Training in progress, epoch 0
Browse files- all_results.json +18 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- runs/Nov02_22-45-34_a4709a859fdb/events.out.tfevents.1698965826.a4709a859fdb.1287.15 +3 -0
- runs/Nov02_22-58-42_a4709a859fdb/events.out.tfevents.1698965932.a4709a859fdb.1287.16 +3 -0
- test_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +448 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.51,
|
| 3 |
+
"eval_accuracy": 0.7853881278538812,
|
| 4 |
+
"eval_loss": 0.5823199152946472,
|
| 5 |
+
"eval_runtime": 3.0684,
|
| 6 |
+
"eval_samples_per_second": 71.373,
|
| 7 |
+
"eval_steps_per_second": 9.125,
|
| 8 |
+
"test_accuracy": 0.7853881278538812,
|
| 9 |
+
"test_loss": 0.7590954303741455,
|
| 10 |
+
"test_runtime": 2.965,
|
| 11 |
+
"test_samples_per_second": 73.862,
|
| 12 |
+
"test_steps_per_second": 9.444,
|
| 13 |
+
"total_flos": 9.874981246081352e+17,
|
| 14 |
+
"train_loss": 0.2905089810490608,
|
| 15 |
+
"train_runtime": 669.2028,
|
| 16 |
+
"train_samples_per_second": 19.516,
|
| 17 |
+
"train_steps_per_second": 0.598
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.51,
|
| 3 |
+
"eval_accuracy": 0.7853881278538812,
|
| 4 |
+
"eval_loss": 0.5823199152946472,
|
| 5 |
+
"eval_runtime": 3.0684,
|
| 6 |
+
"eval_samples_per_second": 71.373,
|
| 7 |
+
"eval_steps_per_second": 9.125
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343230128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d74e68a2de251a507227665bab97ef7ea959e46aeed8bb8603f982b00851b654
|
| 3 |
size 343230128
|
runs/Nov02_22-45-34_a4709a859fdb/events.out.tfevents.1698965826.a4709a859fdb.1287.15
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3a7b57e7d95196aa9df7c4df958522452704926f56c50a33a7e6b825829f6f4
|
| 3 |
+
size 411
|
runs/Nov02_22-58-42_a4709a859fdb/events.out.tfevents.1698965932.a4709a859fdb.1287.16
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:135a83d61ab906d15aaf74f46a9c12b77d47f0b242dcec0faa30c594f0418a25
|
| 3 |
+
size 5010
|
test_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"test_accuracy": 0.7853881278538812,
|
| 3 |
+
"test_loss": 0.7590954303741455,
|
| 4 |
+
"test_runtime": 2.965,
|
| 5 |
+
"test_samples_per_second": 73.862,
|
| 6 |
+
"test_steps_per_second": 9.444
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.51,
|
| 3 |
+
"total_flos": 9.874981246081352e+17,
|
| 4 |
+
"train_loss": 0.2905089810490608,
|
| 5 |
+
"train_runtime": 669.2028,
|
| 6 |
+
"train_samples_per_second": 19.516,
|
| 7 |
+
"train_steps_per_second": 0.598
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7853881278538812,
|
| 3 |
+
"best_model_checkpoint": "deit-base-patch16-224-finetuned-piid/checkpoint-266",
|
| 4 |
+
"epoch": 19.51219512195122,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.49,
|
| 13 |
+
"learning_rate": 1.25e-05,
|
| 14 |
+
"loss": 1.4017,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.98,
|
| 19 |
+
"learning_rate": 2.5e-05,
|
| 20 |
+
"loss": 1.2042,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.98,
|
| 25 |
+
"eval_accuracy": 0.5205479452054794,
|
| 26 |
+
"eval_loss": 1.0728942155838013,
|
| 27 |
+
"eval_runtime": 2.9326,
|
| 28 |
+
"eval_samples_per_second": 74.678,
|
| 29 |
+
"eval_steps_per_second": 9.548,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.46,
|
| 34 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 35 |
+
"loss": 0.8623,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.95,
|
| 40 |
+
"learning_rate": 5e-05,
|
| 41 |
+
"loss": 0.6598,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.0,
|
| 46 |
+
"eval_accuracy": 0.634703196347032,
|
| 47 |
+
"eval_loss": 0.8121764063835144,
|
| 48 |
+
"eval_runtime": 2.9157,
|
| 49 |
+
"eval_samples_per_second": 75.112,
|
| 50 |
+
"eval_steps_per_second": 9.603,
|
| 51 |
+
"step": 41
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.44,
|
| 55 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 56 |
