| { | |
| "best_metric": 0.8181818181818182, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-85-fold5/checkpoint-61", | |
| "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": 0.5454545454545454, | |
| "eval_loss": 1.0103095769882202, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.785, | |
| "eval_steps_per_second": 6.162, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6363636363636364, | |
| "eval_loss": 0.8045657873153687, | |
| "eval_runtime": 0.1606, | |
| "eval_samples_per_second": 68.48, | |
| "eval_steps_per_second": 6.225, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.737779974937439, | |
| "eval_runtime": 0.1609, | |
| "eval_samples_per_second": 68.384, | |
| "eval_steps_per_second": 6.217, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.067632794380188, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.756, | |
| "eval_steps_per_second": 6.069, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3956468105316162, | |
| "eval_runtime": 0.1683, | |
| "eval_samples_per_second": 65.354, | |
| "eval_steps_per_second": 5.941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5799392461776733, | |
| "eval_runtime": 0.1676, | |
| "eval_samples_per_second": 65.649, | |
| "eval_steps_per_second": 5.968, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.606094479560852, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.697, | |
| "eval_steps_per_second": 5.972, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4350547790527344, | |
| "eval_runtime": 0.1678, | |
| "eval_samples_per_second": 65.537, | |
| "eval_steps_per_second": 5.958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3295589685440063, | |
| "eval_runtime": 0.1708, | |
| "eval_samples_per_second": 64.389, | |
| "eval_steps_per_second": 5.854, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 4.930849075317383, | |
| "learning_rate": 5e-05, | |
| "loss": 0.39, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2815629243850708, | |
| "eval_runtime": 0.161, | |
| "eval_samples_per_second": 68.322, | |
| "eval_steps_per_second": 6.211, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.265523910522461, | |
| "eval_runtime": 0.1668, | |
| "eval_samples_per_second": 65.937, | |
| "eval_steps_per_second": 5.994, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2039612531661987, | |
| "eval_runtime": 0.1757, | |
| "eval_samples_per_second": 62.617, | |
| "eval_steps_per_second": 5.692, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0664290189743042, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.739, | |
| "eval_steps_per_second": 6.067, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0846155881881714, | |
| "eval_runtime": 0.1608, | |
| "eval_samples_per_second": 68.402, | |
| "eval_steps_per_second": 6.218, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.214535117149353, | |
| "eval_runtime": 0.1642, | |
| "eval_samples_per_second": 66.984, | |
| "eval_steps_per_second": 6.089, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4681614637374878, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.239, | |
| "eval_steps_per_second": 6.113, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4473122358322144, | |
| "eval_runtime": 0.1607, | |
| "eval_samples_per_second": 68.471, | |
| "eval_steps_per_second": 6.225, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2699377536773682, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.907, | |
| "eval_steps_per_second": 5.992, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.246677041053772, | |
| "eval_runtime": 0.2573, | |
| "eval_samples_per_second": 42.747, | |
| "eval_steps_per_second": 3.886, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.567878484725952, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1832, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2648237943649292, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.792, | |
| "eval_steps_per_second": 6.163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2914077043533325, | |
| "eval_runtime": 0.1601, | |
| "eval_samples_per_second": 68.712, | |
| "eval_steps_per_second": 6.247, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3443835973739624, | |
| "eval_runtime": 0.1569, | |
| "eval_samples_per_second": 70.118, | |
| "eval_steps_per_second": 6.374, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5324546098709106, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.183, | |
| "eval_steps_per_second": 6.017, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6140273809432983, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.822, | |
| "eval_steps_per_second": 6.075, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6262385845184326, | |
| "eval_runtime": 0.1635, | |
| "eval_samples_per_second": 67.284, | |
| "eval_steps_per_second": 6.117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6752601861953735, | |
| "eval_runtime": 0.1704, | |
| "eval_samples_per_second": 64.572, | |
| "eval_steps_per_second": 5.87, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.653100848197937, | |
| "eval_runtime": 0.1637, | |
| "eval_samples_per_second": 67.204, | |
| "eval_steps_per_second": 6.109, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7095893621444702, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.544, | |
| "eval_steps_per_second": 6.14, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.666225790977478, | |
| "eval_runtime": 0.1364, | |
| "eval_samples_per_second": 80.626, | |
| "eval_steps_per_second": 7.33, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 2.4013149738311768, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5768946409225464, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 68.132, | |
| "eval_steps_per_second": 6.194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4446830749511719, | |
| "eval_runtime": 0.1657, | |
| "eval_samples_per_second": 66.386, | |
| "eval_steps_per_second": 6.035, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.264360785484314, | |
| "eval_runtime": 0.1666, | |
| "eval_samples_per_second": 66.03, | |
| "eval_steps_per_second": 6.003, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2033320665359497, | |
| "eval_runtime": 0.1596, | |
| "eval_samples_per_second": 68.902, | |
| "eval_steps_per_second": 6.264, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.270344614982605, | |
| "eval_runtime": 0.1609, | |
| "eval_samples_per_second": 68.347, | |
