtime": 0.1686, | |
| "eval_samples_per_second": 65.251, | |
| "eval_steps_per_second": 5.932, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.881422519683838, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.319, | |
| "eval_steps_per_second": 5.847, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 0.3331330716609955, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0185, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8714560270309448, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 64.821, | |
| "eval_steps_per_second": 5.893, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8891681432724, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.943, | |
| "eval_steps_per_second": 5.904, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9382548332214355, | |
| "eval_runtime": 0.1738, | |
| "eval_samples_per_second": 63.278, | |
| "eval_steps_per_second": 5.753, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9627383947372437, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 64.822, | |
| "eval_steps_per_second": 5.893, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0154221057891846, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.527, | |
| "eval_steps_per_second": 5.866, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.032640218734741, | |
| "eval_runtime": 0.1767, | |
| "eval_samples_per_second": 62.244, | |
| "eval_steps_per_second": 5.659, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0424911975860596, | |
| "eval_runtime": 0.1711, | |
| "eval_samples_per_second": 64.272, | |
| "eval_steps_per_second": 5.843, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0586304664611816, | |
| "eval_runtime": 0.177, | |
| "eval_samples_per_second": 62.132, | |
| "eval_steps_per_second": 5.648, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.058166265487671, | |
| "eval_runtime": 0.1793, | |
| "eval_samples_per_second": 61.357, | |
| "eval_steps_per_second": 5.578, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.086315870285034, | |
| "eval_runtime": 0.1722, | |
| "eval_samples_per_second": 63.888, | |
| "eval_steps_per_second": 5.808, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 0.5901564955711365, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0246, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.123337507247925, | |
| "eval_runtime": 0.168, | |
| "eval_samples_per_second": 65.467, | |
| "eval_steps_per_second": 5.952, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1527483463287354, | |
| "eval_runtime": 0.1714, | |
| "eval_samples_per_second": 64.176, | |
| "eval_steps_per_second": 5.834, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.176025152206421, | |
| "eval_runtime": 0.177, | |
| "eval_samples_per_second": 62.154, | |
| "eval_steps_per_second": 5.65, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.190654993057251, | |
| "eval_runtime": 0.1738, | |
| "eval_samples_per_second": 63.301, | |
| "eval_steps_per_second": 5.755, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1858766078948975, | |
| "eval_runtime": 0.179, | |
| "eval_samples_per_second": 61.465, | |
| "eval_steps_per_second": 5.588, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.165440320968628, | |
| "eval_runtime": 0.1802, | |
| "eval_samples_per_second": 61.042, | |
| "eval_steps_per_second": 5.549, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1478655338287354, | |
| "eval_runtime": 0.1681, | |
| "eval_samples_per_second": 65.441, | |
| "eval_steps_per_second": 5.949, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1194212436676025, | |
| "eval_runtime": 0.1706, | |
| "eval_samples_per_second": 64.486, | |
| "eval_steps_per_second": 5.862, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1058995723724365, | |
| "eval_runtime": 0.173, | |
| "eval_samples_per_second": 63.597, | |
| "eval_steps_per_second": 5.782, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.103247880935669, | |
| "eval_runtime": 0.1721, | |
| "eval_samples_per_second": 63.931, | |
| "eval_steps_per_second": 5.812, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.2021247148513794, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0228, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0998663902282715, | |
| "eval_runtime": 0.1654, | |
| "eval_samples_per_second": 66.509, | |
| "eval_steps_per_second": 6.046, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1037116050720215, | |
| "eval_runtime": 0.1718, | |
| "eval_samples_per_second": 64.033, | |
| "eval_steps_per_second": 5.821, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1025755405426025, | |
| "eval_runtime": 0.175, | |
| "eval_samples_per_second": 62.874, | |
| "eval_steps_per_second": 5.716, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1132094860076904, | |
| "eval_runtime": 0.1668, | |
| "eval_samples_per_second": 65.929, | |
| "eval_steps_per_second": 5.994, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1301839351654053, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.331, | |
| "eval_steps_per_second": 5.848, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1452560424804688, | |
| "eval_runtime": 0.1758, | |
| "eval_samples_per_second": 62.58, | |
| "eval_steps_per_second": 5.689, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.163395643234253, | |
| "eval_runtime": 0.1756, | |
| "eval_samples_per_second": 62.64, | |
| "eval_steps_per_second": 5.695, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1761701107025146, | |
| "eval_runtime": 0.1744, | |
| "eval_samples_per_second": 63.075, | |
| "eval_steps_per_second": 5.734, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1859476566314697, | |
| "eval_runtime": 0.1746, | |
| "eval_samples_per_second": 63.0, | |
| "eval_steps_per_second": 5.727, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1915647983551025, | |
| "eval_runtime": 0.1687, | |
| "eval_samples_per_second": 65.197, | |
| "eval_steps_per_second": 5.927, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 1.034210205078125, | |
| "learning_rate": 0.0, | |
| "loss": 0.0142, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.193308115005493, | |
| "eval_runtime": 0.1657, | |
| "eval_samples_per_second": 66.395, | |
| "eval_steps_per_second": 6.036, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.572150213593088e+17, | |
| "train_loss": 0.07446861431002617, | |
| "train_runtime": 420.0976, | |
| "train_samples_per_second": 14.044, | |
| "train_steps_per_second": 0.238 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9744274020195007, | |
| "eval_runtime": 0.2198, | |
| "eval_samples_per_second": 50.054, | |
| "eval_steps_per_second": 4.55, | |
| "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 | |
| } | |