+
"loss": 0.5489,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.93,
|
| 61 |
+
"learning_rate": 4.722222222222222e-05,
|
| 62 |
+
"loss": 0.5258,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.98,
|
| 67 |
+
"eval_accuracy": 0.6575342465753424,
|
| 68 |
+
"eval_loss": 0.7351560592651367,
|
| 69 |
+
"eval_runtime": 3.0786,
|
| 70 |
+
"eval_samples_per_second": 71.136,
|
| 71 |
+
"eval_steps_per_second": 9.095,
|
| 72 |
+
"step": 61
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.41,
|
| 76 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 77 |
+
"loss": 0.4802,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.9,
|
| 82 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 83 |
+
"loss": 0.4436,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.0,
|
| 88 |
+
"eval_accuracy": 0.7534246575342466,
|
| 89 |
+
"eval_loss": 0.5681129097938538,
|
| 90 |
+
"eval_runtime": 2.8553,
|
| 91 |
+
"eval_samples_per_second": 76.698,
|
| 92 |
+
"eval_steps_per_second": 9.806,
|
| 93 |
+
"step": 82
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.39,
|
| 97 |
+
"learning_rate": 4.305555555555556e-05,
|
| 98 |
+
"loss": 0.4321,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.88,
|
| 103 |
+
"learning_rate": 4.166666666666667e-05,
|
| 104 |
+
"loss": 0.357,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.98,
|
| 109 |
+
"eval_accuracy": 0.7488584474885844,
|
| 110 |
+
"eval_loss": 0.591100811958313,
|
| 111 |
+
"eval_runtime": 3.0505,
|
| 112 |
+
"eval_samples_per_second": 71.791,
|
| 113 |
+
"eval_steps_per_second": 9.179,
|
| 114 |
+
"step": 102
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 5.37,
|
| 118 |
+
"learning_rate": 4.027777777777778e-05,
|
| 119 |
+
"loss": 0.3544,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.85,
|
| 124 |
+
"learning_rate": 3.888888888888889e-05,
|
| 125 |
+
"loss": 0.2805,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 6.0,
|
| 130 |
+
"eval_accuracy": 0.7671232876712328,
|
| 131 |
+
"eval_loss": 0.49708089232444763,
|
| 132 |
+
"eval_runtime": 2.9605,
|
| 133 |
+
"eval_samples_per_second": 73.975,
|
| 134 |
+
"eval_steps_per_second": 9.458,
|
| 135 |
+
"step": 123
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 6.34,
|
| 139 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 140 |
+
"loss": 0.2752,
|
| 141 |
+
"step": 130
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.83,
|
| 145 |
+
"learning_rate": 3.611111111111111e-05,
|
| 146 |
+
"loss": 0.2265,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.98,
|
| 151 |
+
"eval_accuracy": 0.7671232876712328,
|
| 152 |
+
"eval_loss": 0.5660974383354187,
|
| 153 |
+
"eval_runtime": 2.9715,
|
| 154 |
+
"eval_samples_per_second": 73.701,
|
| 155 |
+
"eval_steps_per_second": 9.423,
|
| 156 |
+
"step": 143
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 7.32,
|
| 160 |
+
"learning_rate": 3.472222222222222e-05,
|
| 161 |
+
"loss": 0.2632,
|
| 162 |
+
"step": 150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.8,
|
| 166 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 167 |
+
"loss": 0.2144,
|
| 168 |
+
"step": 160
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 8.0,
|
| 172 |
+
"eval_accuracy": 0.771689497716895,
|
| 173 |
+
"eval_loss": 0.5481449365615845,
|
| 174 |
+
"eval_runtime": 2.9379,
|
| 175 |
+
"eval_samples_per_second": 74.544,
|
| 176 |
+
"eval_steps_per_second": 9.531,
|
| 177 |
+
"step": 164
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.29,
|
| 181 |
+
"learning_rate": 3.194444444444444e-05,
|
| 182 |
+
"loss": 0.1782,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 8.78,
|
| 187 |
+
"learning_rate": 3.055555555555556e-05,
|
| 188 |
+
"loss": 0.1835,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.98,
|
| 193 |
+
"eval_accuracy": 0.7579908675799086,
|
| 194 |
+
"eval_loss": 0.5900073051452637,
|
| 195 |
+
"eval_runtime": 2.9158,
|
| 196 |
+
"eval_samples_per_second": 75.109,
|
| 197 |
+
"eval_steps_per_second": 9.603,
|
| 198 |
+
"step": 184
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 9.27,
|
| 202 |
+
"learning_rate": 2.916666666666667e-05,
|
| 203 |
+
"loss": 0.1617,
|
| 204 |
+
"step": 190
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 9.76,
|
| 208 |
+
"learning_rate": 2.777777777777778e-05,
|
| 209 |
+
"loss": 0.1843,
|
| 210 |
+
"step": 200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 10.0,
|
| 214 |
+
"eval_accuracy": 0.7808219178082192,
|
| 215 |
+
"eval_loss": 0.512748658657074,
|
| 216 |
+
"eval_runtime": 2.9167,
|
| 217 |
+
"eval_samples_per_second": 75.084,
|
| 218 |
+
"eval_steps_per_second": 9.6,
|
| 219 |
+
"step": 205
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 10.24,
|
| 223 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 224 |
+
"loss": 0.1654,
|
| 225 |
+
"step": 210
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 10.73,
|
| 229 |
+
"learning_rate": 2.5e-05,
|
| 230 |
+
"loss": 0.1671,
|
| 231 |
+
"step": 220
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.98,
|
| 235 |
+
"eval_accuracy": 0.7808219178082192,
|
| 236 |
+
"eval_loss": 0.6572665572166443,
|
| 237 |
+
"eval_runtime": 2.9745,
|
| 238 |
+
"eval_samples_per_second": 73.627,
|
| 239 |
+
"eval_steps_per_second": 9.413,
|
| 240 |
+
"step": 225
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 11.22,
|
| 244 |
+
"learning_rate": 2.361111111111111e-05,
|
| 245 |
+
"loss": 0.1803,
|
| 246 |
+
"step": 230
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 11.71,
|
| 250 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 251 |
+
"loss": 0.1492,
|
| 252 |
+
"step": 240
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 12.0,
|
| 256 |
+
"eval_accuracy": 0.7534246575342466,
|
| 257 |
+
"eval_loss": 0.6162325143814087,
|
| 258 |
+
"eval_runtime": 2.9782,
|
| 259 |
+
"eval_samples_per_second": 73.534,
|
| 260 |
+
"eval_steps_per_second": 9.402,
|
| 261 |
+
"step": 246
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 12.2,
|
| 265 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 266 |
+
"loss": 0.1101,
|
| 267 |
+
"step": 250
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 12.68,
|
| 271 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 272 |
+
"loss": 0.1155,
|
| 273 |
+
"step": 260
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.98,
|
| 277 |
+
"eval_accuracy": 0.7853881278538812,
|
| 278 |
+
"eval_loss": 0.5823199152946472,
|
| 279 |
+
"eval_runtime": 2.8881,
|
| 280 |
+
"eval_samples_per_second": 75.828,
|
| 281 |
+
"eval_steps_per_second": 9.695,
|
| 282 |
+
"step": 266
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 13.17,
|
| 286 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 287 |
+
"loss": 0.1632,
|
| 288 |
+
"step": 270
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 13.66,
|
| 292 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 293 |
+
"loss": 0.1268,
|
| 294 |
+
"step": 280
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.0,
|
| 298 |
+
"eval_accuracy": 0.7625570776255708,
|
| 299 |
+
"eval_loss": 0.6223090887069702,
|
| 300 |
+
"eval_runtime": 2.9382,
|
| 301 |
+
"eval_samples_per_second": 74.535,
|
| 302 |
+
"eval_steps_per_second": 9.53,
|
| 303 |
+
"step": 287
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 14.15,
|
| 307 |
+
"learning_rate": 1.527777777777778e-05,
|
| 308 |
+
"loss": 0.1386,
|
| 309 |
+
"step": 290
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 14.63,
|
| 313 |
+
"learning_rate": 1.388888888888889e-05,
|
| 314 |
+
"loss": 0.1405,
|
| 315 |
+
"step": 300
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 14.98,
|
| 319 |
+
"eval_accuracy": 0.7579908675799086,
|
| 320 |
+
"eval_loss": 0.6135131120681763,
|
| 321 |
+
"eval_runtime": 2.96,
|
| 322 |
+
"eval_samples_per_second": 73.987,
|
| 323 |
+
"eval_steps_per_second": 9.46,
|
| 324 |
+
"step": 307
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 15.12,
|
| 328 |
+
"learning_rate": 1.25e-05,
|
| 329 |
+
"loss": 0.094,
|
| 330 |
+
"step": 310
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 15.61,
|
| 334 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 335 |
+
"loss": 0.0656,
|
| 336 |
+
"step": 320
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 16.0,
|
| 340 |
+
"eval_accuracy": 0.7671232876712328,
|
| 341 |
+
"eval_loss": 0.6013427972793579,
|
| 342 |
+
"eval_runtime": 2.897,
|
| 343 |
+
"eval_samples_per_second": 75.595,
|
| 344 |
+
"eval_steps_per_second": 9.665,
|
| 345 |
+
"step": 328
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 16.1,
|
| 349 |
+
"learning_rate": 9.722222222222223e-06,
|
| 350 |
+
"loss": 0.1004,
|
| 351 |
+
"step": 330
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 16.59,
|
| 355 |
+
"learning_rate": 8.333333333333334e-06,
|
| 356 |
+
"loss": 0.0494,
|
| 357 |
+
"step": 340
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 16.98,
|
| 361 |
+
"eval_accuracy": 0.771689497716895,
|
| 362 |
+
"eval_loss": 0.6419550180435181,
|
| 363 |
+
"eval_runtime": 2.9336,
|
| 364 |
+
"eval_samples_per_second": 74.651,
|
| 365 |
+
"eval_steps_per_second": 9.544,
|
| 366 |
+
"step": 348
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 17.07,
|
| 370 |
+
"learning_rate": 6.944444444444445e-06,
|
| 371 |
+
"loss": 0.1044,
|
| 372 |
+
"step": 350
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 17.56,
|
| 376 |
+
"learning_rate": 5.555555555555556e-06,
|
| 377 |
+
"loss": 0.1022,
|
| 378 |
+
"step": 360
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 18.0,
|
| 382 |
+
"eval_accuracy": 0.7671232876712328,
|
| 383 |
+
"eval_loss": 0.6566610336303711,
|
| 384 |
+
"eval_runtime": 2.9773,
|
| 385 |
+
"eval_samples_per_second": 73.557,
|
| 386 |
+
"eval_steps_per_second": 9.405,
|
| 387 |
+
"step": 369
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 18.05,
|
| 391 |
+
"learning_rate": 4.166666666666667e-06,
|
| 392 |
+
"loss": 0.176,
|
| 393 |
+
"step": 370
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 18.54,
|
| 397 |
+
"learning_rate": 2.777777777777778e-06,
|
| 398 |
+
"loss": 0.0539,
|
| 399 |
+
"step": 380
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 18.98,
|
| 403 |
+
"eval_accuracy": 0.7625570776255708,
|
| 404 |
+
"eval_loss": 0.6490917205810547,
|
| 405 |
+
"eval_runtime": 3.0028,
|
| 406 |
+
"eval_samples_per_second": 72.933,
|
| 407 |
+
"eval_steps_per_second": 9.325,
|
| 408 |
+
"step": 389
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 19.02,
|
| 412 |
+
"learning_rate": 1.388888888888889e-06,
|
| 413 |
+
"loss": 0.1147,
|
| 414 |
+
"step": 390
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 19.51,
|
| 418 |
+
"learning_rate": 0.0,
|
| 419 |
+
"loss": 0.0656,
|
| 420 |
+
"step": 400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 19.51,
|
| 424 |
+
"eval_accuracy": 0.7671232876712328,
|
| 425 |
+
"eval_loss": 0.6516732573509216,
|
| 426 |
+
"eval_runtime": 2.9449,
|
| 427 |
+
"eval_samples_per_second": 74.365,
|
| 428 |
+
"eval_steps_per_second": 9.508,
|
| 429 |
+
"step": 400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 19.51,
|
| 433 |
+
"step": 400,
|
| 434 |
+
"total_flos": 9.874981246081352e+17,
|
| 435 |
+
"train_loss": 0.2905089810490608,
|
| 436 |
+
"train_runtime": 669.2028,
|
| 437 |
+
"train_samples_per_second": 19.516,
|
| 438 |
+
"train_steps_per_second": 0.598
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 10,
|
| 442 |
+
"max_steps": 400,
|
| 443 |
+
"num_train_epochs": 20,
|
| 444 |
+
"save_steps": 500,
|
| 445 |
+
"total_flos": 9.874981246081352e+17,
|
| 446 |
+
"trial_name": null,
|
| 447 |
+
"trial_params": null
|
| 448 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cdf18983468bc586bd6ae29887481df8d86466ef3a47b53357a320ebb636577
|
| 3 |
size 4600
|