| "eval_steps_per_second": 6.213, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4491862058639526, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.359, | |
| "eval_steps_per_second": 6.124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5890190601348877, | |
| "eval_runtime": 0.1696, | |
| "eval_samples_per_second": 64.877, | |
| "eval_steps_per_second": 5.898, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.569095253944397, | |
| "eval_runtime": 0.1639, | |
| "eval_samples_per_second": 67.106, | |
| "eval_steps_per_second": 6.101, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.412721872329712, | |
| "eval_runtime": 0.1576, | |
| "eval_samples_per_second": 69.794, | |
| "eval_steps_per_second": 6.345, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3179062604904175, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.079, | |
| "eval_steps_per_second": 6.007, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 4.264218807220459, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0783, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2985975742340088, | |
| "eval_runtime": 0.1572, | |
| "eval_samples_per_second": 69.994, | |
| "eval_steps_per_second": 6.363, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3181326389312744, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.239, | |
| "eval_steps_per_second": 6.113, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4252508878707886, | |
| "eval_runtime": 0.1627, | |
| "eval_samples_per_second": 67.613, | |
| "eval_steps_per_second": 6.147, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5179203748703003, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.914, | |
| "eval_steps_per_second": 5.992, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.568513035774231, | |
| "eval_runtime": 0.172, | |
| "eval_samples_per_second": 63.949, | |
| "eval_steps_per_second": 5.814, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5695762634277344, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.707, | |
| "eval_steps_per_second": 5.973, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.757134199142456, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.512, | |
| "eval_steps_per_second": 6.137, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.912243366241455, | |
| "eval_runtime": 0.1651, | |
| "eval_samples_per_second": 66.609, | |
| "eval_steps_per_second": 6.055, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1062092781066895, | |
| "eval_runtime": 0.1666, | |
| "eval_samples_per_second": 66.025, | |
| "eval_steps_per_second": 6.002, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1660807132720947, | |
| "eval_runtime": 0.1649, | |
| "eval_samples_per_second": 66.721, | |
| "eval_steps_per_second": 6.066, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 4.0951247215271, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.056, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.183253526687622, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.787, | |
| "eval_steps_per_second": 5.981, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.240224599838257, | |
| "eval_runtime": 0.1611, | |
| "eval_samples_per_second": 68.291, | |
| "eval_steps_per_second": 6.208, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.300673723220825, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.765, | |
| "eval_steps_per_second": 6.07, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.369180679321289, | |
| "eval_runtime": 0.1588, | |
| "eval_samples_per_second": 69.263, | |
| "eval_steps_per_second": 6.297, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.382084608078003, | |
| "eval_runtime": 0.1641, | |
| "eval_samples_per_second": 67.023, | |
| "eval_steps_per_second": 6.093, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2715866565704346, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.867, | |
| "eval_steps_per_second": 6.079, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.048184871673584, | |
| "eval_runtime": 0.1627, | |
| "eval_samples_per_second": 67.596, | |
| "eval_steps_per_second": 6.145, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.878261685371399, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.071, | |
| "eval_steps_per_second": 6.006, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7967017889022827, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.839, | |
| "eval_steps_per_second": 6.076, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7035846710205078, | |
| "eval_runtime": 0.166, | |
| "eval_samples_per_second": 66.247, | |
| "eval_steps_per_second": 6.022, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 1.3352000713348389, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.052, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6389153003692627, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.885, | |
| "eval_steps_per_second": 6.08, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 1.635382056236267, | |
| "eval_runtime": 0.1649, | |
| "eval_samples_per_second": 66.706, | |
| "eval_steps_per_second": 6.064, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 1.685198187828064, | |
| "eval_runtime": 0.45, | |
| "eval_samples_per_second": 24.444, | |
| "eval_steps_per_second": 2.222, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.818864107131958, | |
| "eval_runtime": 0.1598, | |
| "eval_samples_per_second": 68.848, | |
| "eval_steps_per_second": 6.259, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9682955741882324, | |
| "eval_runtime": 0.1685, | |
| "eval_samples_per_second": 65.269, | |
| "eval_steps_per_second": 5.934, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.016566753387451, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.08, | |
| "eval_steps_per_second": 6.007, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0854508876800537, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.551, | |
| "eval_steps_per_second": 6.05, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1358840465545654, | |
| "eval_runtime": 0.1723, | |
| "eval_samples_per_second": 63.824, | |
| "eval_steps_per_second": 5.802, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.246534585952759, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.22, | |
| "eval_steps_per_second": 6.111, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2680304050445557, | |
| "eval_runtime": 0.1596, | |
| "eval_samples_per_second": 68.909, | |
