| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-85-fold1/checkpoint-4", | |
| "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": 0.2727272727272727, | |
| "eval_loss": 1.4041039943695068, | |
| "eval_runtime": 0.1564, | |
| "eval_samples_per_second": 70.351, | |
| "eval_steps_per_second": 6.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5454545454545454, | |
| "eval_loss": 1.1167134046554565, | |
| "eval_runtime": 0.1613, | |
| "eval_samples_per_second": 68.177, | |
| "eval_steps_per_second": 6.198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 0.7943854928016663, | |
| "eval_runtime": 0.1622, | |
| "eval_samples_per_second": 67.81, | |
| "eval_steps_per_second": 6.165, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9074404239654541, | |
| "eval_runtime": 0.1651, | |
| "eval_samples_per_second": 66.609, | |
| "eval_steps_per_second": 6.055, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3599826097488403, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.502, | |
| "eval_steps_per_second": 6.137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6643478870391846, | |
| "eval_runtime": 0.1618, | |
| "eval_samples_per_second": 68.001, | |
| "eval_steps_per_second": 6.182, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6410090923309326, | |
| "eval_runtime": 0.1639, | |
| "eval_samples_per_second": 67.133, | |
| "eval_steps_per_second": 6.103, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4549148082733154, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.435, | |
| "eval_steps_per_second": 6.13, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.36363636363636365, | |
| "eval_loss": 1.481427788734436, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.926, | |
| "eval_steps_per_second": 5.993, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 5.92126989364624, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 1.2719258069992065, | |
| "eval_runtime": 0.1585, | |
| "eval_samples_per_second": 69.4, | |
| "eval_steps_per_second": 6.309, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0360393524169922, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.778, | |
| "eval_steps_per_second": 6.162, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0690698623657227, | |
| "eval_runtime": 0.1755, | |
| "eval_samples_per_second": 62.693, | |
| "eval_steps_per_second": 5.699, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9527618288993835, | |
| "eval_runtime": 0.1656, | |
| "eval_samples_per_second": 66.416, | |
| "eval_steps_per_second": 6.038, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0429974794387817, | |
| "eval_runtime": 0.1666, | |
| "eval_samples_per_second": 66.046, | |
| "eval_steps_per_second": 6.004, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3220728635787964, | |
| "eval_runtime": 0.1667, | |
| "eval_samples_per_second": 66.001, | |
| "eval_steps_per_second": 6.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.523647665977478, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.196, | |
| "eval_steps_per_second": 6.018, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5914199352264404, | |
| "eval_runtime": 0.1656, | |
| "eval_samples_per_second": 66.437, | |
| "eval_steps_per_second": 6.04, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5015144348144531, | |
| "eval_runtime": 0.1626, | |
| "eval_samples_per_second": 67.653, | |
| "eval_steps_per_second": 6.15, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3859347105026245, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.841, | |
| "eval_steps_per_second": 6.076, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 3.4740612506866455, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4513541460037231, | |
| "eval_runtime": 0.1604, | |
| "eval_samples_per_second": 68.587, | |
| "eval_steps_per_second": 6.235, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6168898344039917, | |
| "eval_runtime": 0.1618, | |
| "eval_samples_per_second": 67.969, | |
| "eval_steps_per_second": 6.179, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.522349238395691, | |
| "eval_runtime": 0.1647, | |
| "eval_samples_per_second": 66.798, | |
| "eval_steps_per_second": 6.073, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4171791076660156, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.781, | |
| "eval_steps_per_second": 5.889, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 1.475338339805603, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.361, | |
| "eval_steps_per_second": 6.124, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5207356214523315, | |
| "eval_runtime": 0.16, | |
| "eval_samples_per_second": 68.731, | |
| "eval_steps_per_second": 6.248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7054632902145386, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.109, | |
| "eval_steps_per_second": 6.01, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7900539636611938, | |
| "eval_runtime": 0.1635, | |
| "eval_samples_per_second": 67.283, | |
| "eval_steps_per_second": 6.117, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9109127521514893, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.798, | |
| "eval_steps_per_second": 5.891, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8261302709579468, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.528, | |
| "eval_steps_per_second": 6.048, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 2.863417863845825, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1015, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5656546354293823, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.926, | |
| "eval_steps_per_second": 6.175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3513237237930298, | |
| "eval_runtime": 0.1609, | |
| "eval_samples_per_second": 68.346, | |
| "eval_steps_per_second": 6.213, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3374041318893433, | |
| "eval_runtime": 0.1668, | |
| "eval_samples_per_second": 65.94, | |
| "eval_steps_per_second": 5.995, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4942458868026733, | |
| "eval_runtime": 0.1594, | |
| "eval_samples_per_second": 69.018, | |
| "eval_steps_per_second": 6.274, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.773066759109497, | |
| "eval_runtime": 0.1685, | |
| "eval_samples_per_second": 65.276, | |
| "eval_steps_per_second": 5.934, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8369468450546265, | |
