| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-85-fold4/checkpoint-2", | |
| "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": 0.6363636363636364, | |
| "eval_loss": 1.0761245489120483, | |
| "eval_runtime": 0.1602, | |
| "eval_samples_per_second": 68.658, | |
| "eval_steps_per_second": 6.242, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9257901906967163, | |
| "eval_runtime": 0.1749, | |
| "eval_samples_per_second": 62.906, | |
| "eval_steps_per_second": 5.719, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.8309900164604187, | |
| "eval_runtime": 0.1693, | |
| "eval_samples_per_second": 64.981, | |
| "eval_steps_per_second": 5.907, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9402067065238953, | |
| "eval_runtime": 0.1613, | |
| "eval_samples_per_second": 68.199, | |
| "eval_steps_per_second": 6.2, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1380892992019653, | |
| "eval_runtime": 0.16, | |
| "eval_samples_per_second": 68.741, | |
| "eval_steps_per_second": 6.249, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2811881303787231, | |
| "eval_runtime": 0.1681, | |
| "eval_samples_per_second": 65.423, | |
| "eval_steps_per_second": 5.948, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2678855657577515, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.483, | |
| "eval_steps_per_second": 6.135, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.170410394668579, | |
| "eval_runtime": 0.1667, | |
| "eval_samples_per_second": 65.969, | |
| "eval_steps_per_second": 5.997, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1909043788909912, | |
| "eval_runtime": 0.1613, | |
| "eval_samples_per_second": 68.207, | |
| "eval_steps_per_second": 6.201, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2.4812705516815186, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3269, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2981127500534058, | |
| "eval_runtime": 0.1617, | |
| "eval_samples_per_second": 68.039, | |
| "eval_steps_per_second": 6.185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2565165758132935, | |
| "eval_runtime": 0.168, | |
| "eval_samples_per_second": 65.493, | |
| "eval_steps_per_second": 5.954, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1475425958633423, | |
| "eval_runtime": 0.1709, | |
| "eval_samples_per_second": 64.378, | |
| "eval_steps_per_second": 5.853, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0584505796432495, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 68.153, | |
| "eval_steps_per_second": 6.196, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0294095277786255, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.569, | |
| "eval_steps_per_second": 6.143, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.064909815788269, | |
| "eval_runtime": 0.159, | |
| "eval_samples_per_second": 69.19, | |
| "eval_steps_per_second": 6.29, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1712483167648315, | |
| "eval_runtime": 0.1606, | |
| "eval_samples_per_second": 68.479, | |
| "eval_steps_per_second": 6.225, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.208996057510376, | |
| "eval_runtime": 0.1616, | |
| "eval_samples_per_second": 68.068, | |
| "eval_steps_per_second": 6.188, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1579047441482544, | |
| "eval_runtime": 0.1671, | |
| "eval_samples_per_second": 65.83, | |
| "eval_steps_per_second": 5.985, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.094255805015564, | |
| "eval_runtime": 0.1612, | |
| "eval_samples_per_second": 68.223, | |
| "eval_steps_per_second": 6.202, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1.379998803138733, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1921, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1877329349517822, | |
| "eval_runtime": 0.1591, | |
| "eval_samples_per_second": 69.154, | |
| "eval_steps_per_second": 6.287, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3909109830856323, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.439, | |
| "eval_steps_per_second": 6.131, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4300814867019653, | |
| "eval_runtime": 0.1613, | |
| "eval_samples_per_second": 68.186, | |
| "eval_steps_per_second": 6.199, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.421010136604309, | |
| "eval_runtime": 0.1626, | |
| "eval_samples_per_second": 67.631, | |
| "eval_steps_per_second": 6.148, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3993977308273315, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.45, | |
| "eval_steps_per_second": 6.132, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3649417161941528, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.235, | |
| "eval_steps_per_second": 6.112, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3244379758834839, | |
| "eval_runtime": 0.1588, | |
| "eval_samples_per_second": 69.274, | |
| "eval_steps_per_second": 6.298, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2861114740371704, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.756, | |
| "eval_steps_per_second": 6.069, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1633926630020142, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.444, | |
| "eval_steps_per_second": 6.131, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9854040741920471, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.588, | |
| "eval_steps_per_second": 6.144, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 3.8071939945220947, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1374, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0608080625534058, | |
| "eval_runtime": 0.1613, | |
| "eval_samples_per_second": 68.183, | |
| "eval_steps_per_second": 6.198, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3091832399368286, | |
| "eval_runtime": 0.1661, | |
| "eval_samples_per_second": 66.23, | |
| "eval_steps_per_second": 6.021, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4678875207901, | |
| "eval_runtime": 0.1668, | |
| "eval_samples_per_second": 65.935, | |
| "eval_steps_per_second": 5.994, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4396743774414062, | |
| "eval_runtime": 0.1611, | |
| "eval_samples_per_second": 68.27, | |
| "eval_steps_per_second": 6.206, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2948559522628784, | |
| "eval_runtime": 0.1641, | |
| "eval_samples_per_second": 67.029, | |
