End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.125,
|
| 3 |
+
"eval_accuracy": 0.21431451612903227,
|
| 4 |
+
"eval_loss": 2.547022581100464,
|
| 5 |
+
"eval_runtime": 875.9015,
|
| 6 |
+
"eval_samples_per_second": 5.663,
|
| 7 |
+
"eval_steps_per_second": 0.708
|
| 8 |
+
}
|
runs/Sep29_00-14-12_fbe835519fef/events.out.tfevents.1727584795.fbe835519fef.30.5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a993a107f1ae46e9babc51cbb098b3c84b8111fb49da05d58ae80aebc5bdf8e2
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.125,
|
| 3 |
+
"eval_accuracy": 0.21431451612903227,
|
| 4 |
+
"eval_loss": 2.547022581100464,
|
| 5 |
+
"eval_runtime": 875.9015,
|
| 6 |
+
"eval_samples_per_second": 5.663,
|
| 7 |
+
"eval_steps_per_second": 0.708
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,692 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.24527826743893225,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucfcrime-full2/checkpoint-400",
|
| 4 |
+
"epoch": 7.125,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0125,
|
| 13 |
+
"grad_norm": 416496.125,
|
| 14 |
+
"learning_rate": 6.25e-06,
|
| 15 |
+
"loss": 1.9739,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.025,
|
| 20 |
+
"grad_norm": 594418.0625,
|
| 21 |
+
"learning_rate": 1.25e-05,
|
| 22 |
+
"loss": 2.0117,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0375,
|
| 27 |
+
"grad_norm": 669342.5,
|
| 28 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 29 |
+
"loss": 1.9919,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05,
|
| 34 |
+
"grad_norm": 686419.375,
|
| 35 |
+
"learning_rate": 2.5e-05,
|
| 36 |
+
"loss": 1.8385,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0625,
|
| 41 |
+
"grad_norm": 561864.3125,
|
| 42 |
+
"learning_rate": 3.125e-05,
|
| 43 |
+
"loss": 2.0993,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.075,
|
| 48 |
+
"grad_norm": 931406.9375,
|
| 49 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 50 |
+
"loss": 2.1469,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0875,
|
| 55 |
+
"grad_norm": 518422.0,
|
| 56 |
+
"learning_rate": 4.375e-05,
|
| 57 |
+
"loss": 2.2427,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1,
|
| 62 |
+
"grad_norm": 702745.9375,
|
| 63 |
+
"learning_rate": 5e-05,
|
| 64 |
+
"loss": 2.0093,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1125,
|
| 69 |
+
"grad_norm": 737373.75,
|
| 70 |
+
"learning_rate": 4.930555555555556e-05,
|
| 71 |
+
"loss": 2.0531,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.125,
|
| 76 |
+
"grad_norm": 951342.4375,
|
| 77 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 78 |
+
"loss": 2.2039,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.125,
|
| 83 |
+
"eval_accuracy": 0.16441441441441443,
|
| 84 |
+
"eval_loss": 2.4596593379974365,
|
| 85 |
+
"eval_runtime": 1486.363,
|
| 86 |
+
"eval_samples_per_second": 5.377,
|
| 87 |
+
"eval_steps_per_second": 0.672,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0125,
|
| 92 |
+
"grad_norm": 783028.0625,
|
| 93 |
+
"learning_rate": 4.791666666666667e-05,
|
| 94 |
+
"loss": 1.9407,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.025,
|
| 99 |
+
"grad_norm": 592436.375,
|
| 100 |
+
"learning_rate": 4.722222222222222e-05,
|
| 101 |
+
"loss": 2.128,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.0375,
|
| 106 |
+
"grad_norm": 551391.1875,
|
| 107 |
+
"learning_rate": 4.652777777777778e-05,
|
| 108 |
+
"loss": 1.8403,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.05,
|
| 113 |
+
"grad_norm": 732315.75,
|
| 114 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 115 |
+
"loss": 2.199,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0625,
|
| 120 |
+
"grad_norm": 833000.5,
|
| 121 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 122 |
+
"loss": 2.1457,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.075,
|
| 127 |
+
"grad_norm": 645952.25,
|
| 128 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 129 |
+
"loss": 2.1546,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0875,
|
| 134 |
+
"grad_norm": 741493.375,
|
| 135 |
+
"learning_rate": 4.375e-05,
|
| 136 |
+
"loss": 1.9128,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1,
|
| 141 |
+
"grad_norm": 610463.875,
|
| 142 |
+
"learning_rate": 4.305555555555556e-05,
|
| 143 |
+
"loss": 1.9581,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.1125,
|
| 148 |
+
"grad_norm": 669701.875,
|
| 149 |
+
"learning_rate": 4.236111111111111e-05,
|
| 150 |
+
"loss": 2.2864,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.125,
|
| 155 |
+
"grad_norm": 555390.8125,
|
| 156 |
+
"learning_rate": 4.166666666666667e-05,
|
| 157 |
+
"loss": 1.8182,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.125,
|
| 162 |
+
"eval_accuracy": 0.2046084109796021,
|
| 163 |
+
"eval_loss": 2.3359453678131104,
|
| 164 |
+
"eval_runtime": 1481.2653,
|
| 165 |
+
"eval_samples_per_second": 5.362,
|
| 166 |
+
"eval_steps_per_second": 0.67,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.0125,
|
| 171 |
+
"grad_norm": 982366.0,
|
| 172 |
+
"learning_rate": 4.0972222222222225e-05,
|
| 173 |
+
"loss": 1.7361,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.025,
|
| 178 |
+
"grad_norm": 489943.53125,
|
| 179 |
+
"learning_rate": 4.027777777777778e-05,
|
| 180 |
+
"loss": 1.9965,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.0375,
|
| 185 |
+
"grad_norm": 691774.0625,
|
| 186 |
+
"learning_rate": 3.958333333333333e-05,
|
| 187 |
+
"loss": 1.9369,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.05,
|
| 192 |
+
"grad_norm": 592585.875,
|
| 193 |
+
"learning_rate": 3.888888888888889e-05,
|
| 194 |
+
"loss": 2.2331,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.0625,
|
| 199 |
+
"grad_norm": 774321.4375,
|
| 200 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 201 |
+
"loss": 1.9108,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.075,
|
| 206 |
+
"grad_norm": 443132.03125,
|
| 207 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 208 |
+
"loss": 1.5835,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.0875,
|
| 213 |
+
"grad_norm": 816018.125,
|
| 214 |
+
"learning_rate": 3.6805555555555556e-05,
|
| 215 |
+
"loss": 1.9894,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.1,
|
| 220 |
+
"grad_norm": 558110.125,
|
| 221 |
+
"learning_rate": 3.611111111111111e-05,
|
| 222 |
+
"loss": 1.8828,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.1125,
|
| 227 |
+
"grad_norm": 582578.75,
|
| 228 |
+
"learning_rate": 3.541666666666667e-05,
|
| 229 |
+
"loss": 1.9,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.125,
|
| 234 |
+
"grad_norm": 637794.125,
|
| 235 |
+
"learning_rate": 3.472222222222222e-05,
|
| 236 |
+
"loss": 1.9124,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.125,
|
| 241 |
+
"eval_accuracy": 0.2077562326869806,
|
| 242 |
+
"eval_loss": 2.680464506149292,
|
| 243 |
+
"eval_runtime": 1473.8252,
|
| 244 |
+
"eval_samples_per_second": 5.389,
|
| 245 |
+
"eval_steps_per_second": 0.674,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.0125,
|
| 250 |
+
"grad_norm": 860386.8125,
|
| 251 |
+
"learning_rate": 3.402777777777778e-05,
|
| 252 |
+
"loss": 1.7279,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.025,
|
| 257 |
+
"grad_norm": 607838.0,
|
| 258 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 259 |
+
"loss": 1.7094,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.0375,
|
| 264 |
+
"grad_norm": 742987.3125,
|
| 265 |
+
"learning_rate": 3.263888888888889e-05,
|
| 266 |
+
"loss": 1.9674,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.05,
|
| 271 |
+
"grad_norm": 1233058.5,
|
| 272 |
+
"learning_rate": 3.194444444444444e-05,
|
| 273 |
+
"loss": 1.7507,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.0625,
|
| 278 |
+
"grad_norm": 582323.3125,
|
| 279 |
+
"learning_rate": 3.125e-05,
|
| 280 |
+
"loss": 1.7098,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.075,
|
| 285 |
+
"grad_norm": 1024568.625,
|
| 286 |
+
"learning_rate": 3.055555555555556e-05,
|
| 287 |
+
"loss": 1.9264,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.0875,
|
| 292 |
+
"grad_norm": 656340.6875,
|
| 293 |
+
"learning_rate": 2.9861111111111113e-05,
|
| 294 |
+
"loss": 1.6687,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.1,
|
| 299 |
+
"grad_norm": 1037552.0,
|
| 300 |
+
"learning_rate": 2.916666666666667e-05,
|
| 301 |
+
"loss": 1.6596,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.1125,
|
| 306 |
+
"grad_norm": 680651.3125,
|
| 307 |
+
"learning_rate": 2.8472222222222223e-05,
|
| 308 |
+
"loss": 1.8054,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.125,
|
| 313 |
+
"grad_norm": 687134.875,
|
| 314 |
+
"learning_rate": 2.777777777777778e-05,
|
| 315 |
+
"loss": 1.7017,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.125,
|
| 320 |
+
"eval_accuracy": 0.24527826743893225,
|
| 321 |
+
"eval_loss": 2.333141803741455,
|
| 322 |
+
"eval_runtime": 1475.5703,
|
| 323 |
+
"eval_samples_per_second": 5.382,
|
| 324 |
+
"eval_steps_per_second": 0.673,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.0125,
|
| 329 |
+
"grad_norm": 719175.6875,
|
| 330 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 331 |
+
"loss": 1.5792,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.025,
|
| 336 |
+
"grad_norm": 613320.625,
|
| 337 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 338 |
+
"loss": 1.7086,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.0375,
|
| 343 |
+
"grad_norm": 795721.5625,
|
| 344 |
+
"learning_rate": 2.5694444444444445e-05,
|
| 345 |
+
"loss": 1.7548,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.05,
|
| 350 |
+
"grad_norm": 754591.0,
|
| 351 |
+
"learning_rate": 2.5e-05,
|
| 352 |
+
"loss": 1.7227,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.0625,
|
| 357 |
+
"grad_norm": 898280.9375,
|
| 358 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 359 |
+
"loss": 1.7121,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.075,
|
| 364 |
+
"grad_norm": 973403.75,
|
| 365 |
+
"learning_rate": 2.361111111111111e-05,
|
| 366 |
+
"loss": 1.6087,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.0875,
|
| 371 |
+
"grad_norm": 794706.0625,
|
| 372 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 373 |
+
"loss": 1.6259,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.1,
|
| 378 |
+
"grad_norm": 780511.9375,
|
| 379 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 380 |
+
"loss": 1.7734,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.1125,
|
| 385 |
+
"grad_norm": 1010192.125,
|
| 386 |
+
"learning_rate": 2.152777777777778e-05,
|
| 387 |
+
"loss": 1.6318,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.125,
|
| 392 |
+
"grad_norm": 610750.1875,
|
| 393 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 394 |
+
"loss": 1.68,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.125,
|
| 399 |
+
"eval_accuracy": 0.22248803827751196,
|
| 400 |
+
"eval_loss": 2.2636775970458984,
|
| 401 |
+
"eval_runtime": 1479.3494,
|
| 402 |
+
"eval_samples_per_second": 5.369,
|
| 403 |
+
"eval_steps_per_second": 0.671,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.0125,
|
| 408 |
+
"grad_norm": 1084686.25,
|
| 409 |
+
"learning_rate": 2.013888888888889e-05,
|
| 410 |
+
"loss": 1.4838,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 5.025,
|
| 415 |
+
"grad_norm": 723063.5625,
|
| 416 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 417 |
+
"loss": 1.7148,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 5.0375,
|
| 422 |
+
"grad_norm": 780978.0,
|
| 423 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 424 |
+
"loss": 1.6672,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 5.05,
|
| 429 |
+
"grad_norm": 875436.0625,
|
| 430 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 431 |
+
"loss": 1.5467,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.0625,
|
| 436 |
+
"grad_norm": 742270.875,
|
| 437 |
+
"learning_rate": 1.736111111111111e-05,
|
| 438 |
+
"loss": 1.5539,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.075,
|
| 443 |
+
"grad_norm": 846790.625,
|
| 444 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 445 |
+
"loss": 1.5211,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.0875,
|
| 450 |
+
"grad_norm": 833175.75,
|
| 451 |
+
"learning_rate": 1.597222222222222e-05,
|
| 452 |
+
"loss": 1.5436,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.1,
|
| 457 |
+
"grad_norm": 1164196.0,
|
| 458 |
+
"learning_rate": 1.527777777777778e-05,
|
| 459 |
+
"loss": 1.2434,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.1125,
|
| 464 |
+
"grad_norm": 1534336.75,
|
| 465 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 466 |
+
"loss": 1.6604,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.125,
|
| 471 |
+
"grad_norm": 1043594.25,
|
| 472 |
+
"learning_rate": 1.388888888888889e-05,
|
| 473 |
+
"loss": 1.5457,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.125,
|
| 478 |
+
"eval_accuracy": 0.22840594308738352,
|
| 479 |
+
"eval_loss": 2.471050977706909,
|
| 480 |
+
"eval_runtime": 1474.9621,
|
| 481 |
+
"eval_samples_per_second": 5.385,
|
| 482 |
+
"eval_steps_per_second": 0.673,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 6.0125,
|
| 487 |
+
"grad_norm": 970448.25,
|
| 488 |
+
"learning_rate": 1.3194444444444446e-05,
|
| 489 |
+
"loss": 1.4714,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 6.025,
|
| 494 |
+
"grad_norm": 623090.375,
|
| 495 |
+
"learning_rate": 1.25e-05,
|
| 496 |
+
"loss": 1.3935,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 6.0375,
|
| 501 |
+
"grad_norm": 744650.8125,
|
| 502 |
+
"learning_rate": 1.1805555555555555e-05,
|
| 503 |
+
"loss": 1.4471,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 6.05,
|
| 508 |
+
"grad_norm": 971446.3125,
|
| 509 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 510 |
+
"loss": 1.5173,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 6.0625,
|
| 515 |
+
"grad_norm": 773394.0625,
|
| 516 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 517 |
+
"loss": 1.4809,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.075,
|
| 522 |
+
"grad_norm": 852698.6875,
|
| 523 |
+
"learning_rate": 9.722222222222223e-06,
|
| 524 |
+
"loss": 1.392,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.0875,
|
| 529 |
+
"grad_norm": 949506.75,
|
| 530 |
+
"learning_rate": 9.027777777777777e-06,
|
| 531 |
+
"loss": 1.4143,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.1,
|
| 536 |
+
"grad_norm": 1045740.0,
|
| 537 |
+
"learning_rate": 8.333333333333334e-06,
|
| 538 |
+
"loss": 1.6005,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.1125,
|
| 543 |
+
"grad_norm": 793035.75,
|
| 544 |
+
"learning_rate": 7.63888888888889e-06,
|
| 545 |
+
"loss": 1.3571,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.125,
|
| 550 |
+
"grad_norm": 638157.5625,
|
| 551 |
+
"learning_rate": 6.944444444444445e-06,
|
| 552 |
+
"loss": 1.4727,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.125,
|
| 557 |
+
"eval_accuracy": 0.21102996726265424,
|
| 558 |
+
"eval_loss": 2.369114637374878,
|
| 559 |
+
"eval_runtime": 1473.3779,
|
| 560 |
+
"eval_samples_per_second": 5.39,
|
| 561 |
+
"eval_steps_per_second": 0.674,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.0125,
|
| 566 |
+
"grad_norm": 529226.1875,
|
| 567 |
+
"learning_rate": 6.25e-06,
|
| 568 |
+
"loss": 1.0833,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.025,
|
| 573 |
+
"grad_norm": 796843.1875,
|
| 574 |
+
"learning_rate": 5.555555555555556e-06,
|
| 575 |
+
"loss": 1.341,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.0375,
|
| 580 |
+
"grad_norm": 747058.1875,
|
| 581 |
+
"learning_rate": 4.861111111111111e-06,
|
| 582 |
+
"loss": 1.5642,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.05,
|
| 587 |
+
"grad_norm": 647754.0625,
|
| 588 |
+
"learning_rate": 4.166666666666667e-06,
|
| 589 |
+
"loss": 1.3922,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 7.0625,
|
| 594 |
+
"grad_norm": 1013934.3125,
|
| 595 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 596 |
+
"loss": 1.5842,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 7.075,
|
| 601 |
+
"grad_norm": 694990.5625,
|
| 602 |
+
"learning_rate": 2.777777777777778e-06,
|
| 603 |
+
"loss": 1.2497,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.0875,
|
| 608 |
+
"grad_norm": 964756.0,
|
| 609 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 610 |
+
"loss": 1.2914,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.1,
|
| 615 |
+
"grad_norm": 754335.25,
|
| 616 |
+
"learning_rate": 1.388888888888889e-06,
|
| 617 |
+
"loss": 1.3096,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.1125,
|
| 622 |
+
"grad_norm": 1201313.375,
|
| 623 |
+
"learning_rate": 6.944444444444445e-07,
|
| 624 |
+
"loss": 1.4434,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.125,
|
| 629 |
+
"grad_norm": 1206534.625,
|
| 630 |
+
"learning_rate": 0.0,
|
| 631 |
+
"loss": 1.5393,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.125,
|
| 636 |
+
"eval_accuracy": 0.20246789221858474,
|
| 637 |
+
"eval_loss": 2.456111431121826,
|
| 638 |
+
"eval_runtime": 1474.6345,
|
| 639 |
+
"eval_samples_per_second": 5.386,
|
| 640 |
+
"eval_steps_per_second": 0.673,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 7.125,
|
| 645 |
+
"step": 800,
|
| 646 |
+
"total_flos": 7.975666818691891e+18,
|
| 647 |
+
"train_loss": 1.7285779798030854,
|
| 648 |
+
"train_runtime": 14999.7991,
|
| 649 |
+
"train_samples_per_second": 0.427,
|
| 650 |
+
"train_steps_per_second": 0.053
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 7.125,
|
| 654 |
+
"eval_accuracy": 0.21431451612903227,
|
| 655 |
+
"eval_loss": 2.547022819519043,
|
| 656 |
+
"eval_runtime": 883.8934,
|
| 657 |
+
"eval_samples_per_second": 5.612,
|
| 658 |
+
"eval_steps_per_second": 0.701,
|
| 659 |
+
"step": 800
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 7.125,
|
| 663 |
+
"eval_accuracy": 0.21431451612903227,
|
| 664 |
+
"eval_loss": 2.547022581100464,
|
| 665 |
+
"eval_runtime": 875.9015,
|
| 666 |
+
"eval_samples_per_second": 5.663,
|
| 667 |
+
"eval_steps_per_second": 0.708,
|
| 668 |
+
"step": 800
|
| 669 |
+
}
|
| 670 |
+
],
|
| 671 |
+
"logging_steps": 10,
|
| 672 |
+
"max_steps": 800,
|
| 673 |
+
"num_input_tokens_seen": 0,
|
| 674 |
+
"num_train_epochs": 9223372036854775807,
|
| 675 |
+
"save_steps": 500,
|
| 676 |
+
"stateful_callbacks": {
|
| 677 |
+
"TrainerControl": {
|
| 678 |
+
"args": {
|
| 679 |
+
"should_epoch_stop": false,
|
| 680 |
+
"should_evaluate": false,
|
| 681 |
+
"should_log": false,
|
| 682 |
+
"should_save": true,
|
| 683 |
+
"should_training_stop": true
|
| 684 |
+
},
|
| 685 |
+
"attributes": {}
|
| 686 |
+
}
|
| 687 |
+
},
|
| 688 |
+
"total_flos": 7.975666818691891e+18,
|
| 689 |
+
"train_batch_size": 8,
|
| 690 |
+
"trial_name": null,
|
| 691 |
+
"trial_params": null
|
| 692 |
+
}
|