| "eval_runtime": 0.1744, | |
| "eval_samples_per_second": 63.091, | |
| "eval_steps_per_second": 5.736, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7328110933303833, | |
| "eval_runtime": 0.165, | |
| "eval_samples_per_second": 66.653, | |
| "eval_steps_per_second": 6.059, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5451053380966187, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.933, | |
| "eval_steps_per_second": 6.176, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4483166933059692, | |
| "eval_runtime": 0.1652, | |
| "eval_samples_per_second": 66.579, | |
| "eval_steps_per_second": 6.053, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.428899884223938, | |
| "eval_runtime": 0.1784, | |
| "eval_samples_per_second": 61.66, | |
| "eval_steps_per_second": 5.605, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 2.0319314002990723, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0819, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3921602964401245, | |
| "eval_runtime": 0.1575, | |
| "eval_samples_per_second": 69.834, | |
| "eval_steps_per_second": 6.349, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4001747369766235, | |
| "eval_runtime": 0.1717, | |
| "eval_samples_per_second": 64.056, | |
| "eval_steps_per_second": 5.823, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3672713041305542, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.498, | |
| "eval_steps_per_second": 6.136, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2193830013275146, | |
| "eval_runtime": 0.1693, | |
| "eval_samples_per_second": 64.983, | |
| "eval_steps_per_second": 5.908, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2879159450531006, | |
| "eval_runtime": 0.1697, | |
| "eval_samples_per_second": 64.802, | |
| "eval_steps_per_second": 5.891, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4545269012451172, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.576, | |
| "eval_steps_per_second": 6.143, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.690229058265686, | |
| "eval_runtime": 0.1655, | |
| "eval_samples_per_second": 66.484, | |
| "eval_steps_per_second": 6.044, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.841526746749878, | |
| "eval_runtime": 0.1592, | |
| "eval_samples_per_second": 69.109, | |
| "eval_steps_per_second": 6.283, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8891047239303589, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.73, | |
| "eval_steps_per_second": 6.066, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8338725566864014, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.92, | |
| "eval_steps_per_second": 6.084, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 3.850102186203003, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0551, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8432774543762207, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.484, | |
| "eval_steps_per_second": 6.135, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8432278633117676, | |
| "eval_runtime": 0.2062, | |
| "eval_samples_per_second": 53.334, | |
| "eval_steps_per_second": 4.849, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8002498149871826, | |
| "eval_runtime": 0.1696, | |
| "eval_samples_per_second": 64.874, | |
| "eval_steps_per_second": 5.898, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7276179790496826, | |
| "eval_runtime": 0.1613, | |
| "eval_samples_per_second": 68.189, | |
| "eval_steps_per_second": 6.199, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.576358437538147, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.937, | |
| "eval_steps_per_second": 6.176, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3950941562652588, | |
| "eval_runtime": 0.1733, | |
| "eval_samples_per_second": 63.49, | |
| "eval_steps_per_second": 5.772, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4242897033691406, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.775, | |
| "eval_steps_per_second": 5.98, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5619553327560425, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.374, | |
| "eval_steps_per_second": 6.125, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6896965503692627, | |
| "eval_runtime": 0.166, | |
| "eval_samples_per_second": 66.266, | |
| "eval_steps_per_second": 6.024, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.799486517906189, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.5, | |
| "eval_steps_per_second": 5.864, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.7450773119926453, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0413, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.873887300491333, | |
| "eval_runtime": 0.1624, | |
| "eval_samples_per_second": 67.749, | |
| "eval_steps_per_second": 6.159, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8485583066940308, | |
| "eval_runtime": 0.1594, | |
| "eval_samples_per_second": 69.026, | |
| "eval_steps_per_second": 6.275, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8072762489318848, | |
| "eval_runtime": 0.1617, | |
| "eval_samples_per_second": 68.035, | |
| "eval_steps_per_second": 6.185, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8192728757858276, | |
| "eval_runtime": 0.166, | |
| "eval_samples_per_second": 66.255, | |
| "eval_steps_per_second": 6.023, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.760420560836792, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.12, | |
| "eval_steps_per_second": 6.011, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6326606273651123, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.711, | |
| "eval_steps_per_second": 5.974, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5446624755859375, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.898, | |
| "eval_steps_per_second": 6.082, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.424346923828125, | |
| "eval_runtime": 0.1647, | |
| "eval_samples_per_second": 66.773, | |
| "eval_steps_per_second": 6.07, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3809901475906372, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.542, | |
| "eval_steps_per_second": 6.14, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3640745878219604, | |
| "eval_runtime": 0.1716, | |
| "eval_samples_per_second": 64.118, | |