| "eval_steps_per_second": 6.264, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 1.2708288431167603, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0276, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2728347778320312, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.468, | |
| "eval_steps_per_second": 6.133, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.282043218612671, | |
| "eval_runtime": 0.1579, | |
| "eval_samples_per_second": 69.686, | |
| "eval_steps_per_second": 6.335, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2427427768707275, | |
| "eval_runtime": 0.1656, | |
| "eval_samples_per_second": 66.429, | |
| "eval_steps_per_second": 6.039, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.20658540725708, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.32, | |
| "eval_steps_per_second": 5.847, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2434442043304443, | |
| "eval_runtime": 0.1632, | |
| "eval_samples_per_second": 67.392, | |
| "eval_steps_per_second": 6.127, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3205888271331787, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.241, | |
| "eval_steps_per_second": 6.113, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4407994747161865, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.119, | |
| "eval_steps_per_second": 6.011, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.480969190597534, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.577, | |
| "eval_steps_per_second": 6.143, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.509140729904175, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.806, | |
| "eval_steps_per_second": 5.982, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.486177682876587, | |
| "eval_runtime": 0.1683, | |
| "eval_samples_per_second": 65.368, | |
| "eval_steps_per_second": 5.943, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 2.5931143760681152, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0411, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4502298831939697, | |
| "eval_runtime": 0.1622, | |
| "eval_samples_per_second": 67.834, | |
| "eval_steps_per_second": 6.167, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4204084873199463, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.475, | |
| "eval_steps_per_second": 6.134, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3837873935699463, | |
| "eval_runtime": 0.1661, | |
| "eval_samples_per_second": 66.226, | |
| "eval_steps_per_second": 6.021, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.343120813369751, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 68.159, | |
| "eval_steps_per_second": 6.196, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.292693614959717, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.18, | |
| "eval_steps_per_second": 6.016, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2180917263031006, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.081, | |
| "eval_steps_per_second": 6.007, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1632635593414307, | |
| "eval_runtime": 0.1684, | |
| "eval_samples_per_second": 65.315, | |
| "eval_steps_per_second": 5.938, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0965707302093506, | |
| "eval_runtime": 0.165, | |
| "eval_samples_per_second": 66.655, | |
| "eval_steps_per_second": 6.06, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.053642988204956, | |
| "eval_runtime": 0.1705, | |
| "eval_samples_per_second": 64.51, | |
| "eval_steps_per_second": 5.865, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0427496433258057, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 68.103, | |
| "eval_steps_per_second": 6.191, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.728418231010437, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0317, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0523698329925537, | |
| "eval_runtime": 0.1681, | |
| "eval_samples_per_second": 65.445, | |
| "eval_steps_per_second": 5.95, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0489087104797363, | |
| "eval_runtime": 0.1658, | |
| "eval_samples_per_second": 66.365, | |
| "eval_steps_per_second": 6.033, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.064781904220581, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.891, | |
| "eval_steps_per_second": 5.99, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.094611644744873, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.836, | |
| "eval_steps_per_second": 6.076, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.115490436553955, | |
| "eval_runtime": 0.1669, | |
| "eval_samples_per_second": 65.919, | |
| "eval_steps_per_second": 5.993, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1469366550445557, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 68.154, | |
| "eval_steps_per_second": 6.196, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1768057346343994, | |
| "eval_runtime": 0.1696, | |
| "eval_samples_per_second": 64.857, | |
| "eval_steps_per_second": 5.896, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2026336193084717, | |
| "eval_runtime": 0.1585, | |
| "eval_samples_per_second": 69.396, | |
| "eval_steps_per_second": 6.309, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2204527854919434, | |
| "eval_runtime": 0.1606, | |
| "eval_samples_per_second": 68.492, | |
| "eval_steps_per_second": 6.227, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2304117679595947, | |
| "eval_runtime": 0.1642, | |
| "eval_samples_per_second": 67.008, | |
| "eval_steps_per_second": 6.092, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 4.493223190307617, | |
| "learning_rate": 0.0, | |
| "loss": 0.0394, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.234973430633545, | |
| "eval_runtime": 0.1591, | |
| "eval_samples_per_second": 69.124, | |
| "eval_steps_per_second": 6.284, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.570114227259392e+17, | |
| "train_loss": 0.10187353670597077, | |
| "train_runtime": 408.9093, | |
| "train_samples_per_second": 14.429, | |
| "train_steps_per_second": 0.245 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_loss": 1.635382056236267, | |
| "eval_runtime": 0.2152, | |
| "eval_samples_per_second": 51.111, | |
| "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": 4.570114227259392e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |