| { | |
| "best_metric": 0.9305555555555556, | |
| "best_model_checkpoint": "vit-base-patch16-224-Soybean_11-46/checkpoint-473", | |
| "epoch": 50.0, | |
| "global_step": 550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.09090909090909e-07, | |
| "loss": 1.677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.818181818181818e-06, | |
| "loss": 1.663, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.7272727272727272e-06, | |
| "loss": 1.6847, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 1.7074, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.6866, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 1.571, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 6.363636363636363e-06, | |
| "loss": 1.5806, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 1.5372, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 1.51, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.4441, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3661, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5069444444444444, | |
| "eval_loss": 1.3697991371154785, | |
| "eval_runtime": 1.9108, | |
| "eval_samples_per_second": 150.721, | |
| "eval_steps_per_second": 2.617, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 1.386, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1.1818181818181819e-05, | |
| "loss": 1.4072, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.2727272727272727e-05, | |
| "loss": 1.3612, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 1.2649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 1.2608, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 1.5454545454545454e-05, | |
| "loss": 1.2141, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.6363636363636366e-05, | |
| "loss": 1.1708, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.7272727272727274e-05, | |
| "loss": 1.1569, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 1.0257, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.9090909090909094e-05, | |
| "loss": 1.0738, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9979, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6631944444444444, | |
| "eval_loss": 0.9816781282424927, | |
| "eval_runtime": 1.5585, | |
| "eval_samples_per_second": 184.794, | |
| "eval_steps_per_second": 3.208, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.090909090909091e-05, | |
| "loss": 0.9297, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 1.0059, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.9702, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.3636363636363637e-05, | |
| "loss": 0.9763, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.4545454545454545e-05, | |
| "loss": 0.9261, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 0.8262, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.636363636363636e-05, | |
| "loss": 0.9163, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 0.8509, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2.818181818181818e-05, | |
| "loss": 0.9219, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 0.7396, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6746, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7395833333333334, | |
| "eval_loss": 0.7423216700553894, | |
| "eval_runtime": 1.6283, | |
| "eval_samples_per_second": 176.87, | |
| "eval_steps_per_second": 3.071, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 3.090909090909091e-05, | |
| "loss": 0.8067, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.7232, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.7808, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 3.3636363636363636e-05, | |
| "loss": 0.6977, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 3.454545454545455e-05, | |
| "loss": 0.777, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 3.545454545454546e-05, | |
| "loss": 0.6499, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.773, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 3.7272727272727276e-05, | |
| "loss": 0.6632, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 3.818181818181819e-05, | |
| "loss": 0.6182, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 3.909090909090909e-05, | |
| "loss": 0.6828, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6364, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7569444444444444, | |
| "eval_loss": 0.6075392365455627, | |
| "eval_runtime": 1.563, | |
| "eval_samples_per_second": 184.265, | |
| "eval_steps_per_second": 3.199, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.5537, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 4.181818181818182e-05, | |
| "loss": 0.5685, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 4.2727272727272724e-05, | |
| "loss": 0.6091, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.617, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 4.454545454545455e-05, | |
| "loss": 0.6308, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.6292, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.636363636363636e-05, | |
| "loss": 0.5864, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.6432, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 4.8181818181818186e-05, | |
| "loss": 0.5012, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 4.909090909090909e-05, | |
| "loss": 0.5659, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5425, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7951388888888888, | |
| "eval_loss": 0.5500215291976929, | |
| "eval_runtime": 1.5702, | |
| "eval_samples_per_second": 183.416, | |
| "eval_steps_per_second": 3.184, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 4.98989898989899e-05, | |
| "loss": 0.5388, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 4.97979797979798e-05, | |
| "loss": 0.474, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 4.9696969696969694e-05, | |
| "loss": 0.5091, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 4.9595959595959594e-05, | |
| "loss": 0.4634, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 4.94949494949495e-05, | |
| "loss": 0.5044, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 4.93939393939394e-05, | |
| "loss": 0.4715, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 4.92929292929293e-05, | |
| "loss": 0.4705, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 4.919191919191919e-05, | |
| "loss": 0.4706, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 4.909090909090909e-05, | |
| "loss": 0.4945, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 4.898989898989899e-05, | |
| "loss": 0.5611, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.5001, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8159722222222222, | |
| "eval_loss": 0.4882892072200775, | |
| "eval_runtime": 1.6356, | |
| "eval_samples_per_second": 176.082, | |
| "eval_steps_per_second": 3.057, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 4.878787878787879e-05, | |
| "loss": 0.3538, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 4.868686868686869e-05, | |
| "loss": 0.4787, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 4.858585858585859e-05, | |
| "loss": 0.4181, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 4.848484848484849e-05, | |
| "loss": 0.451, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 4.838383838383839e-05, | |
| "loss": 0.4455, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 4.828282828282829e-05, | |
| "loss": 0.4275, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 4.8181818181818186e-05, | |
| "loss": 0.4366, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 4.808080808080808e-05, | |
| "loss": 0.4176, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.4344, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 4.787878787878788e-05, | |
| "loss": 0.4482, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.3519, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8263888888888888, | |
| "eval_loss": 0.4539467394351959, | |
| "eval_runtime": 1.5682, | |
| "eval_samples_per_second": 183.653, | |
| "eval_steps_per_second": 3.188, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 4.7676767676767684e-05, | |
| "loss": 0.42, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 4.7575757575757576e-05, | |
| "loss": 0.4017, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 4.7474747474747476e-05, | |
| "loss": 0.3604, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.7373737373737375e-05, | |
| "loss": 0.4075, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.399, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 4.7171717171717174e-05, | |
| "loss": 0.335, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 4.7070707070707074e-05, | |
| "loss": 0.297, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 4.696969696969697e-05, | |
| "loss": 0.3727, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 4.686868686868687e-05, | |
| "loss": 0.3886, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 4.676767676767677e-05, | |
| "loss": 0.4117, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.4421, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8194444444444444, | |
| "eval_loss": 0.4483272135257721, | |
| "eval_runtime": 1.5685, | |
| "eval_samples_per_second": 183.62, | |
| "eval_steps_per_second": 3.188, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 4.656565656565657e-05, | |
| "loss": 0.334, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 4.6464646464646464e-05, | |
| "loss": 0.3811, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 4.636363636363636e-05, | |
| "loss": 0.3582, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 4.626262626262626e-05, | |
| "loss": 0.381, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 4.616161616161616e-05, | |
| "loss": 0.3449, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 4.606060606060607e-05, | |
| "loss": 0.3465, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.595959595959596e-05, | |
| "loss": 0.3676, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 4.585858585858586e-05, | |
| "loss": 0.3616, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 4.575757575757576e-05, | |
| "loss": 0.3392, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 4.565656565656566e-05, | |
| "loss": 0.3374, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.3207, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.84375, | |
| "eval_loss": 0.3785366117954254, | |
| "eval_runtime": 1.5932, | |
| "eval_samples_per_second": 180.771, | |
| "eval_steps_per_second": 3.138, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.3319, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 4.535353535353535e-05, | |
| "loss": 0.3582, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 4.525252525252526e-05, | |
| "loss": 0.2702, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 4.515151515151516e-05, | |
| "loss": 0.3054, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 4.5050505050505056e-05, | |
| "loss": 0.3041, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 4.494949494949495e-05, | |
| "loss": 0.2398, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 4.484848484848485e-05, | |
| "loss": 0.338, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 4.474747474747475e-05, | |
| "loss": 0.2486, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 4.464646464646465e-05, | |
| "loss": 0.279, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 4.454545454545455e-05, | |
| "loss": 0.3784, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.3682, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8645833333333334, | |
| "eval_loss": 0.3384600281715393, | |
| "eval_runtime": 1.5672, | |
| "eval_samples_per_second": 183.763, | |
| "eval_steps_per_second": 3.19, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 4.4343434343434346e-05, | |
| "loss": 0.3374, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 4.4242424242424246e-05, | |
| "loss": 0.3114, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 4.4141414141414145e-05, | |
| "loss": 0.3062, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 4.4040404040404044e-05, | |
| "loss": 0.3199, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 4.3939393939393944e-05, | |
| "loss": 0.2839, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 4.383838383838384e-05, | |
| "loss": 0.2866, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 4.3737373737373736e-05, | |
| "loss": 0.2628, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.3463, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 4.3535353535353535e-05, | |
| "loss": 0.263, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "learning_rate": 4.343434343434344e-05, | |
| "loss": 0.3273, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.2642, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8402777777777778, | |
| "eval_loss": 0.38269615173339844, | |
| "eval_runtime": 1.622, | |
| "eval_samples_per_second": 177.56, | |
| "eval_steps_per_second": 3.083, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 4.3232323232323234e-05, | |
| "loss": 0.2527, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 4.313131313131313e-05, | |
| "loss": 0.2828, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 4.303030303030303e-05, | |
| "loss": 0.2746, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.2746, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 11.45, | |
| "learning_rate": 4.282828282828283e-05, | |
| "loss": 0.2531, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 11.55, | |
| "learning_rate": 4.2727272727272724e-05, | |
| "loss": 0.3099, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 4.262626262626263e-05, | |
| "loss": 0.2967, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 4.252525252525253e-05, | |
| "loss": 0.2549, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 4.242424242424243e-05, | |
| "loss": 0.278, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 11.91, | |
| "learning_rate": 4.232323232323233e-05, | |
| "loss": 0.2509, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.3444, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8506944444444444, | |
| "eval_loss": 0.346247136592865, | |
| "eval_runtime": 1.5635, | |
| "eval_samples_per_second": 184.201, | |
| "eval_steps_per_second": 3.198, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 4.212121212121212e-05, | |
| "loss": 0.2451, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 4.202020202020202e-05, | |
| "loss": 0.2623, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 4.191919191919192e-05, | |
| "loss": 0.226, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 4.181818181818182e-05, | |
| "loss": 0.2158, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 12.45, | |
| "learning_rate": 4.171717171717172e-05, | |
| "loss": 0.2471, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 12.55, | |
| "learning_rate": 4.161616161616162e-05, | |
| "loss": 0.249, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 4.151515151515152e-05, | |
| "loss": 0.2439, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 4.141414141414142e-05, | |
| "loss": 0.284, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 4.131313131313132e-05, | |
| "loss": 0.2701, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 4.1212121212121216e-05, | |
| "loss": 0.3189, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.2423, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8680555555555556, | |
| "eval_loss": 0.317039430141449, | |
| "eval_runtime": 1.5869, | |
| "eval_samples_per_second": 181.49, | |
| "eval_steps_per_second": 3.151, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 13.09, | |
| "learning_rate": 4.101010101010101e-05, | |
| "loss": 0.2665, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 13.18, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.2167, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 4.0808080808080814e-05, | |
| "loss": 0.2306, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 4.070707070707071e-05, | |
| "loss": 0.2633, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 4.0606060606060606e-05, | |
| "loss": 0.2385, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 13.55, | |
| "learning_rate": 4.0505050505050506e-05, | |
| "loss": 0.3078, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.2579, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 4.0303030303030305e-05, | |
| "loss": 0.2388, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 4.0202020202020204e-05, | |
| "loss": 0.2028, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 4.01010101010101e-05, | |
| "loss": 0.2058, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3168, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8715277777777778, | |
| "eval_loss": 0.3167605996131897, | |
| "eval_runtime": 1.5799, | |
| "eval_samples_per_second": 182.284, | |
| "eval_steps_per_second": 3.165, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 3.98989898989899e-05, | |
| "loss": 0.1858, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 3.97979797979798e-05, | |
| "loss": 0.251, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 14.27, | |
| "learning_rate": 3.96969696969697e-05, | |
| "loss": 0.1862, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 3.9595959595959594e-05, | |
| "loss": 0.2788, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 14.45, | |
| "learning_rate": 3.9494949494949494e-05, | |
| "loss": 0.1804, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 3.939393939393939e-05, | |
| "loss": 0.2121, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 3.929292929292929e-05, | |
| "loss": 0.2029, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 3.91919191919192e-05, | |
| "loss": 0.2308, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 3.909090909090909e-05, | |
| "loss": 0.2396, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 3.898989898989899e-05, | |
| "loss": 0.2234, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.2781, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8333333333333334, | |
| "eval_loss": 0.33227282762527466, | |
| "eval_runtime": 1.5652, | |
| "eval_samples_per_second": 184.003, | |
| "eval_steps_per_second": 3.194, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 3.878787878787879e-05, | |
| "loss": 0.2058, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 3.868686868686869e-05, | |
| "loss": 0.2155, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 3.858585858585859e-05, | |
| "loss": 0.2097, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 3.848484848484848e-05, | |
| "loss": 0.2237, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 3.838383838383838e-05, | |
| "loss": 0.2715, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 3.828282828282829e-05, | |
| "loss": 0.2293, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 15.64, | |
| "learning_rate": 3.818181818181819e-05, | |
| "loss": 0.2285, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 3.8080808080808087e-05, | |
| "loss": 0.2612, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 3.797979797979798e-05, | |
| "loss": 0.196, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.2298, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.2411, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8715277777777778, | |
| "eval_loss": 0.31996577978134155, | |
| "eval_runtime": 1.5652, | |
| "eval_samples_per_second": 184.008, | |
| "eval_steps_per_second": 3.195, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "learning_rate": 3.767676767676768e-05, | |
| "loss": 0.1726, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 3.757575757575758e-05, | |
| "loss": 0.2112, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 16.27, | |
| "learning_rate": 3.747474747474748e-05, | |
| "loss": 0.1964, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 16.36, | |
| "learning_rate": 3.7373737373737376e-05, | |
| "loss": 0.1967, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 16.45, | |
| "learning_rate": 3.7272727272727276e-05, | |
| "loss": 0.2126, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 3.7171717171717175e-05, | |
| "loss": 0.1554, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 3.7070707070707075e-05, | |
| "loss": 0.1857, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 3.6969696969696974e-05, | |
| "loss": 0.211, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 16.82, | |
| "learning_rate": 3.686868686868687e-05, | |
| "loss": 0.2358, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 3.6767676767676766e-05, | |
| "loss": 0.1626, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.2276, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.32961538434028625, | |
| "eval_runtime": 1.6093, | |
| "eval_samples_per_second": 178.958, | |
| "eval_steps_per_second": 3.107, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 3.656565656565657e-05, | |
| "loss": 0.1915, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 17.18, | |
| "learning_rate": 3.6464646464646465e-05, | |
| "loss": 0.1826, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 17.27, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.2162, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 17.36, | |
| "learning_rate": 3.6262626262626264e-05, | |
| "loss": 0.1755, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 17.45, | |
| "learning_rate": 3.616161616161616e-05, | |
| "loss": 0.24, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 17.55, | |
| "learning_rate": 3.606060606060606e-05, | |
| "loss": 0.1746, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 3.595959595959596e-05, | |
| "loss": 0.1443, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 17.73, | |
| "learning_rate": 3.5858585858585855e-05, | |
| "loss": 0.189, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 17.82, | |
| "learning_rate": 3.575757575757576e-05, | |
| "loss": 0.1735, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 3.565656565656566e-05, | |
| "loss": 0.1383, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.192, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8854166666666666, | |
| "eval_loss": 0.3118571639060974, | |
| "eval_runtime": 1.5666, | |
| "eval_samples_per_second": 183.832, | |
| "eval_steps_per_second": 3.192, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 18.09, | |
| "learning_rate": 3.545454545454546e-05, | |
| "loss": 0.2313, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.2429, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 3.525252525252525e-05, | |
| "loss": 0.1745, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 3.515151515151515e-05, | |
| "loss": 0.189, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 18.45, | |
| "learning_rate": 3.505050505050505e-05, | |
| "loss": 0.1607, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 3.494949494949495e-05, | |
| "loss": 0.2268, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 3.484848484848485e-05, | |
| "loss": 0.1263, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 3.474747474747475e-05, | |
| "loss": 0.2372, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 3.464646464646465e-05, | |
| "loss": 0.1604, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 3.454545454545455e-05, | |
| "loss": 0.2622, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.1612, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.875, | |
| "eval_loss": 0.36473166942596436, | |
| "eval_runtime": 1.5912, | |
| "eval_samples_per_second": 180.99, | |
| "eval_steps_per_second": 3.142, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 19.09, | |
| "learning_rate": 3.434343434343435e-05, | |
| "loss": 0.2007, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "learning_rate": 3.424242424242424e-05, | |
| "loss": 0.1945, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 3.414141414141414e-05, | |
| "loss": 0.1654, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 3.4040404040404045e-05, | |
| "loss": 0.141, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 3.3939393939393945e-05, | |
| "loss": 0.2012, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 3.3838383838383844e-05, | |
| "loss": 0.1692, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 3.373737373737374e-05, | |
| "loss": 0.163, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 3.3636363636363636e-05, | |
| "loss": 0.2155, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 3.3535353535353536e-05, | |
| "loss": 0.1732, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 3.3434343434343435e-05, | |
| "loss": 0.1395, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1084, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8993055555555556, | |
| "eval_loss": 0.2640966773033142, | |
| "eval_runtime": 1.5715, | |
| "eval_samples_per_second": 183.268, | |
| "eval_steps_per_second": 3.182, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 3.3232323232323234e-05, | |
| "loss": 0.138, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 20.18, | |
| "learning_rate": 3.3131313131313134e-05, | |
| "loss": 0.1625, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 20.27, | |
| "learning_rate": 3.303030303030303e-05, | |
| "loss": 0.1838, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 3.292929292929293e-05, | |
| "loss": 0.1558, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.2134, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.1694, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 3.2626262626262624e-05, | |
| "loss": 0.2243, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 3.2525252525252524e-05, | |
| "loss": 0.219, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "learning_rate": 3.2424242424242423e-05, | |
| "loss": 0.1761, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 20.91, | |
| "learning_rate": 3.232323232323233e-05, | |
| "loss": 0.1231, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.2099, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8958333333333334, | |
| "eval_loss": 0.2806669771671295, | |
| "eval_runtime": 1.5627, | |
| "eval_samples_per_second": 184.299, | |
| "eval_steps_per_second": 3.2, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 21.09, | |
| "learning_rate": 3.212121212121212e-05, | |
| "loss": 0.1831, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 21.18, | |
| "learning_rate": 3.202020202020202e-05, | |
| "loss": 0.123, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 3.191919191919192e-05, | |
| "loss": 0.168, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 21.36, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.1516, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 21.45, | |
| "learning_rate": 3.171717171717172e-05, | |
| "loss": 0.1424, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 21.55, | |
| "learning_rate": 3.161616161616161e-05, | |
| "loss": 0.1368, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 3.151515151515151e-05, | |
| "loss": 0.234, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 21.73, | |
| "learning_rate": 3.141414141414142e-05, | |
| "loss": 0.1563, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 21.82, | |
| "learning_rate": 3.131313131313132e-05, | |
| "loss": 0.1288, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "learning_rate": 3.121212121212122e-05, | |
| "loss": 0.1547, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.1666, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9097222222222222, | |
| "eval_loss": 0.25945279002189636, | |
| "eval_runtime": 1.5674, | |
| "eval_samples_per_second": 183.74, | |
| "eval_steps_per_second": 3.19, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 22.09, | |
| "learning_rate": 3.101010101010101e-05, | |
| "loss": 0.1237, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 22.18, | |
| "learning_rate": 3.090909090909091e-05, | |
| "loss": 0.1206, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "learning_rate": 3.080808080808081e-05, | |
| "loss": 0.1572, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 3.070707070707071e-05, | |
| "loss": 0.2006, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 22.45, | |
| "learning_rate": 3.060606060606061e-05, | |
| "loss": 0.191, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 3.050505050505051e-05, | |
| "loss": 0.1191, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 22.64, | |
| "learning_rate": 3.0404040404040406e-05, | |
| "loss": 0.1462, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.1679, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 22.82, | |
| "learning_rate": 3.0202020202020205e-05, | |
| "loss": 0.2127, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 3.01010101010101e-05, | |
| "loss": 0.1359, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1355, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8923611111111112, | |
| "eval_loss": 0.2734811007976532, | |
| "eval_runtime": 1.5633, | |
| "eval_samples_per_second": 184.23, | |
| "eval_steps_per_second": 3.198, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 23.09, | |
| "learning_rate": 2.98989898989899e-05, | |
| "loss": 0.1139, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 23.18, | |
| "learning_rate": 2.9797979797979796e-05, | |
| "loss": 0.1299, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 23.27, | |
| "learning_rate": 2.96969696969697e-05, | |
| "loss": 0.1732, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.95959595959596e-05, | |
| "loss": 0.1417, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 23.45, | |
| "learning_rate": 2.9494949494949498e-05, | |
| "loss": 0.1588, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 23.55, | |
| "learning_rate": 2.9393939393939394e-05, | |
| "loss": 0.1159, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 23.64, | |
| "learning_rate": 2.9292929292929294e-05, | |
| "loss": 0.1636, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 23.73, | |
| "learning_rate": 2.9191919191919193e-05, | |
| "loss": 0.1375, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 0.128, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 23.91, | |
| "learning_rate": 2.898989898989899e-05, | |
| "loss": 0.1347, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.1165, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8784722222222222, | |
| "eval_loss": 0.3238440155982971, | |
| "eval_runtime": 1.6248, | |
| "eval_samples_per_second": 177.253, | |
| "eval_steps_per_second": 3.077, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 24.09, | |
| "learning_rate": 2.878787878787879e-05, | |
| "loss": 0.108, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "learning_rate": 2.868686868686869e-05, | |
| "loss": 0.1276, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 24.27, | |
| "learning_rate": 2.8585858585858587e-05, | |
| "loss": 0.1893, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 24.36, | |
| "learning_rate": 2.8484848484848486e-05, | |
| "loss": 0.1291, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 24.45, | |
| "learning_rate": 2.8383838383838386e-05, | |
| "loss": 0.1547, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "learning_rate": 2.8282828282828282e-05, | |
| "loss": 0.1697, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 2.818181818181818e-05, | |
| "loss": 0.1465, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 2.808080808080808e-05, | |
| "loss": 0.1422, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 24.82, | |
| "learning_rate": 2.7979797979797984e-05, | |
| "loss": 0.165, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 2.7878787878787883e-05, | |
| "loss": 0.1262, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.112, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8888888888888888, | |
| "eval_loss": 0.3065586984157562, | |
| "eval_runtime": 1.5997, | |
| "eval_samples_per_second": 180.037, | |
| "eval_steps_per_second": 3.126, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 2.767676767676768e-05, | |
| "loss": 0.1132, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 2.7575757575757578e-05, | |
| "loss": 0.1252, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "learning_rate": 2.7474747474747474e-05, | |
| "loss": 0.1023, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 25.36, | |
| "learning_rate": 2.7373737373737374e-05, | |
| "loss": 0.1254, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 2.7272727272727273e-05, | |
| "loss": 0.1575, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 25.55, | |
| "learning_rate": 2.717171717171717e-05, | |
| "loss": 0.1072, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 2.7070707070707075e-05, | |
| "loss": 0.135, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "learning_rate": 2.696969696969697e-05, | |
| "loss": 0.1851, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 2.686868686868687e-05, | |
| "loss": 0.1454, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 25.91, | |
| "learning_rate": 2.676767676767677e-05, | |
| "loss": 0.1629, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.1191, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.90625, | |
| "eval_loss": 0.24274842441082, | |
| "eval_runtime": 1.5782, | |
| "eval_samples_per_second": 182.491, | |
| "eval_steps_per_second": 3.168, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 2.6565656565656566e-05, | |
| "loss": 0.1726, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 26.18, | |
| "learning_rate": 2.6464646464646466e-05, | |
| "loss": 0.1017, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 26.27, | |
| "learning_rate": 2.636363636363636e-05, | |
| "loss": 0.0857, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 26.36, | |
| "learning_rate": 2.6262626262626268e-05, | |
| "loss": 0.1463, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 26.45, | |
| "learning_rate": 2.6161616161616164e-05, | |
| "loss": 0.1513, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 2.6060606060606063e-05, | |
| "loss": 0.0975, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 2.5959595959595963e-05, | |
| "loss": 0.1405, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 26.73, | |
| "learning_rate": 2.585858585858586e-05, | |
| "loss": 0.1236, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 26.82, | |
| "learning_rate": 2.575757575757576e-05, | |
| "loss": 0.1641, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 26.91, | |
| "learning_rate": 2.5656565656565658e-05, | |
| "loss": 0.1164, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.1293, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9201388888888888, | |
| "eval_loss": 0.25357797741889954, | |
| "eval_runtime": 1.574, | |
| "eval_samples_per_second": 182.979, | |
| "eval_steps_per_second": 3.177, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 27.09, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 0.1206, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 27.18, | |
| "learning_rate": 2.5353535353535356e-05, | |
| "loss": 0.1533, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.1269, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 2.5151515151515155e-05, | |
| "loss": 0.1208, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 2.505050505050505e-05, | |
| "loss": 0.1069, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 27.55, | |
| "learning_rate": 2.494949494949495e-05, | |
| "loss": 0.1034, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 2.4848484848484847e-05, | |
| "loss": 0.087, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 27.73, | |
| "learning_rate": 2.474747474747475e-05, | |
| "loss": 0.0929, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 27.82, | |
| "learning_rate": 2.464646464646465e-05, | |
| "loss": 0.1334, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 2.4545454545454545e-05, | |
| "loss": 0.112, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.2932, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8923611111111112, | |
| "eval_loss": 0.27067822217941284, | |
| "eval_runtime": 1.5637, | |
| "eval_samples_per_second": 184.181, | |
| "eval_steps_per_second": 3.198, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 28.09, | |
| "learning_rate": 2.4343434343434344e-05, | |
| "loss": 0.1466, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 28.18, | |
| "learning_rate": 2.4242424242424244e-05, | |
| "loss": 0.1069, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 28.27, | |
| "learning_rate": 2.4141414141414143e-05, | |
| "loss": 0.0743, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 2.404040404040404e-05, | |
| "loss": 0.0703, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 28.45, | |
| "learning_rate": 2.393939393939394e-05, | |
| "loss": 0.1335, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 28.55, | |
| "learning_rate": 2.3838383838383842e-05, | |
| "loss": 0.1313, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 2.3737373737373738e-05, | |
| "loss": 0.1224, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 28.73, | |
| "learning_rate": 2.3636363636363637e-05, | |
| "loss": 0.1197, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 28.82, | |
| "learning_rate": 2.3535353535353537e-05, | |
| "loss": 0.1188, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 28.91, | |
| "learning_rate": 2.3434343434343436e-05, | |
| "loss": 0.1575, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0918, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8923611111111112, | |
| "eval_loss": 0.26875555515289307, | |
| "eval_runtime": 1.5673, | |
| "eval_samples_per_second": 183.752, | |
| "eval_steps_per_second": 3.19, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 29.09, | |
| "learning_rate": 2.3232323232323232e-05, | |
| "loss": 0.0987, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 29.18, | |
| "learning_rate": 2.313131313131313e-05, | |
| "loss": 0.1075, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 29.27, | |
| "learning_rate": 2.3030303030303034e-05, | |
| "loss": 0.1035, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "learning_rate": 2.292929292929293e-05, | |
| "loss": 0.1098, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 29.45, | |
| "learning_rate": 2.282828282828283e-05, | |
| "loss": 0.0967, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.1303, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 29.64, | |
| "learning_rate": 2.262626262626263e-05, | |
| "loss": 0.1276, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 29.73, | |
| "learning_rate": 2.2525252525252528e-05, | |
| "loss": 0.1105, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 2.2424242424242424e-05, | |
| "loss": 0.1067, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 29.91, | |
| "learning_rate": 2.2323232323232324e-05, | |
| "loss": 0.1119, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1529, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8888888888888888, | |
| "eval_loss": 0.2714914083480835, | |
| "eval_runtime": 1.5703, | |
| "eval_samples_per_second": 183.402, | |
| "eval_steps_per_second": 3.184, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 30.09, | |
| "learning_rate": 2.2121212121212123e-05, | |
| "loss": 0.1097, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "learning_rate": 2.2020202020202022e-05, | |
| "loss": 0.0645, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 30.27, | |
| "learning_rate": 2.191919191919192e-05, | |
| "loss": 0.098, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 0.1134, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 2.171717171717172e-05, | |
| "loss": 0.1161, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 2.1616161616161617e-05, | |
| "loss": 0.1452, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 30.64, | |
| "learning_rate": 2.1515151515151516e-05, | |
| "loss": 0.0576, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 30.73, | |
| "learning_rate": 2.1414141414141416e-05, | |
| "loss": 0.1293, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 30.82, | |
| "learning_rate": 2.1313131313131315e-05, | |
| "loss": 0.1267, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 30.91, | |
| "learning_rate": 2.1212121212121215e-05, | |
| "loss": 0.1049, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.227, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.9027777777777778, | |
| "eval_loss": 0.2664012014865875, | |
| "eval_runtime": 1.5768, | |
| "eval_samples_per_second": 182.651, | |
| "eval_steps_per_second": 3.171, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 31.09, | |
| "learning_rate": 2.101010101010101e-05, | |
| "loss": 0.1239, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 31.18, | |
| "learning_rate": 2.090909090909091e-05, | |
| "loss": 0.0908, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 31.27, | |
| "learning_rate": 2.080808080808081e-05, | |
| "loss": 0.1132, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 31.36, | |
| "learning_rate": 2.070707070707071e-05, | |
| "loss": 0.0946, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 31.45, | |
| "learning_rate": 2.0606060606060608e-05, | |
| "loss": 0.093, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 31.55, | |
| "learning_rate": 2.0505050505050504e-05, | |
| "loss": 0.1207, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "learning_rate": 2.0404040404040407e-05, | |
| "loss": 0.111, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 31.73, | |
| "learning_rate": 2.0303030303030303e-05, | |
| "loss": 0.1069, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 31.82, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.0982, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 31.91, | |
| "learning_rate": 2.0101010101010102e-05, | |
| "loss": 0.158, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1044, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8993055555555556, | |
| "eval_loss": 0.2808922529220581, | |
| "eval_runtime": 1.5749, | |
| "eval_samples_per_second": 182.87, | |
| "eval_steps_per_second": 3.175, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 32.09, | |
| "learning_rate": 1.98989898989899e-05, | |
| "loss": 0.0917, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 32.18, | |
| "learning_rate": 1.9797979797979797e-05, | |
| "loss": 0.0979, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 32.27, | |
| "learning_rate": 1.9696969696969697e-05, | |
| "loss": 0.111, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 1.95959595959596e-05, | |
| "loss": 0.121, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 32.45, | |
| "learning_rate": 1.9494949494949496e-05, | |
| "loss": 0.1075, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 32.55, | |
| "learning_rate": 1.9393939393939395e-05, | |
| "loss": 0.1152, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 1.9292929292929295e-05, | |
| "loss": 0.0991, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 32.73, | |
| "learning_rate": 1.919191919191919e-05, | |
| "loss": 0.1117, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 32.82, | |
| "learning_rate": 1.9090909090909094e-05, | |
| "loss": 0.1275, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 1.898989898989899e-05, | |
| "loss": 0.1033, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0894, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8923611111111112, | |
| "eval_loss": 0.2863243818283081, | |
| "eval_runtime": 1.5629, | |
| "eval_samples_per_second": 184.271, | |
| "eval_steps_per_second": 3.199, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 33.09, | |
| "learning_rate": 1.878787878787879e-05, | |
| "loss": 0.0979, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 33.18, | |
| "learning_rate": 1.8686868686868688e-05, | |
| "loss": 0.076, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 33.27, | |
| "learning_rate": 1.8585858585858588e-05, | |
| "loss": 0.0744, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 33.36, | |
| "learning_rate": 1.8484848484848487e-05, | |
| "loss": 0.0952, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 33.45, | |
| "learning_rate": 1.8383838383838383e-05, | |
| "loss": 0.1057, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 33.55, | |
| "learning_rate": 1.8282828282828286e-05, | |
| "loss": 0.0713, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 33.64, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.0957, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 33.73, | |
| "learning_rate": 1.808080808080808e-05, | |
| "loss": 0.0771, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 33.82, | |
| "learning_rate": 1.797979797979798e-05, | |
| "loss": 0.111, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 33.91, | |
| "learning_rate": 1.787878787878788e-05, | |
| "loss": 0.1235, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0566, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9201388888888888, | |
| "eval_loss": 0.24742072820663452, | |
| "eval_runtime": 1.5761, | |
| "eval_samples_per_second": 182.728, | |
| "eval_steps_per_second": 3.172, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.0865, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 34.18, | |
| "learning_rate": 1.7575757575757576e-05, | |
| "loss": 0.1036, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 34.27, | |
| "learning_rate": 1.7474747474747475e-05, | |
| "loss": 0.0638, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 34.36, | |
| "learning_rate": 1.7373737373737375e-05, | |
| "loss": 0.0975, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 34.45, | |
| "learning_rate": 1.7272727272727274e-05, | |
| "loss": 0.0933, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 34.55, | |
| "learning_rate": 1.7171717171717173e-05, | |
| "loss": 0.1113, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 34.64, | |
| "learning_rate": 1.707070707070707e-05, | |
| "loss": 0.0718, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 34.73, | |
| "learning_rate": 1.6969696969696972e-05, | |
| "loss": 0.1104, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 34.82, | |
| "learning_rate": 1.686868686868687e-05, | |
| "loss": 0.0873, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 34.91, | |
| "learning_rate": 1.6767676767676768e-05, | |
| "loss": 0.1197, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0915, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.9097222222222222, | |
| "eval_loss": 0.2427683174610138, | |
| "eval_runtime": 1.5702, | |
| "eval_samples_per_second": 183.413, | |
| "eval_steps_per_second": 3.184, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 35.09, | |
| "learning_rate": 1.6565656565656567e-05, | |
| "loss": 0.1235, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 35.18, | |
| "learning_rate": 1.6464646464646466e-05, | |
| "loss": 0.0871, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 35.27, | |
| "learning_rate": 1.6363636363636366e-05, | |
| "loss": 0.0765, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 35.36, | |
| "learning_rate": 1.6262626262626262e-05, | |
| "loss": 0.0927, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 35.45, | |
| "learning_rate": 1.6161616161616165e-05, | |
| "loss": 0.1012, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 35.55, | |
| "learning_rate": 1.606060606060606e-05, | |
| "loss": 0.084, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 35.64, | |
| "learning_rate": 1.595959595959596e-05, | |
| "loss": 0.0936, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 1.585858585858586e-05, | |
| "loss": 0.128, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 35.82, | |
| "learning_rate": 1.5757575757575756e-05, | |
| "loss": 0.0969, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 35.91, | |
| "learning_rate": 1.565656565656566e-05, | |
| "loss": 0.0794, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.1136, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9097222222222222, | |
| "eval_loss": 0.25445806980133057, | |
| "eval_runtime": 1.5637, | |
| "eval_samples_per_second": 184.175, | |
| "eval_steps_per_second": 3.197, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 36.09, | |
| "learning_rate": 1.5454545454545454e-05, | |
| "loss": 0.0435, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 36.18, | |
| "learning_rate": 1.5353535353535354e-05, | |
| "loss": 0.0474, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 36.27, | |
| "learning_rate": 1.5252525252525255e-05, | |
| "loss": 0.1082, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.0613, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 36.45, | |
| "learning_rate": 1.505050505050505e-05, | |
| "loss": 0.0681, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "learning_rate": 1.494949494949495e-05, | |
| "loss": 0.0777, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 36.64, | |
| "learning_rate": 1.484848484848485e-05, | |
| "loss": 0.0706, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 36.73, | |
| "learning_rate": 1.4747474747474749e-05, | |
| "loss": 0.0696, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 36.82, | |
| "learning_rate": 1.4646464646464647e-05, | |
| "loss": 0.0689, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 36.91, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 0.0978, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.0947, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9097222222222222, | |
| "eval_loss": 0.2598806619644165, | |
| "eval_runtime": 1.5727, | |
| "eval_samples_per_second": 183.13, | |
| "eval_steps_per_second": 3.179, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 37.09, | |
| "learning_rate": 1.4343434343434345e-05, | |
| "loss": 0.05, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 37.18, | |
| "learning_rate": 1.4242424242424243e-05, | |
| "loss": 0.1237, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 37.27, | |
| "learning_rate": 1.4141414141414141e-05, | |
| "loss": 0.0491, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 37.36, | |
| "learning_rate": 1.404040404040404e-05, | |
| "loss": 0.0882, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 37.45, | |
| "learning_rate": 1.3939393939393942e-05, | |
| "loss": 0.0765, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 37.55, | |
| "learning_rate": 1.383838383838384e-05, | |
| "loss": 0.073, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 37.64, | |
| "learning_rate": 1.3737373737373737e-05, | |
| "loss": 0.0728, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 37.73, | |
| "learning_rate": 1.3636363636363637e-05, | |
| "loss": 0.075, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 37.82, | |
| "learning_rate": 1.3535353535353538e-05, | |
| "loss": 0.0682, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 37.91, | |
| "learning_rate": 1.3434343434343436e-05, | |
| "loss": 0.0675, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.1012, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.24541756510734558, | |
| "eval_runtime": 1.5701, | |
| "eval_samples_per_second": 183.432, | |
| "eval_steps_per_second": 3.185, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 38.09, | |
| "learning_rate": 1.3232323232323233e-05, | |
| "loss": 0.0642, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 38.18, | |
| "learning_rate": 1.3131313131313134e-05, | |
| "loss": 0.0701, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 38.27, | |
| "learning_rate": 1.3030303030303032e-05, | |
| "loss": 0.0675, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 38.36, | |
| "learning_rate": 1.292929292929293e-05, | |
| "loss": 0.0763, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 38.45, | |
| "learning_rate": 1.2828282828282829e-05, | |
| "loss": 0.0664, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 38.55, | |
| "learning_rate": 1.2727272727272727e-05, | |
| "loss": 0.1222, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 38.64, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.072, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 38.73, | |
| "learning_rate": 1.2525252525252526e-05, | |
| "loss": 0.0877, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 38.82, | |
| "learning_rate": 1.2424242424242424e-05, | |
| "loss": 0.1098, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 38.91, | |
| "learning_rate": 1.2323232323232325e-05, | |
| "loss": 0.0774, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.0465, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9201388888888888, | |
| "eval_loss": 0.24348551034927368, | |
| "eval_runtime": 1.5838, | |
| "eval_samples_per_second": 181.842, | |
| "eval_steps_per_second": 3.157, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 39.09, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 0.0474, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 39.18, | |
| "learning_rate": 1.202020202020202e-05, | |
| "loss": 0.0535, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 39.27, | |
| "learning_rate": 1.1919191919191921e-05, | |
| "loss": 0.1069, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 39.36, | |
| "learning_rate": 1.1818181818181819e-05, | |
| "loss": 0.0872, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 39.45, | |
| "learning_rate": 1.1717171717171718e-05, | |
| "loss": 0.0852, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 39.55, | |
| "learning_rate": 1.1616161616161616e-05, | |
| "loss": 0.0503, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 39.64, | |
| "learning_rate": 1.1515151515151517e-05, | |
| "loss": 0.0746, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 39.73, | |
| "learning_rate": 1.1414141414141415e-05, | |
| "loss": 0.0866, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 39.82, | |
| "learning_rate": 1.1313131313131314e-05, | |
| "loss": 0.1031, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 39.91, | |
| "learning_rate": 1.1212121212121212e-05, | |
| "loss": 0.075, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0299, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.90625, | |
| "eval_loss": 0.25319477915763855, | |
| "eval_runtime": 1.5767, | |
| "eval_samples_per_second": 182.661, | |
| "eval_steps_per_second": 3.171, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 40.09, | |
| "learning_rate": 1.1010101010101011e-05, | |
| "loss": 0.0958, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 40.18, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 0.0964, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 40.27, | |
| "learning_rate": 1.0808080808080808e-05, | |
| "loss": 0.0524, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 40.36, | |
| "learning_rate": 1.0707070707070708e-05, | |
| "loss": 0.0487, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 40.45, | |
| "learning_rate": 1.0606060606060607e-05, | |
| "loss": 0.0801, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 1.0505050505050505e-05, | |
| "loss": 0.1102, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 40.64, | |
| "learning_rate": 1.0404040404040405e-05, | |
| "loss": 0.0523, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 40.73, | |
| "learning_rate": 1.0303030303030304e-05, | |
| "loss": 0.0825, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 40.82, | |
| "learning_rate": 1.0202020202020204e-05, | |
| "loss": 0.0664, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 40.91, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.0621, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0311, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.9270833333333334, | |
| "eval_loss": 0.2298324704170227, | |
| "eval_runtime": 1.577, | |
| "eval_samples_per_second": 182.629, | |
| "eval_steps_per_second": 3.171, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 41.09, | |
| "learning_rate": 9.898989898989899e-06, | |
| "loss": 0.0482, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 41.18, | |
| "learning_rate": 9.7979797979798e-06, | |
| "loss": 0.0874, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 41.27, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 0.0582, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 41.36, | |
| "learning_rate": 9.595959595959595e-06, | |
| "loss": 0.0519, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 41.45, | |
| "learning_rate": 9.494949494949495e-06, | |
| "loss": 0.1067, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 41.55, | |
| "learning_rate": 9.393939393939394e-06, | |
| "loss": 0.0855, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 41.64, | |
| "learning_rate": 9.292929292929294e-06, | |
| "loss": 0.0874, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 41.73, | |
| "learning_rate": 9.191919191919192e-06, | |
| "loss": 0.0601, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 41.82, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.0572, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 41.91, | |
| "learning_rate": 8.98989898989899e-06, | |
| "loss": 0.0762, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0796, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_loss": 0.24221903085708618, | |
| "eval_runtime": 1.5621, | |
| "eval_samples_per_second": 184.366, | |
| "eval_steps_per_second": 3.201, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 42.09, | |
| "learning_rate": 8.787878787878788e-06, | |
| "loss": 0.0636, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 42.18, | |
| "learning_rate": 8.686868686868687e-06, | |
| "loss": 0.0522, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 42.27, | |
| "learning_rate": 8.585858585858587e-06, | |
| "loss": 0.0725, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 42.36, | |
| "learning_rate": 8.484848484848486e-06, | |
| "loss": 0.0872, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 42.45, | |
| "learning_rate": 8.383838383838384e-06, | |
| "loss": 0.0571, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 42.55, | |
| "learning_rate": 8.282828282828283e-06, | |
| "loss": 0.0991, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 8.181818181818183e-06, | |
| "loss": 0.0781, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 42.73, | |
| "learning_rate": 8.080808080808082e-06, | |
| "loss": 0.0814, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 42.82, | |
| "learning_rate": 7.97979797979798e-06, | |
| "loss": 0.071, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "learning_rate": 7.878787878787878e-06, | |
| "loss": 0.08, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.058, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.9305555555555556, | |
| "eval_loss": 0.2058059573173523, | |
| "eval_runtime": 1.5649, | |
| "eval_samples_per_second": 184.034, | |
| "eval_steps_per_second": 3.195, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 43.09, | |
| "learning_rate": 7.676767676767677e-06, | |
| "loss": 0.0719, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 43.18, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.0663, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 43.27, | |
| "learning_rate": 7.474747474747475e-06, | |
| "loss": 0.0397, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 43.36, | |
| "learning_rate": 7.3737373737373745e-06, | |
| "loss": 0.0452, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 43.45, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 0.0515, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 43.55, | |
| "learning_rate": 7.171717171717173e-06, | |
| "loss": 0.0958, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 43.64, | |
| "learning_rate": 7.0707070707070704e-06, | |
| "loss": 0.104, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 43.73, | |
| "learning_rate": 6.969696969696971e-06, | |
| "loss": 0.0882, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 43.82, | |
| "learning_rate": 6.8686868686868685e-06, | |
| "loss": 0.0734, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 43.91, | |
| "learning_rate": 6.767676767676769e-06, | |
| "loss": 0.0448, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0853, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9305555555555556, | |
| "eval_loss": 0.2266363501548767, | |
| "eval_runtime": 1.5654, | |
| "eval_samples_per_second": 183.973, | |
| "eval_steps_per_second": 3.194, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 44.09, | |
| "learning_rate": 6.565656565656567e-06, | |
| "loss": 0.0558, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 44.18, | |
| "learning_rate": 6.464646464646465e-06, | |
| "loss": 0.0655, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 44.27, | |
| "learning_rate": 6.363636363636363e-06, | |
| "loss": 0.0781, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 44.36, | |
| "learning_rate": 6.262626262626263e-06, | |
| "loss": 0.0626, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 44.45, | |
| "learning_rate": 6.161616161616162e-06, | |
| "loss": 0.0671, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 44.55, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 0.0565, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 44.64, | |
| "learning_rate": 5.9595959595959605e-06, | |
| "loss": 0.0517, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 44.73, | |
| "learning_rate": 5.858585858585859e-06, | |
| "loss": 0.0785, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 44.82, | |
| "learning_rate": 5.7575757575757586e-06, | |
| "loss": 0.0558, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 44.91, | |
| "learning_rate": 5.656565656565657e-06, | |
| "loss": 0.0655, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0868, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.9236111111111112, | |
| "eval_loss": 0.22659315168857574, | |
| "eval_runtime": 1.5757, | |
| "eval_samples_per_second": 182.772, | |
| "eval_steps_per_second": 3.173, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 45.09, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 0.0681, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 45.18, | |
| "learning_rate": 5.353535353535354e-06, | |
| "loss": 0.0541, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 45.27, | |
| "learning_rate": 5.2525252525252526e-06, | |
| "loss": 0.0695, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 45.36, | |
| "learning_rate": 5.151515151515152e-06, | |
| "loss": 0.0344, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 45.45, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.0554, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 45.55, | |
| "learning_rate": 4.949494949494949e-06, | |
| "loss": 0.0691, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 45.64, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 0.0715, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 45.73, | |
| "learning_rate": 4.747474747474747e-06, | |
| "loss": 0.0519, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 45.82, | |
| "learning_rate": 4.646464646464647e-06, | |
| "loss": 0.0658, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 45.91, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 0.088, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0554, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.9270833333333334, | |
| "eval_loss": 0.2163047045469284, | |
| "eval_runtime": 1.5704, | |
| "eval_samples_per_second": 183.395, | |
| "eval_steps_per_second": 3.184, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 46.09, | |
| "learning_rate": 4.343434343434344e-06, | |
| "loss": 0.0632, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 46.18, | |
| "learning_rate": 4.242424242424243e-06, | |
| "loss": 0.0838, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 46.27, | |
| "learning_rate": 4.141414141414142e-06, | |
| "loss": 0.0752, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 46.36, | |
| "learning_rate": 4.040404040404041e-06, | |
| "loss": 0.0767, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 46.45, | |
| "learning_rate": 3.939393939393939e-06, | |
| "loss": 0.0855, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 46.55, | |
| "learning_rate": 3.8383838383838385e-06, | |
| "loss": 0.0392, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 46.64, | |
| "learning_rate": 3.7373737373737375e-06, | |
| "loss": 0.0681, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 46.73, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 0.0551, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 46.82, | |
| "learning_rate": 3.5353535353535352e-06, | |
| "loss": 0.0516, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 46.91, | |
| "learning_rate": 3.4343434343434343e-06, | |
| "loss": 0.0778, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0508, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.9305555555555556, | |
| "eval_loss": 0.21035218238830566, | |
| "eval_runtime": 1.5655, | |
| "eval_samples_per_second": 183.961, | |
| "eval_steps_per_second": 3.194, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 47.09, | |
| "learning_rate": 3.2323232323232324e-06, | |
| "loss": 0.041, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 47.18, | |
| "learning_rate": 3.1313131313131314e-06, | |
| "loss": 0.041, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 47.27, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 0.0813, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 47.36, | |
| "learning_rate": 2.9292929292929295e-06, | |
| "loss": 0.0567, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 47.45, | |
| "learning_rate": 2.8282828282828286e-06, | |
| "loss": 0.055, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 47.55, | |
| "learning_rate": 2.7272727272727272e-06, | |
| "loss": 0.0505, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 47.64, | |
| "learning_rate": 2.6262626262626263e-06, | |
| "loss": 0.0239, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 47.73, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.0441, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 47.82, | |
| "learning_rate": 2.4242424242424244e-06, | |
| "loss": 0.0567, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 2.3232323232323234e-06, | |
| "loss": 0.0711, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0589, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.9270833333333334, | |
| "eval_loss": 0.21717707812786102, | |
| "eval_runtime": 1.5625, | |
| "eval_samples_per_second": 184.318, | |
| "eval_steps_per_second": 3.2, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 48.09, | |
| "learning_rate": 2.1212121212121216e-06, | |
| "loss": 0.0363, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 48.18, | |
| "learning_rate": 2.0202020202020206e-06, | |
| "loss": 0.0767, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 48.27, | |
| "learning_rate": 1.9191919191919192e-06, | |
| "loss": 0.0835, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 48.36, | |
| "learning_rate": 1.818181818181818e-06, | |
| "loss": 0.0769, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 48.45, | |
| "learning_rate": 1.7171717171717171e-06, | |
| "loss": 0.0373, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 48.55, | |
| "learning_rate": 1.6161616161616162e-06, | |
| "loss": 0.0473, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 48.64, | |
| "learning_rate": 1.5151515151515152e-06, | |
| "loss": 0.0439, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 48.73, | |
| "learning_rate": 1.4141414141414143e-06, | |
| "loss": 0.0615, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 48.82, | |
| "learning_rate": 1.3131313131313131e-06, | |
| "loss": 0.0554, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 48.91, | |
| "learning_rate": 1.2121212121212122e-06, | |
| "loss": 0.0669, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.0369, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.9270833333333334, | |
| "eval_loss": 0.22139286994934082, | |
| "eval_runtime": 1.5665, | |
| "eval_samples_per_second": 183.854, | |
| "eval_steps_per_second": 3.192, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 49.09, | |
| "learning_rate": 1.0101010101010103e-06, | |
| "loss": 0.043, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 49.18, | |
| "learning_rate": 9.09090909090909e-07, | |
| "loss": 0.0441, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 49.27, | |
| "learning_rate": 8.080808080808081e-07, | |
| "loss": 0.0507, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 49.36, | |
| "learning_rate": 7.070707070707071e-07, | |
| "loss": 0.0612, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 49.45, | |
| "learning_rate": 6.060606060606061e-07, | |
| "loss": 0.0719, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 49.55, | |
| "learning_rate": 5.050505050505052e-07, | |
| "loss": 0.0757, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 49.64, | |
| "learning_rate": 4.0404040404040405e-07, | |
| "loss": 0.0473, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 49.73, | |
| "learning_rate": 3.0303030303030305e-07, | |
| "loss": 0.0859, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 49.82, | |
| "learning_rate": 2.0202020202020202e-07, | |
| "loss": 0.0462, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 49.91, | |
| "learning_rate": 1.0101010101010101e-07, | |
| "loss": 0.0517, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0852, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.9270833333333334, | |
| "eval_loss": 0.22411441802978516, | |
| "eval_runtime": 1.5744, | |
| "eval_samples_per_second": 182.932, | |
| "eval_steps_per_second": 3.176, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 550, | |
| "total_flos": 1.0035482482400256e+19, | |
| "train_loss": 0.24394690781493078, | |
| "train_runtime": 2413.5397, | |
| "train_samples_per_second": 53.656, | |
| "train_steps_per_second": 0.228 | |
| } | |
| ], | |
| "max_steps": 550, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.0035482482400256e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |