| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-85-fold2/checkpoint-3", | |
| "epoch": 100.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 1.3942718505859375, | |
| "eval_runtime": 0.1655, | |
| "eval_samples_per_second": 66.48, | |
| "eval_steps_per_second": 6.044, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.36363636363636365, | |
| "eval_loss": 1.1771122217178345, | |
| "eval_runtime": 0.159, | |
| "eval_samples_per_second": 69.184, | |
| "eval_steps_per_second": 6.289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0030003786087036, | |
| "eval_runtime": 0.1641, | |
| "eval_samples_per_second": 67.017, | |
| "eval_steps_per_second": 6.092, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1174808740615845, | |
| "eval_runtime": 0.1634, | |
| "eval_samples_per_second": 67.302, | |
| "eval_steps_per_second": 6.118, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3271055221557617, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.738, | |
| "eval_steps_per_second": 6.067, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3904811143875122, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.903, | |
| "eval_steps_per_second": 6.173, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2947728633880615, | |
| "eval_runtime": 0.1663, | |
| "eval_samples_per_second": 66.138, | |
| "eval_steps_per_second": 6.013, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0698984861373901, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.566, | |
| "eval_steps_per_second": 6.142, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9284465909004211, | |
| "eval_runtime": 0.1582, | |
| "eval_samples_per_second": 69.548, | |
| "eval_steps_per_second": 6.323, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 3.653879165649414, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3023, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9572641253471375, | |
| "eval_runtime": 0.1643, | |
| "eval_samples_per_second": 66.947, | |
| "eval_steps_per_second": 6.086, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1349629163742065, | |
| "eval_runtime": 0.1639, | |
| "eval_samples_per_second": 67.099, | |
| "eval_steps_per_second": 6.1, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2566031217575073, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.503, | |
| "eval_steps_per_second": 6.137, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.297853708267212, | |
| "eval_runtime": 0.1691, | |
| "eval_samples_per_second": 65.062, | |
| "eval_steps_per_second": 5.915, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1942445039749146, | |
| "eval_runtime": 0.1684, | |
| "eval_samples_per_second": 65.321, | |
| "eval_steps_per_second": 5.938, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1980408430099487, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.719, | |
| "eval_steps_per_second": 5.974, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2017428874969482, | |
| "eval_runtime": 0.1617, | |
| "eval_samples_per_second": 68.04, | |
| "eval_steps_per_second": 6.185, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4193841218948364, | |
| "eval_runtime": 0.1661, | |
| "eval_samples_per_second": 66.207, | |
| "eval_steps_per_second": 6.019, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5204254388809204, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.819, | |
| "eval_steps_per_second": 6.074, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3899296522140503, | |
| "eval_runtime": 0.1642, | |
| "eval_samples_per_second": 67.006, | |
| "eval_steps_per_second": 6.091, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.7979230880737305, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1701, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2406777143478394, | |
| "eval_runtime": 0.1639, | |
| "eval_samples_per_second": 67.132, | |
| "eval_steps_per_second": 6.103, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3355902433395386, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.347, | |
| "eval_steps_per_second": 6.122, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5076453685760498, | |
| "eval_runtime": 0.1675, | |
| "eval_samples_per_second": 65.69, | |
| "eval_steps_per_second": 5.972, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4259604215621948, | |
| "eval_runtime": 0.1618, | |
| "eval_samples_per_second": 68.006, | |
| "eval_steps_per_second": 6.182, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1877496242523193, | |
| "eval_runtime": 0.1601, | |
| "eval_samples_per_second": 68.727, | |
| "eval_steps_per_second": 6.248, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0432525873184204, | |
| "eval_runtime": 0.1632, | |
| "eval_samples_per_second": 67.382, | |
| "eval_steps_per_second": 6.126, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.026136040687561, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.812, | |
| "eval_steps_per_second": 6.074, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.086931586265564, | |
| "eval_runtime": 0.1617, | |
| "eval_samples_per_second": 68.039, | |
| "eval_steps_per_second": 6.185, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.107432246208191, | |
| "eval_runtime": 0.1617, | |
| "eval_samples_per_second": 68.048, | |
| "eval_steps_per_second": 6.186, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.085809588432312, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.531, | |
| "eval_steps_per_second": 6.139, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 4.284212589263916, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1058, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0020207166671753, | |
| "eval_runtime": 0.1607, | |
| "eval_samples_per_second": 68.447, | |
| "eval_steps_per_second": 6.222, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.988141655921936, | |
| "eval_runtime": 0.1642, | |
| "eval_samples_per_second": 67.01, | |
| "eval_steps_per_second": 6.092, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0529652833938599, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.091, | |
| "eval_steps_per_second": 6.008, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.373605489730835, | |
| "eval_runtime": 0.168, | |
| "eval_samples_per_second": 65.484, | |
| "eval_steps_per_second": 5.953, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.476812481880188, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.882, | |
| "eval_steps_per_second": 6.171, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4371956586837769, | |
| "eval_runtime": 0.1616, | |
| "eval_samples_per_second": 68.09, | |
| "eval_steps_per_second": 6.19, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4593983888626099, | |
| "eval_runtime": 0.1625, | |
| "eval_samples_per_second": 67.689, | |
| "eval_steps_per_second": 6.154, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4529162645339966, | |
| "eval_runtime": 0.1658, | |
| "eval_samples_per_second": 66.34, | |
| "eval_steps_per_second": 6.031, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6026790142059326, | |
| "eval_runtime": 0.1639, | |
| "eval_samples_per_second": 67.114, | |
| "eval_steps_per_second": 6.101, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7375715970993042, | |
| "eval_runtime": 0.1673, | |
| "eval_samples_per_second": 65.737, | |
| "eval_steps_per_second": 5.976, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 4.128200531005859, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.065, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8992785215377808, | |
| "eval_runtime": 0.156, | |
| "eval_samples_per_second": 70.516, | |
| "eval_steps_per_second": 6.411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.99269437789917, | |
| "eval_runtime": 0.1694, | |
| "eval_samples_per_second": 64.943, | |
| "eval_steps_per_second": 5.904, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.886697769165039, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.909, | |
| "eval_steps_per_second": 6.174, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.636297583580017, | |
| "eval_runtime": 0.1651, | |
| "eval_samples_per_second": 66.638, | |
| "eval_steps_per_second": 6.058, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5641781091690063, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.571, | |
| "eval_steps_per_second": 6.143, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5277984142303467, | |
| "eval_runtime": 0.1616, | |
| "eval_samples_per_second": 68.088, | |
| "eval_steps_per_second": 6.19, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5096694231033325, | |
| "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": 1.5585776567459106, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.519, | |
| "eval_steps_per_second": 6.138, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5659198760986328, | |
| "eval_runtime": 0.1607, | |
| "eval_samples_per_second": 68.456, | |
| "eval_steps_per_second": 6.223, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5743082761764526, | |
| "eval_runtime": 0.1896, | |
| "eval_samples_per_second": 58.003, | |
| "eval_steps_per_second": 5.273, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 2.4044439792633057, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.061, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5951069593429565, | |
| "eval_runtime": 0.1604, | |
| "eval_samples_per_second": 68.596, | |
| "eval_steps_per_second": 6.236, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6096874475479126, | |
| "eval_runtime": 0.1624, | |
| "eval_samples_per_second": 67.75, | |
| "eval_steps_per_second": 6.159, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6781367063522339, | |
| "eval_runtime": 0.1659, | |
| "eval_samples_per_second": 66.289, | |
| "eval_steps_per_second": 6.026, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.716800332069397, | |
| "eval_runtime": 0.1655, | |
| "eval_samples_per_second": 66.481, | |
| "eval_steps_per_second": 6.044, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6330821514129639, | |
| "eval_runtime": 0.1657, | |
| "eval_samples_per_second": 66.392, | |
| "eval_steps_per_second": 6.036, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.571137547492981, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.373, | |
| "eval_steps_per_second": 6.125, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6042648553848267, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.878, | |
| "eval_steps_per_second": 6.08, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6589672565460205, | |
| "eval_runtime": 0.1749, | |
| "eval_samples_per_second": 62.878, | |
| "eval_steps_per_second": 5.716, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.687893033027649, | |
| "eval_runtime": 0.1739, | |
| "eval_samples_per_second": 63.265, | |
| "eval_steps_per_second": 5.751, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.645227313041687, | |
| "eval_runtime": 0.1683, | |
| "eval_samples_per_second": 65.362, | |
| "eval_steps_per_second": 5.942, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 1.9491686820983887, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0642, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6099064350128174, | |
| "eval_runtime": 0.1625, | |
| "eval_samples_per_second": 67.708, | |
| "eval_steps_per_second": 6.155, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5535567998886108, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.736, | |
| "eval_steps_per_second": 6.067, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.549566388130188, | |
| "eval_runtime": 0.1674, | |
| "eval_samples_per_second": 65.71, | |
| "eval_steps_per_second": 5.974, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5527859926223755, | |
| "eval_runtime": 0.1702, | |
| "eval_samples_per_second": 64.625, | |
| "eval_steps_per_second": 5.875, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.635145902633667, | |
| "eval_runtime": 0.1635, | |
| "eval_samples_per_second": 67.287, | |
| "eval_steps_per_second": 6.117, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7556191682815552, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.894, | |
| "eval_steps_per_second": 6.172, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8993223905563354, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 68.161, | |
| "eval_steps_per_second": 6.196, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0309484004974365, | |
| "eval_runtime": 0.1688, | |
| "eval_samples_per_second": 65.155, | |
| "eval_steps_per_second": 5.923, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.154777765274048, | |
| "eval_runtime": 0.164, | |
| "eval_samples_per_second": 67.088, | |
| "eval_steps_per_second": 6.099, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.208738327026367, | |
| "eval_runtime": 0.1635, | |
| "eval_samples_per_second": 67.277, | |
| "eval_steps_per_second": 6.116, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 1.5443565845489502, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0411, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2061707973480225, | |
| "eval_runtime": 0.1602, | |
| "eval_samples_per_second": 68.656, | |
| "eval_steps_per_second": 6.241, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.160473108291626, | |
| "eval_runtime": 0.1703, | |
| "eval_samples_per_second": 64.578, | |
| "eval_steps_per_second": 5.871, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1346824169158936, | |
| "eval_runtime": 0.164, | |
| "eval_samples_per_second": 67.092, | |
| "eval_steps_per_second": 6.099, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0661559104919434, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.545, | |
| "eval_steps_per_second": 6.05, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0682950019836426, | |
| "eval_runtime": 0.1666, | |
| "eval_samples_per_second": 66.034, | |
| "eval_steps_per_second": 6.003, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.046642303466797, | |
| "eval_runtime": 0.1618, | |
| "eval_samples_per_second": 67.97, | |
| "eval_steps_per_second": 6.179, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.975563406944275, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.753, | |
| "eval_steps_per_second": 6.068, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8928240537643433, | |
| "eval_runtime": 0.172, | |
| "eval_samples_per_second": 63.964, | |
| "eval_steps_per_second": 5.815, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8972359895706177, | |
| "eval_runtime": 0.1594, | |
| "eval_samples_per_second": 69.026, | |
| "eval_steps_per_second": 6.275, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.940840482711792, | |
| "eval_runtime": 0.1642, | |
| "eval_samples_per_second": 66.996, | |
| "eval_steps_per_second": 6.091, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 2.940497875213623, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0421, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9689593315124512, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 68.126, | |
| "eval_steps_per_second": 6.193, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.046592950820923, | |
| "eval_runtime": 0.1672, | |
| "eval_samples_per_second": 65.791, | |
| "eval_steps_per_second": 5.981, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1173698902130127, | |
| "eval_runtime": 0.1665, | |
| "eval_samples_per_second": 66.064, | |
| "eval_steps_per_second": 6.006, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1824681758880615, | |
| "eval_runtime": 0.1632, | |
| "eval_samples_per_second": 67.401, | |
| "eval_steps_per_second": 6.127, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2527048587799072, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.873, | |
| "eval_steps_per_second": 6.079, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.293335199356079, | |
| "eval_runtime": 0.1695, | |
| "eval_samples_per_second": 64.88, | |
| "eval_steps_per_second": 5.898, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3311402797698975, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 68.105, | |
| "eval_steps_per_second": 6.191, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3468058109283447, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.168, | |
| "eval_steps_per_second": 6.015, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3222219944000244, | |
| "eval_runtime": 0.1629, | |
| "eval_samples_per_second": 67.521, | |
| "eval_steps_per_second": 6.138, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2764031887054443, | |
| "eval_runtime": 0.161, | |
| "eval_samples_per_second": 68.32, | |
| "eval_steps_per_second": 6.211, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 2.269606828689575, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0304, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2189602851867676, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.908, | |
| "eval_steps_per_second": 6.173, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.185450792312622, | |
| "eval_runtime": 0.1741, | |
| "eval_samples_per_second": 63.191, | |
| "eval_steps_per_second": 5.745, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1677095890045166, | |
| "eval_runtime": 0.168, | |
| "eval_samples_per_second": 65.459, | |
| "eval_steps_per_second": 5.951, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1493093967437744, | |
| "eval_runtime": 0.3872, | |
| "eval_samples_per_second": 28.41, | |
| "eval_steps_per_second": 2.583, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1259407997131348, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.225, | |
| "eval_steps_per_second": 6.111, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1151316165924072, | |
| "eval_runtime": 0.1731, | |
| "eval_samples_per_second": 63.555, | |
| "eval_steps_per_second": 5.778, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1178739070892334, | |
| "eval_runtime": 0.159, | |
| "eval_samples_per_second": 69.189, | |
| "eval_steps_per_second": 6.29, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1249771118164062, | |
| "eval_runtime": 0.169, | |
| "eval_samples_per_second": 65.097, | |
| "eval_steps_per_second": 5.918, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1301894187927246, | |
| "eval_runtime": 0.1668, | |
| "eval_samples_per_second": 65.937, | |
| "eval_steps_per_second": 5.994, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.133030414581299, | |
| "eval_runtime": 0.1677, | |
| "eval_samples_per_second": 65.611, | |
| "eval_steps_per_second": 5.965, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 0.5588133335113525, | |
| "learning_rate": 0.0, | |
| "loss": 0.0305, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1359941959381104, | |
| "eval_runtime": 0.165, | |
| "eval_samples_per_second": 66.682, | |
| "eval_steps_per_second": 6.062, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.570114227259392e+17, | |
| "train_loss": 0.09125248789787292, | |
| "train_runtime": 408.9195, | |
| "train_samples_per_second": 14.428, | |
| "train_steps_per_second": 0.245 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.0030003786087036, | |
| "eval_runtime": 0.2141, | |
| "eval_samples_per_second": 51.378, | |
| "eval_steps_per_second": 4.671, | |
| "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 | |
| } | |