| { | |
| "best_metric": 0.7272727272727273, | |
| "best_model_checkpoint": "beit-base-patch16-224-hasta-85-fold3/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": 0.18181818181818182, | |
| "eval_loss": 1.3301132917404175, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.894, | |
| "eval_steps_per_second": 6.081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.36363636363636365, | |
| "eval_loss": 1.1011773347854614, | |
| "eval_runtime": 0.1612, | |
| "eval_samples_per_second": 68.24, | |
| "eval_steps_per_second": 6.204, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.8911389708518982, | |
| "eval_runtime": 0.1596, | |
| "eval_samples_per_second": 68.906, | |
| "eval_steps_per_second": 6.264, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.9554937481880188, | |
| "eval_runtime": 0.1586, | |
| "eval_samples_per_second": 69.349, | |
| "eval_steps_per_second": 6.304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2581778764724731, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 68.168, | |
| "eval_steps_per_second": 6.197, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.557570219039917, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.86, | |
| "eval_steps_per_second": 6.078, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6687114238739014, | |
| "eval_runtime": 0.1573, | |
| "eval_samples_per_second": 69.909, | |
| "eval_steps_per_second": 6.355, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5014568567276, | |
| "eval_runtime": 0.1624, | |
| "eval_samples_per_second": 67.739, | |
| "eval_steps_per_second": 6.158, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.27287757396698, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.765, | |
| "eval_steps_per_second": 6.16, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 3.620285987854004, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2127418518066406, | |
| "eval_runtime": 0.1592, | |
| "eval_samples_per_second": 69.089, | |
| "eval_steps_per_second": 6.281, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3132389783859253, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.236, | |
| "eval_steps_per_second": 6.112, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3349677324295044, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.54, | |
| "eval_steps_per_second": 6.049, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2578802108764648, | |
| "eval_runtime": 0.1747, | |
| "eval_samples_per_second": 62.948, | |
| "eval_steps_per_second": 5.723, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3559178113937378, | |
| "eval_runtime": 0.1651, | |
| "eval_samples_per_second": 66.608, | |
| "eval_steps_per_second": 6.055, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.423079252243042, | |
| "eval_runtime": 0.168, | |
| "eval_samples_per_second": 65.49, | |
| "eval_steps_per_second": 5.954, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5141488313674927, | |
| "eval_runtime": 0.163, | |
| "eval_samples_per_second": 67.484, | |
| "eval_steps_per_second": 6.135, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.41997230052948, | |
| "eval_runtime": 0.1724, | |
| "eval_samples_per_second": 63.808, | |
| "eval_steps_per_second": 5.801, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2498489618301392, | |
| "eval_runtime": 0.1643, | |
| "eval_samples_per_second": 66.969, | |
| "eval_steps_per_second": 6.088, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1455856561660767, | |
| "eval_runtime": 0.1696, | |
| "eval_samples_per_second": 64.868, | |
| "eval_steps_per_second": 5.897, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.7856740951538086, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1054821014404297, | |
| "eval_runtime": 0.1613, | |
| "eval_samples_per_second": 68.212, | |
| "eval_steps_per_second": 6.201, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.193658471107483, | |
| "eval_runtime": 0.1643, | |
| "eval_samples_per_second": 66.956, | |
| "eval_steps_per_second": 6.087, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2767573595046997, | |
| "eval_runtime": 0.1622, | |
| "eval_samples_per_second": 67.828, | |
| "eval_steps_per_second": 6.166, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3223987817764282, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.365, | |
| "eval_steps_per_second": 6.124, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3628963232040405, | |
| "eval_runtime": 0.1675, | |
| "eval_samples_per_second": 65.691, | |
| "eval_steps_per_second": 5.972, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3238441944122314, | |
| "eval_runtime": 0.1572, | |
| "eval_samples_per_second": 69.971, | |
| "eval_steps_per_second": 6.361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2279627323150635, | |
| "eval_runtime": 0.166, | |
| "eval_samples_per_second": 66.269, | |
| "eval_steps_per_second": 6.024, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2445907592773438, | |
| "eval_runtime": 0.1614, | |
| "eval_samples_per_second": 68.153, | |
| "eval_steps_per_second": 6.196, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.253031849861145, | |
| "eval_runtime": 0.1722, | |
| "eval_samples_per_second": 63.893, | |
| "eval_steps_per_second": 5.808, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2467639446258545, | |
| "eval_runtime": 0.1684, | |
| "eval_samples_per_second": 65.331, | |
| "eval_steps_per_second": 5.939, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 3.461214542388916, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1447, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.153478980064392, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.918, | |
| "eval_steps_per_second": 6.174, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.1125404834747314, | |
| "eval_runtime": 0.1631, | |
| "eval_samples_per_second": 67.429, | |
| "eval_steps_per_second": 6.13, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.2051128149032593, | |
| "eval_runtime": 0.161, | |
| "eval_samples_per_second": 68.316, | |
| "eval_steps_per_second": 6.211, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5901983976364136, | |
| "eval_runtime": 0.1626, | |
| "eval_samples_per_second": 67.643, | |
| "eval_steps_per_second": 6.149, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8445490598678589, | |
| "eval_runtime": 0.1601, | |
| "eval_samples_per_second": 68.723, | |
| "eval_steps_per_second": 6.248, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.722154974937439, | |
| "eval_runtime": 0.1652, | |
| "eval_samples_per_second": 66.6, | |
| "eval_steps_per_second": 6.055, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.5080395936965942, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.756, | |
| "eval_steps_per_second": 6.16, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3541849851608276, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.79, | |
| "eval_steps_per_second": 6.163, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.3106049299240112, | |
| "eval_runtime": 0.1682, | |
| "eval_samples_per_second": 65.411, | |
| "eval_steps_per_second": 5.946, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4533156156539917, | |
| "eval_runtime": 0.1659, | |
| "eval_samples_per_second": 66.304, | |
| "eval_steps_per_second": 6.028, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 1.8162009716033936, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1053, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.642745852470398, | |
| "eval_runtime": 0.1604, | |
| "eval_samples_per_second": 68.576, | |
| "eval_steps_per_second": 6.234, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7518008947372437, | |
| "eval_runtime": 0.1627, | |
| "eval_samples_per_second": 67.61, | |
| "eval_steps_per_second": 6.146, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7775400876998901, | |
| "eval_runtime": 0.1634, | |
| "eval_samples_per_second": 67.301, | |
| "eval_steps_per_second": 6.118, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6830981969833374, | |
| "eval_runtime": 0.1596, | |
| "eval_samples_per_second": 68.902, | |
| "eval_steps_per_second": 6.264, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6967986822128296, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.883, | |
| "eval_steps_per_second": 6.171, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8235682249069214, | |
| "eval_runtime": 0.1682, | |
| "eval_samples_per_second": 65.408, | |
| "eval_steps_per_second": 5.946, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8845221996307373, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.573, | |
| "eval_steps_per_second": 6.143, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8785400390625, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.911, | |
| "eval_steps_per_second": 6.174, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8805489540100098, | |
| "eval_runtime": 0.1627, | |
| "eval_samples_per_second": 67.617, | |
| "eval_steps_per_second": 6.147, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.962545394897461, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.898, | |
| "eval_steps_per_second": 6.173, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 3.943336248397827, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0771, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9860399961471558, | |
| "eval_runtime": 0.1625, | |
| "eval_samples_per_second": 67.674, | |
| "eval_steps_per_second": 6.152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9708118438720703, | |
| "eval_runtime": 0.1616, | |
| "eval_samples_per_second": 68.056, | |
| "eval_steps_per_second": 6.187, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9148517847061157, | |
| "eval_runtime": 0.1636, | |
| "eval_samples_per_second": 67.221, | |
| "eval_steps_per_second": 6.111, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9064445495605469, | |
| "eval_runtime": 0.1621, | |
| "eval_samples_per_second": 67.844, | |
| "eval_steps_per_second": 6.168, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.880388617515564, | |
| "eval_runtime": 0.1649, | |
| "eval_samples_per_second": 66.704, | |
| "eval_steps_per_second": 6.064, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8466503620147705, | |
| "eval_runtime": 0.1652, | |
| "eval_samples_per_second": 66.593, | |
| "eval_steps_per_second": 6.054, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8508163690567017, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.827, | |
| "eval_steps_per_second": 6.075, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8674921989440918, | |
| "eval_runtime": 0.1633, | |
| "eval_samples_per_second": 67.361, | |
| "eval_steps_per_second": 6.124, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8886075019836426, | |
| "eval_runtime": 0.1605, | |
| "eval_samples_per_second": 68.539, | |
| "eval_steps_per_second": 6.231, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.885992407798767, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.535, | |
| "eval_steps_per_second": 6.049, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "grad_norm": 2.378823757171631, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0528, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.8777347803115845, | |
| "eval_runtime": 0.1581, | |
| "eval_samples_per_second": 69.569, | |
| "eval_steps_per_second": 6.324, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.911914348602295, | |
| "eval_runtime": 0.1655, | |
| "eval_samples_per_second": 66.476, | |
| "eval_steps_per_second": 6.043, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.986009955406189, | |
| "eval_runtime": 0.1645, | |
| "eval_samples_per_second": 66.856, | |
| "eval_steps_per_second": 6.078, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.100313425064087, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.764, | |
| "eval_steps_per_second": 6.16, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1560723781585693, | |
| "eval_runtime": 0.164, | |
| "eval_samples_per_second": 67.088, | |
| "eval_steps_per_second": 6.099, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1454484462738037, | |
| "eval_runtime": 0.1662, | |
| "eval_samples_per_second": 66.203, | |
| "eval_steps_per_second": 6.018, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.0684831142425537, | |
| "eval_runtime": 0.1611, | |
| "eval_samples_per_second": 68.271, | |
| "eval_steps_per_second": 6.206, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.9260677099227905, | |
| "eval_runtime": 0.162, | |
| "eval_samples_per_second": 67.885, | |
| "eval_steps_per_second": 6.171, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6838963031768799, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.93, | |
| "eval_steps_per_second": 6.085, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.4305803775787354, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.769, | |
| "eval_steps_per_second": 6.161, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "grad_norm": 2.906874179840088, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.043, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.379963994026184, | |
| "eval_runtime": 0.1612, | |
| "eval_samples_per_second": 68.232, | |
| "eval_steps_per_second": 6.203, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.481353759765625, | |
| "eval_runtime": 0.1627, | |
| "eval_samples_per_second": 67.596, | |
| "eval_steps_per_second": 6.145, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.6013743877410889, | |
| "eval_runtime": 0.1646, | |
| "eval_samples_per_second": 66.837, | |
| "eval_steps_per_second": 6.076, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.7792106866836548, | |
| "eval_runtime": 0.1715, | |
| "eval_samples_per_second": 64.154, | |
| "eval_steps_per_second": 5.832, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 1.942270278930664, | |
| "eval_runtime": 0.1798, | |
| "eval_samples_per_second": 61.175, | |
| "eval_steps_per_second": 5.561, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.058955430984497, | |
| "eval_runtime": 0.1686, | |
| "eval_samples_per_second": 65.256, | |
| "eval_steps_per_second": 5.932, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1119210720062256, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 64.776, | |
| "eval_steps_per_second": 5.889, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1115880012512207, | |
| "eval_runtime": 0.159, | |
| "eval_samples_per_second": 69.169, | |
| "eval_steps_per_second": 6.288, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.09788179397583, | |
| "eval_runtime": 0.1658, | |
| "eval_samples_per_second": 66.358, | |
| "eval_steps_per_second": 6.033, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.1457321643829346, | |
| "eval_runtime": 0.1628, | |
| "eval_samples_per_second": 67.574, | |
| "eval_steps_per_second": 6.143, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "grad_norm": 0.6453837156295776, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0429, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.222235918045044, | |
| "eval_runtime": 0.1592, | |
| "eval_samples_per_second": 69.083, | |
| "eval_steps_per_second": 6.28, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.2802772521972656, | |
| "eval_runtime": 0.2145, | |
| "eval_samples_per_second": 51.279, | |
| "eval_steps_per_second": 4.662, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3327412605285645, | |
| "eval_runtime": 0.1729, | |
| "eval_samples_per_second": 63.606, | |
| "eval_steps_per_second": 5.782, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.364278554916382, | |
| "eval_runtime": 0.1621, | |
| "eval_samples_per_second": 67.852, | |
| "eval_steps_per_second": 6.168, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.37738037109375, | |
| "eval_runtime": 0.1644, | |
| "eval_samples_per_second": 66.893, | |
| "eval_steps_per_second": 6.081, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3838162422180176, | |
| "eval_runtime": 0.1652, | |
| "eval_samples_per_second": 66.585, | |
| "eval_steps_per_second": 6.053, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.40724778175354, | |
| "eval_runtime": 0.1632, | |
| "eval_samples_per_second": 67.387, | |
| "eval_steps_per_second": 6.126, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.418928384780884, | |
| "eval_runtime": 0.1615, | |
| "eval_samples_per_second": 68.108, | |
| "eval_steps_per_second": 6.192, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4027860164642334, | |
| "eval_runtime": 0.1627, | |
| "eval_samples_per_second": 67.601, | |
| "eval_steps_per_second": 6.146, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.384704351425171, | |
| "eval_runtime": 0.1619, | |
| "eval_samples_per_second": 67.95, | |
| "eval_steps_per_second": 6.177, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "grad_norm": 0.6196302771568298, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0475, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.37929368019104, | |
| "eval_runtime": 0.1648, | |
| "eval_samples_per_second": 66.751, | |
| "eval_steps_per_second": 6.068, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.383119821548462, | |
| "eval_runtime": 0.1666, | |
| "eval_samples_per_second": 66.015, | |
| "eval_steps_per_second": 6.001, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.388152837753296, | |
| "eval_runtime": 0.1664, | |
| "eval_samples_per_second": 66.106, | |
| "eval_steps_per_second": 6.01, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.3963706493377686, | |
| "eval_runtime": 0.1623, | |
| "eval_samples_per_second": 67.777, | |
| "eval_steps_per_second": 6.162, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.412632465362549, | |
| "eval_runtime": 0.1653, | |
| "eval_samples_per_second": 66.532, | |
| "eval_steps_per_second": 6.048, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4309277534484863, | |
| "eval_runtime": 0.1616, | |
| "eval_samples_per_second": 68.068, | |
| "eval_steps_per_second": 6.188, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.4486470222473145, | |
| "eval_runtime": 0.1667, | |
| "eval_samples_per_second": 65.993, | |
| "eval_steps_per_second": 5.999, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.462806463241577, | |
| "eval_runtime": 0.1661, | |
| "eval_samples_per_second": 66.236, | |
| "eval_steps_per_second": 6.021, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.472334146499634, | |
| "eval_runtime": 0.1592, | |
| "eval_samples_per_second": 69.097, | |
| "eval_steps_per_second": 6.282, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.477539300918579, | |
| "eval_runtime": 0.164, | |
| "eval_samples_per_second": 67.09, | |
| "eval_steps_per_second": 6.099, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 4.00584602355957, | |
| "learning_rate": 0.0, | |
| "loss": 0.0337, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 2.478825330734253, | |
| "eval_runtime": 0.1604, | |
| "eval_samples_per_second": 68.581, | |
| "eval_steps_per_second": 6.235, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 4.570114227259392e+17, | |
| "train_loss": 0.10973343044519425, | |
| "train_runtime": 402.8029, | |
| "train_samples_per_second": 14.647, | |
| "train_steps_per_second": 0.248 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.7272727272727273, | |
| "eval_loss": 0.8911389708518982, | |
| "eval_runtime": 0.2137, | |
| "eval_samples_per_second": 51.475, | |
| "eval_steps_per_second": 4.68, | |
| "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 | |
| } | |