| "eval_steps_per_second": 6.094, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2339611053466797, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.194, | |
| "eval_steps_per_second": 6.018, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2524040937423706, | |
| "eval_runtime": 0.1641, | |
| "eval_samples_per_second": 67.031, | |
| "eval_steps_per_second": 6.094, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.210758090019226, | |
| "eval_runtime": 0.1604, | |
| "eval_samples_per_second": 68.59, | |
| "eval_steps_per_second": 6.235, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1877820491790771, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 68.163, | |
| "eval_steps_per_second": 6.197, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.140025019645691, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.771, | |
| "eval_steps_per_second": 5.979, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 3.4294357299804688, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0886, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1185942888259888, | |
| "eval_runtime": 0.1634, | |
| "eval_samples_per_second": 67.302, | |
| "eval_steps_per_second": 6.118, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3144683837890625, | |
| "eval_runtime": 0.1649, | |
| "eval_samples_per_second": 66.707, | |
| "eval_steps_per_second": 6.064, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4748523235321045, | |
| "eval_runtime": 0.171, | |
| "eval_samples_per_second": 64.325, | |
| "eval_steps_per_second": 5.848, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5772589445114136, | |
| "eval_runtime": 0.1605, | |
| "eval_samples_per_second": 68.525, | |
| "eval_steps_per_second": 6.23, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6792014837265015, | |
| "eval_runtime": 0.1601, | |
| "eval_samples_per_second": 68.694, | |
| "eval_steps_per_second": 6.245, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7716128826141357, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.797, | |
| "eval_steps_per_second": 6.163, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8942890167236328, | |
| "eval_runtime": 0.1652, | |
| "eval_samples_per_second": 66.588, | |
| "eval_steps_per_second": 6.053, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8541417121887207, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.353, | |
| "eval_steps_per_second": 6.123, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.665623426437378, | |
| "eval_runtime": 0.1606, | |
| "eval_samples_per_second": 68.506, | |
| "eval_steps_per_second": 6.228, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4896851778030396, | |
| "eval_runtime": 0.1632, | |
| "eval_samples_per_second": 67.4, | |
| "eval_steps_per_second": 6.127, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 1.571501612663269, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0509, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2921388149261475, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.52, | |
| "eval_steps_per_second": 6.138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.202133059501648, | |
| "eval_runtime": 0.1643, | |
| "eval_samples_per_second": 66.963, | |
| "eval_steps_per_second": 6.088, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2643142938613892, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.855, | |
| "eval_steps_per_second": 6.078, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4621602296829224, | |
| "eval_runtime": 0.1659, | |
| "eval_samples_per_second": 66.297, | |
| "eval_steps_per_second": 6.027, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5043293237686157, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 68.097, | |
| "eval_steps_per_second": 6.191, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5063341856002808, | |
| "eval_runtime": 0.1597, | |
| "eval_samples_per_second": 68.859, | |
| "eval_steps_per_second": 6.26, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.460426688194275, | |
| "eval_runtime": 0.1598, | |
| "eval_samples_per_second": 68.857, | |
| "eval_steps_per_second": 6.26, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.341434359550476, | |
| "eval_runtime": 0.1593, | |
| "eval_samples_per_second": 69.031, | |
| "eval_steps_per_second": 6.276, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1789151430130005, | |
| "eval_runtime": 0.1605, | |
| "eval_samples_per_second": 68.543, | |
| "eval_steps_per_second": 6.231, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.17151939868927, | |
| "eval_runtime": 0.1618, | |
| "eval_samples_per_second": 67.979, | |
| "eval_steps_per_second": 6.18, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 0.6576238870620728, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0471, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.255001187324524, | |
| "eval_runtime": 0.1599, | |
| "eval_samples_per_second": 68.777, | |
| "eval_steps_per_second": 6.252, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3513411283493042, | |
| "eval_runtime": 0.1668, | |
| "eval_samples_per_second": 65.936, | |
| "eval_steps_per_second": 5.994, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4921551942825317, | |
| "eval_runtime": 0.1601, | |
| "eval_samples_per_second": 68.712, | |
| "eval_steps_per_second": 6.247, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6911064386367798, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.845, | |
| "eval_steps_per_second": 6.077, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7746772766113281, | |
| "eval_runtime": 0.1598, | |
| "eval_samples_per_second": 68.851, | |
| "eval_steps_per_second": 6.259, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7659435272216797, | |
| "eval_runtime": 0.1605, | |
| "eval_samples_per_second": 68.552, | |
| "eval_steps_per_second": 6.232, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6729789972305298, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.075, | |
| "eval_steps_per_second": 6.007, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5296233892440796, | |
| "eval_runtime": 0.1752, | |
| "eval_samples_per_second": 62.779, | |
| "eval_steps_per_second": 5.707, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.497283935546875, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.538, | |
| "eval_steps_per_second": 6.049, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4649982452392578, | |
| "eval_runtime": 0.1608, | |
| "eval_samples_per_second": 68.421, | |
| "eval_steps_per_second": 6.22, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 2.330393075942993, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0212, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4969764947891235, | |
| "eval_runtime": 0.1601, | |
| "eval_samples_per_second": 68.703, | |
| "eval_steps_per_second": 6.246, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5021611452102661, | |
| "eval_runtime": 0.1647, | |
| "eval_samples_per_second": 66.792, | |
| "eval_steps_per_second": 6.072, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5275318622589111, | |
| "eval_runtime": 0.1611, | |
| "eval_samples_per_second": 68.289, | |
| "eval_steps_per_second": 6.208, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5780352354049683, | |
| "eval_runtime": 0.1625, | |
| "eval_samples_per_second": 67.706, | |
| "eval_steps_per_second": 6.155, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.714918851852417, | |
| "eval_runtime": 0.1604, | |
| "eval_samples_per_second": 68.585, | |
| "eval_steps_per_second": 6.235, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8055766820907593, | |
| "eval_runtime": 0.165, | |
| "eval_samples_per_second": 66.661, | |
| "eval_steps_per_second": 6.06, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8394047021865845, | |
| "eval_runtime": 0.165, | |
| "eval_samples_per_second": 66.656, | |
| "eval_steps_per_second": 6.06, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8526023626327515, | |
| "eval_runtime": 0.1626, | |
| "eval_samples_per_second": 67.651, | |
| "eval_steps_per_second": 6.15, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.794382095336914, | |
| "eval_runtime": 0.1959, | |
| "eval_samples_per_second": 56.138, | |
| "eval_steps_per_second": 5.103, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7440181970596313, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.546, | |
| "eval_steps_per_second": 6.141, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 1.3924683332443237, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0313, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.699449896812439, | |
| "eval_runtime": 0.1553, | |
| "eval_samples_per_second": 70.817, | |
| "eval_steps_per_second": 6.438, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6076394319534302, | |
| "eval_runtime": 0.1656, | |
| "eval_samples_per_second": 66.42, | |
| "eval_steps_per_second": 6.038, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5752601623535156, | |
| "eval_runtime": 0.1584, | |
| "eval_samples_per_second": 69.43, | |
| "eval_steps_per_second": 6.312, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5831207036972046, | |
| "eval_runtime": 0.1714, | |
| "eval_samples_per_second": 64.168, | |
| "eval_steps_per_second": 5.833, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5471209287643433, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.756, | |
| "eval_steps_per_second": 6.069, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5600395202636719, | |
| "eval_runtime": 0.1603, | |
| "eval_samples_per_second": 68.607, | |
| "eval_steps_per_second": 6.237, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.583156943321228, | |
| "eval_runtime": 0.1649, | |
| "eval_samples_per_second": 66.722, | |
| "eval_steps_per_second": 6.066, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5818580389022827, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.827, | |
| "eval_steps_per_second": 6.075, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6053249835968018, | |
| "eval_runtime": 0.1634, | |
| "eval_samples_per_second": 67.338, | |
| "eval_steps_per_second": 6.122, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6329036951065063, | |
| "eval_runtime": 0.1657, | |
| "eval_samples_per_second": 66.376, | |
| "eval_steps_per_second": 6.034, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 1.730581283569336, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0205, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6750754117965698, | |
| "eval_runtime": 0.1601, | |
| "eval_samples_per_second": 68.705, | |
| "eval_steps_per_second": 6.246, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6956837177276611, | |
| "eval_runtime": 0.1605, | |
| "eval_samples_per_second": 68.544, | |
| "eval_steps_per_second": 6.231, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7326122522354126, | |
| "eval_runtime": 0.1627, | |
| "eval_samples_per_second": 67.592, | |
| "eval_steps_per_second": 6.145, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7474762201309204, | |
| "eval_runtime": 0.1609, | |
| "eval_samples_per_second": 68.37, | |
| "eval_steps_per_second": 6.215, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7503242492675781, | |
| "eval_runtime": 0.1663, | |
| "eval_samples_per_second": 66.152, | |
| "eval_steps_per_second": 6.014, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7442704439163208, | |
| "eval_runtime": 0.1639, | |
| "eval_samples_per_second": 67.112, | |
| "eval_steps_per_second": 6.101, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7483036518096924, | |
| "eval_runtime": 0.1641, | |
| "eval_samples_per_second": 67.017, | |
| "eval_steps_per_second": 6.092, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7523319721221924, | |
| "eval_runtime": 0.1673, | |
| "eval_samples_per_second": 65.749, | |
| "eval_steps_per_second": 5.977, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7516257762908936, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.87, | |
| "eval_steps_per_second": 6.079, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7482516765594482, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.939, | |
| "eval_steps_per_second": 6.176, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 2.2856013774871826, | |
| "learning_rate": 0.0, | |
| "loss": 0.0334, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7462173700332642, | |
| "eval_runtime": 0.1596, | |
| "eval_samples_per_second": 68.913, | |
| "eval_steps_per_second": 6.265, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.570114227259392e+17, | |
| "train_loss": 0.09494904980063439, | |
| "train_runtime": 412.6058, | |
| "train_samples_per_second": 14.299, | |
| "train_steps_per_second": 0.242 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9257901906967163, | |
| "eval_runtime": 0.2042, | |
| "eval_samples_per_second": 53.876, | |
| "eval_steps_per_second": 4.898, | |
| "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 | |
| } | |