| "eval_steps_per_second": 5.829, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 1.508904218673706, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.038, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4687689542770386, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.948, | |
| "eval_steps_per_second": 6.177, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5677317380905151, | |
| "eval_runtime": 0.1666, | |
| "eval_samples_per_second": 66.03, | |
| "eval_steps_per_second": 6.003, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.717352271080017, | |
| "eval_runtime": 0.1661, | |
| "eval_samples_per_second": 66.219, | |
| "eval_steps_per_second": 6.02, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.791959285736084, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.755, | |
| "eval_steps_per_second": 6.16, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8999717235565186, | |
| "eval_runtime": 0.1611, | |
| "eval_samples_per_second": 68.291, | |
| "eval_steps_per_second": 6.208, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9467865228652954, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.731, | |
| "eval_steps_per_second": 6.066, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9872097969055176, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.843, | |
| "eval_steps_per_second": 6.077, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0208170413970947, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.445, | |
| "eval_steps_per_second": 6.131, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0134825706481934, | |
| "eval_runtime": 0.1701, | |
| "eval_samples_per_second": 64.674, | |
| "eval_steps_per_second": 5.879, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9762377738952637, | |
| "eval_runtime": 0.1647, | |
| "eval_samples_per_second": 66.795, | |
| "eval_steps_per_second": 6.072, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 1.9063314199447632, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0365, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9576034545898438, | |
| "eval_runtime": 0.1617, | |
| "eval_samples_per_second": 68.013, | |
| "eval_steps_per_second": 6.183, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.931043267250061, | |
| "eval_runtime": 0.1692, | |
| "eval_samples_per_second": 65.005, | |
| "eval_steps_per_second": 5.91, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.849521517753601, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.543, | |
| "eval_steps_per_second": 6.049, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7683414220809937, | |
| "eval_runtime": 0.1658, | |
| "eval_samples_per_second": 66.355, | |
| "eval_steps_per_second": 6.032, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.710900902748108, | |
| "eval_runtime": 0.1657, | |
| "eval_samples_per_second": 66.404, | |
| "eval_steps_per_second": 6.037, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6437627077102661, | |
| "eval_runtime": 0.1641, | |
| "eval_samples_per_second": 67.039, | |
| "eval_steps_per_second": 6.094, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6153919696807861, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.115, | |
| "eval_steps_per_second": 6.01, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5714579820632935, | |
| "eval_runtime": 0.1606, | |
| "eval_samples_per_second": 68.51, | |
| "eval_steps_per_second": 6.228, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5428203344345093, | |
| "eval_runtime": 0.1625, | |
| "eval_samples_per_second": 67.699, | |
| "eval_steps_per_second": 6.154, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5164352655410767, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.086, | |
| "eval_steps_per_second": 6.008, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.735504388809204, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.038, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5007927417755127, | |
| "eval_runtime": 0.1612, | |
| "eval_samples_per_second": 68.243, | |
| "eval_steps_per_second": 6.204, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4729591608047485, | |
| "eval_runtime": 0.1685, | |
| "eval_samples_per_second": 65.283, | |
| "eval_steps_per_second": 5.935, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4492815732955933, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.72, | |
| "eval_steps_per_second": 5.975, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4728164672851562, | |
| "eval_runtime": 0.1687, | |
| "eval_samples_per_second": 65.196, | |
| "eval_steps_per_second": 5.927, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5032776594161987, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.93, | |
| "eval_steps_per_second": 6.175, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5345958471298218, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.89, | |
| "eval_steps_per_second": 6.081, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5555568933486938, | |
| "eval_runtime": 0.1681, | |
| "eval_samples_per_second": 65.45, | |
| "eval_steps_per_second": 5.95, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5642927885055542, | |
| "eval_runtime": 0.1687, | |
| "eval_samples_per_second": 65.192, | |
| "eval_steps_per_second": 5.927, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.575886845588684, | |
| "eval_runtime": 0.1637, | |
| "eval_samples_per_second": 67.21, | |
| "eval_steps_per_second": 6.11, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5806941986083984, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.959, | |
| "eval_steps_per_second": 6.178, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 2.8808040618896484, | |
| "learning_rate": 0.0, | |
| "loss": 0.0191, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.580631971359253, | |
| "eval_runtime": 0.1593, | |
| "eval_samples_per_second": 69.053, | |
| "eval_steps_per_second": 6.278, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.570114227259392e+17, | |
| "train_loss": 0.09848821982741356, | |
| "train_runtime": 419.3344, | |
| "train_samples_per_second": 14.07, | |
| "train_steps_per_second": 0.238 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9074404239654541, | |
| "eval_runtime": 0.218, | |
| "eval_samples_per_second": 50.454, | |
| "eval_steps_per_second": 4.587, | |
| "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": 4.570114227259392e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |