End of training
Browse files- README.md +36 -36
- all_results.json +8 -8
- eval_results.json +4 -4
- model.safetensors +1 -1
- runs/Dec01_10-45-48_DESKTOP-SKBE9FB/events.out.tfevents.1733071549.DESKTOP-SKBE9FB.15824.0 +3 -0
- runs/Dec01_10-45-48_DESKTOP-SKBE9FB/events.out.tfevents.1733071679.DESKTOP-SKBE9FB.15824.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +156 -156
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -31,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
- Loss: 113.
|
| 35 |
- Accuracy: 0.1087
|
| 36 |
|
| 37 |
## Model description
|
|
@@ -66,41 +66,41 @@ The following hyperparameters were used during training:
|
|
| 66 |
|
| 67 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
-
| No log | 0.86 | 3 | 113.
|
| 70 |
-
| No log | 2.0 | 7 | 113.
|
| 71 |
-
| 114.
|
| 72 |
-
| 114.
|
| 73 |
-
| 114.
|
| 74 |
-
| 113.
|
| 75 |
-
| 113.
|
| 76 |
-
| 113.
|
| 77 |
-
| 111.
|
| 78 |
-
| 111.
|
| 79 |
-
| 111.
|
| 80 |
-
| 115.
|
| 81 |
-
| 115.
|
| 82 |
-
| 115.
|
| 83 |
-
| 111.
|
| 84 |
-
| 111.
|
| 85 |
-
| 111.
|
| 86 |
-
| 112.
|
| 87 |
-
| 112.
|
| 88 |
-
|
|
| 89 |
-
|
|
| 90 |
-
|
|
| 91 |
-
| 113.
|
| 92 |
-
| 113.
|
| 93 |
-
| 113.
|
| 94 |
-
|
|
| 95 |
-
|
|
| 96 |
-
|
|
| 97 |
-
| 111.
|
| 98 |
-
| 111.
|
| 99 |
-
| 111.
|
| 100 |
-
| 112.
|
| 101 |
-
| 112.
|
| 102 |
-
| 112.
|
| 103 |
-
| 112.
|
| 104 |
|
| 105 |
|
| 106 |
### Framework versions
|
|
|
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 113.7364
|
| 35 |
- Accuracy: 0.1087
|
| 36 |
|
| 37 |
## Model description
|
|
|
|
| 66 |
|
| 67 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| No log | 0.86 | 3 | 113.7364 | 0.1087 |
|
| 70 |
+
| No log | 2.0 | 7 | 113.7326 | 0.1087 |
|
| 71 |
+
| 114.0068 | 2.86 | 10 | 113.7256 | 0.1087 |
|
| 72 |
+
| 114.0068 | 4.0 | 14 | 113.7186 | 0.1087 |
|
| 73 |
+
| 114.0068 | 4.86 | 17 | 113.7029 | 0.1087 |
|
| 74 |
+
| 113.3375 | 6.0 | 21 | 113.6791 | 0.1087 |
|
| 75 |
+
| 113.3375 | 6.86 | 24 | 113.6215 | 0.1087 |
|
| 76 |
+
| 113.3375 | 8.0 | 28 | 113.5252 | 0.1087 |
|
| 77 |
+
| 111.4746 | 8.86 | 31 | 113.4319 | 0.1087 |
|
| 78 |
+
| 111.4746 | 10.0 | 35 | 113.3363 | 0.1087 |
|
| 79 |
+
| 111.4746 | 10.86 | 38 | 113.2650 | 0.1087 |
|
| 80 |
+
| 115.4431 | 12.0 | 42 | 113.2107 | 0.1087 |
|
| 81 |
+
| 115.4431 | 12.86 | 45 | 113.0735 | 0.1087 |
|
| 82 |
+
| 115.4431 | 14.0 | 49 | 112.9594 | 0.1087 |
|
| 83 |
+
| 111.5901 | 14.86 | 52 | 112.8571 | 0.1087 |
|
| 84 |
+
| 111.5901 | 16.0 | 56 | 112.6748 | 0.1087 |
|
| 85 |
+
| 111.5901 | 16.86 | 59 | 112.6704 | 0.1087 |
|
| 86 |
+
| 112.1751 | 18.0 | 63 | 112.6418 | 0.1087 |
|
| 87 |
+
| 112.1751 | 18.86 | 66 | 112.8373 | 0.1087 |
|
| 88 |
+
| 112.9078 | 20.0 | 70 | 112.8380 | 0.1087 |
|
| 89 |
+
| 112.9078 | 20.86 | 73 | 112.7914 | 0.1087 |
|
| 90 |
+
| 112.9078 | 22.0 | 77 | 112.5887 | 0.1087 |
|
| 91 |
+
| 113.1403 | 22.86 | 80 | 112.6198 | 0.1087 |
|
| 92 |
+
| 113.1403 | 24.0 | 84 | 112.2571 | 0.1087 |
|
| 93 |
+
| 113.1403 | 24.86 | 87 | 112.2411 | 0.1087 |
|
| 94 |
+
| 112.9338 | 26.0 | 91 | 112.1696 | 0.1087 |
|
| 95 |
+
| 112.9338 | 26.86 | 94 | 112.1566 | 0.1087 |
|
| 96 |
+
| 112.9338 | 28.0 | 98 | 112.3235 | 0.1087 |
|
| 97 |
+
| 111.1035 | 28.86 | 101 | 112.2629 | 0.1087 |
|
| 98 |
+
| 111.1035 | 30.0 | 105 | 112.0586 | 0.1087 |
|
| 99 |
+
| 111.1035 | 30.86 | 108 | 112.0911 | 0.1087 |
|
| 100 |
+
| 112.5756 | 32.0 | 112 | 112.2091 | 0.1087 |
|
| 101 |
+
| 112.5756 | 32.86 | 115 | 112.1568 | 0.1087 |
|
| 102 |
+
| 112.5756 | 34.0 | 119 | 111.8474 | 0.1087 |
|
| 103 |
+
| 112.2756 | 34.29 | 120 | 111.8630 | 0.1087 |
|
| 104 |
|
| 105 |
|
| 106 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
"eval_accuracy": 0.10869565217391304,
|
| 4 |
-
"eval_loss": 113.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"train_loss": 112.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
"eval_accuracy": 0.10869565217391304,
|
| 4 |
+
"eval_loss": 113.73644256591797,
|
| 5 |
+
"eval_runtime": 0.5946,
|
| 6 |
+
"eval_samples_per_second": 77.357,
|
| 7 |
+
"eval_steps_per_second": 5.045,
|
| 8 |
+
"train_loss": 112.74697774251302,
|
| 9 |
+
"train_runtime": 128.6494,
|
| 10 |
+
"train_samples_per_second": 66.226,
|
| 11 |
+
"train_steps_per_second": 0.933
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
"eval_accuracy": 0.10869565217391304,
|
| 4 |
-
"eval_loss": 113.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
"eval_accuracy": 0.10869565217391304,
|
| 4 |
+
"eval_loss": 113.73644256591797,
|
| 5 |
+
"eval_runtime": 0.5946,
|
| 6 |
+
"eval_samples_per_second": 77.357,
|
| 7 |
+
"eval_steps_per_second": 5.045
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12203648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37a2062fdea25c565927efa1bccc4042e6d74effa034bf445f2c9d3b5d6f1cb3
|
| 3 |
size 12203648
|
runs/Dec01_10-45-48_DESKTOP-SKBE9FB/events.out.tfevents.1733071549.DESKTOP-SKBE9FB.15824.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26fb8b33917d8c1ee88ce1e90d1e972b9e49cd9242b1e30a454d9ffc1b14d1df
|
| 3 |
+
size 17835
|
runs/Dec01_10-45-48_DESKTOP-SKBE9FB/events.out.tfevents.1733071679.DESKTOP-SKBE9FB.15824.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fadb3855185b9bcad8d72110d7ee2626579c478993a550f2c7d4bbbc94f53c6
|
| 3 |
+
size 405
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
-
"train_loss": 112.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
+
"train_loss": 112.74697774251302,
|
| 4 |
+
"train_runtime": 128.6494,
|
| 5 |
+
"train_samples_per_second": 66.226,
|
| 6 |
+
"train_steps_per_second": 0.933
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -11,398 +11,398 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.86,
|
| 13 |
"eval_accuracy": 0.10869565217391304,
|
| 14 |
-
"eval_loss": 113.
|
| 15 |
-
"eval_runtime": 0.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second": 4.
|
| 18 |
"step": 3
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
"eval_accuracy": 0.10869565217391304,
|
| 23 |
-
"eval_loss": 113.
|
| 24 |
-
"eval_runtime": 0.
|
| 25 |
-
"eval_samples_per_second":
|
| 26 |
-
"eval_steps_per_second": 4.
|
| 27 |
"step": 7
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 2.86,
|
| 31 |
"learning_rate": 0.000125,
|
| 32 |
-
"loss": 114.
|
| 33 |
"step": 10
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 2.86,
|
| 37 |
"eval_accuracy": 0.10869565217391304,
|
| 38 |
-
"eval_loss": 113.
|
| 39 |
-
"eval_runtime": 0.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second":
|
| 42 |
"step": 10
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 4.0,
|
| 46 |
"eval_accuracy": 0.10869565217391304,
|
| 47 |
-
"eval_loss": 113.
|
| 48 |
-
"eval_runtime": 0.
|
| 49 |
-
"eval_samples_per_second":
|
| 50 |
-
"eval_steps_per_second":
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 4.86,
|
| 55 |
"eval_accuracy": 0.10869565217391304,
|
| 56 |
-
"eval_loss": 113.
|
| 57 |
-
"eval_runtime": 0.
|
| 58 |
-
"eval_samples_per_second":
|
| 59 |
-
"eval_steps_per_second":
|
| 60 |
"step": 17
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 5.71,
|
| 64 |
"learning_rate": 0.0001388888888888889,
|
| 65 |
-
"loss": 113.
|
| 66 |
"step": 20
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 6.0,
|
| 70 |
"eval_accuracy": 0.10869565217391304,
|
| 71 |
-
"eval_loss": 113.
|
| 72 |
-
"eval_runtime": 0.
|
| 73 |
-
"eval_samples_per_second":
|
| 74 |
-
"eval_steps_per_second":
|
| 75 |
"step": 21
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 6.86,
|
| 79 |
"eval_accuracy": 0.10869565217391304,
|
| 80 |
-
"eval_loss": 113.
|
| 81 |
-
"eval_runtime": 0.
|
| 82 |
-
"eval_samples_per_second":
|
| 83 |
-
"eval_steps_per_second":
|
| 84 |
"step": 24
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 8.0,
|
| 88 |
"eval_accuracy": 0.10869565217391304,
|
| 89 |
-
"eval_loss": 113.
|
| 90 |
-
"eval_runtime": 0.
|
| 91 |
-
"eval_samples_per_second":
|
| 92 |
-
"eval_steps_per_second":
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 8.57,
|
| 97 |
"learning_rate": 0.000125,
|
| 98 |
-
"loss": 111.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 8.86,
|
| 103 |
"eval_accuracy": 0.10869565217391304,
|
| 104 |
-
"eval_loss": 113.
|
| 105 |
-
"eval_runtime": 0.
|
| 106 |
-
"eval_samples_per_second":
|
| 107 |
-
"eval_steps_per_second": 4.
|
| 108 |
"step": 31
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 10.0,
|
| 112 |
"eval_accuracy": 0.10869565217391304,
|
| 113 |
-
"eval_loss": 113.
|
| 114 |
-
"eval_runtime": 0.
|
| 115 |
-
"eval_samples_per_second":
|
| 116 |
-
"eval_steps_per_second": 4.
|
| 117 |
"step": 35
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 10.86,
|
| 121 |
"eval_accuracy": 0.10869565217391304,
|
| 122 |
-
"eval_loss": 113.
|
| 123 |
-
"eval_runtime": 0.
|
| 124 |
-
"eval_samples_per_second":
|
| 125 |
-
"eval_steps_per_second":
|
| 126 |
"step": 38
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 11.43,
|
| 130 |
"learning_rate": 0.00011111111111111109,
|
| 131 |
-
"loss": 115.
|
| 132 |
"step": 40
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 12.0,
|
| 136 |
"eval_accuracy": 0.10869565217391304,
|
| 137 |
-
"eval_loss": 113.
|
| 138 |
-
"eval_runtime": 0.
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second": 4.
|
| 141 |
"step": 42
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 12.86,
|
| 145 |
"eval_accuracy": 0.10869565217391304,
|
| 146 |
-
"eval_loss": 113.
|
| 147 |
-
"eval_runtime": 0.
|
| 148 |
-
"eval_samples_per_second":
|
| 149 |
-
"eval_steps_per_second": 4.
|
| 150 |
"step": 45
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 14.0,
|
| 154 |
"eval_accuracy": 0.10869565217391304,
|
| 155 |
-
"eval_loss":
|
| 156 |
-
"eval_runtime": 0.
|
| 157 |
-
"eval_samples_per_second":
|
| 158 |
-
"eval_steps_per_second":
|
| 159 |
"step": 49
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 14.29,
|
| 163 |
"learning_rate": 9.722222222222222e-05,
|
| 164 |
-
"loss": 111.
|
| 165 |
"step": 50
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 14.86,
|
| 169 |
"eval_accuracy": 0.10869565217391304,
|
| 170 |
-
"eval_loss":
|
| 171 |
-
"eval_runtime": 0.
|
| 172 |
-
"eval_samples_per_second":
|
| 173 |
-
"eval_steps_per_second":
|
| 174 |
"step": 52
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 16.0,
|
| 178 |
"eval_accuracy": 0.10869565217391304,
|
| 179 |
-
"eval_loss": 112.
|
| 180 |
-
"eval_runtime": 0.
|
| 181 |
-
"eval_samples_per_second":
|
| 182 |
-
"eval_steps_per_second": 4.
|
| 183 |
"step": 56
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 16.86,
|
| 187 |
"eval_accuracy": 0.10869565217391304,
|
| 188 |
-
"eval_loss": 112.
|
| 189 |
-
"eval_runtime": 0.
|
| 190 |
-
"eval_samples_per_second":
|
| 191 |
-
"eval_steps_per_second":
|
| 192 |
"step": 59
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 17.14,
|
| 196 |
"learning_rate": 8.333333333333333e-05,
|
| 197 |
-
"loss": 112.
|
| 198 |
"step": 60
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 18.0,
|
| 202 |
"eval_accuracy": 0.10869565217391304,
|
| 203 |
-
"eval_loss": 112.
|
| 204 |
-
"eval_runtime": 0.
|
| 205 |
-
"eval_samples_per_second":
|
| 206 |
-
"eval_steps_per_second":
|
| 207 |
"step": 63
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 18.86,
|
| 211 |
"eval_accuracy": 0.10869565217391304,
|
| 212 |
-
"eval_loss":
|
| 213 |
-
"eval_runtime": 0.
|
| 214 |
-
"eval_samples_per_second":
|
| 215 |
-
"eval_steps_per_second":
|
| 216 |
"step": 66
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 20.0,
|
| 220 |
"learning_rate": 6.944444444444444e-05,
|
| 221 |
-
"loss":
|
| 222 |
"step": 70
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 20.0,
|
| 226 |
"eval_accuracy": 0.10869565217391304,
|
| 227 |
-
"eval_loss":
|
| 228 |
-
"eval_runtime": 0.
|
| 229 |
-
"eval_samples_per_second":
|
| 230 |
-
"eval_steps_per_second": 4.
|
| 231 |
"step": 70
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 20.86,
|
| 235 |
"eval_accuracy": 0.10869565217391304,
|
| 236 |
-
"eval_loss": 112.
|
| 237 |
-
"eval_runtime": 0.
|
| 238 |
-
"eval_samples_per_second":
|
| 239 |
-
"eval_steps_per_second": 4.
|
| 240 |
"step": 73
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 22.0,
|
| 244 |
"eval_accuracy": 0.10869565217391304,
|
| 245 |
-
"eval_loss": 112.
|
| 246 |
-
"eval_runtime": 0.
|
| 247 |
-
"eval_samples_per_second":
|
| 248 |
-
"eval_steps_per_second":
|
| 249 |
"step": 77
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 22.86,
|
| 253 |
"learning_rate": 5.5555555555555545e-05,
|
| 254 |
-
"loss": 113.
|
| 255 |
"step": 80
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 22.86,
|
| 259 |
"eval_accuracy": 0.10869565217391304,
|
| 260 |
-
"eval_loss": 112.
|
| 261 |
-
"eval_runtime": 0.
|
| 262 |
-
"eval_samples_per_second": 74.
|
| 263 |
-
"eval_steps_per_second": 4.
|
| 264 |
"step": 80
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 24.0,
|
| 268 |
"eval_accuracy": 0.10869565217391304,
|
| 269 |
-
"eval_loss": 112.
|
| 270 |
-
"eval_runtime": 0.
|
| 271 |
-
"eval_samples_per_second":
|
| 272 |
-
"eval_steps_per_second": 4.
|
| 273 |
"step": 84
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 24.86,
|
| 277 |
"eval_accuracy": 0.10869565217391304,
|
| 278 |
-
"eval_loss": 112.
|
| 279 |
-
"eval_runtime": 0.
|
| 280 |
-
"eval_samples_per_second":
|
| 281 |
-
"eval_steps_per_second":
|
| 282 |
"step": 87
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 25.71,
|
| 286 |
"learning_rate": 4.1666666666666665e-05,
|
| 287 |
-
"loss":
|
| 288 |
"step": 90
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 26.0,
|
| 292 |
"eval_accuracy": 0.10869565217391304,
|
| 293 |
-
"eval_loss": 112.
|
| 294 |
-
"eval_runtime": 0.
|
| 295 |
-
"eval_samples_per_second":
|
| 296 |
-
"eval_steps_per_second": 4.
|
| 297 |
"step": 91
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 26.86,
|
| 301 |
"eval_accuracy": 0.10869565217391304,
|
| 302 |
-
"eval_loss": 112.
|
| 303 |
-
"eval_runtime": 0.
|
| 304 |
-
"eval_samples_per_second":
|
| 305 |
-
"eval_steps_per_second": 4.
|
| 306 |
"step": 94
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 28.0,
|
| 310 |
"eval_accuracy": 0.10869565217391304,
|
| 311 |
-
"eval_loss": 112.
|
| 312 |
-
"eval_runtime": 0.
|
| 313 |
-
"eval_samples_per_second":
|
| 314 |
-
"eval_steps_per_second":
|
| 315 |
"step": 98
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 28.57,
|
| 319 |
"learning_rate": 2.7777777777777772e-05,
|
| 320 |
-
"loss": 111.
|
| 321 |
"step": 100
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 28.86,
|
| 325 |
"eval_accuracy": 0.10869565217391304,
|
| 326 |
-
"eval_loss": 112.
|
| 327 |
-
"eval_runtime": 0.
|
| 328 |
-
"eval_samples_per_second":
|
| 329 |
-
"eval_steps_per_second":
|
| 330 |
"step": 101
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 30.0,
|
| 334 |
"eval_accuracy": 0.10869565217391304,
|
| 335 |
-
"eval_loss": 112.
|
| 336 |
-
"eval_runtime": 0.
|
| 337 |
-
"eval_samples_per_second":
|
| 338 |
-
"eval_steps_per_second": 4.
|
| 339 |
"step": 105
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 30.86,
|
| 343 |
"eval_accuracy": 0.10869565217391304,
|
| 344 |
-
"eval_loss": 112.
|
| 345 |
-
"eval_runtime": 0.
|
| 346 |
-
"eval_samples_per_second":
|
| 347 |
-
"eval_steps_per_second":
|
| 348 |
"step": 108
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 31.43,
|
| 352 |
"learning_rate": 1.3888888888888886e-05,
|
| 353 |
-
"loss": 112.
|
| 354 |
"step": 110
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 32.0,
|
| 358 |
"eval_accuracy": 0.10869565217391304,
|
| 359 |
-
"eval_loss": 112.
|
| 360 |
-
"eval_runtime": 0.
|
| 361 |
-
"eval_samples_per_second":
|
| 362 |
-
"eval_steps_per_second": 4.
|
| 363 |
"step": 112
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 32.86,
|
| 367 |
"eval_accuracy": 0.10869565217391304,
|
| 368 |
-
"eval_loss": 112.
|
| 369 |
-
"eval_runtime": 0.
|
| 370 |
-
"eval_samples_per_second": 74.
|
| 371 |
-
"eval_steps_per_second": 4.
|
| 372 |
"step": 115
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 34.0,
|
| 376 |
"eval_accuracy": 0.10869565217391304,
|
| 377 |
-
"eval_loss":
|
| 378 |
-
"eval_runtime": 0.
|
| 379 |
-
"eval_samples_per_second":
|
| 380 |
-
"eval_steps_per_second":
|
| 381 |
"step": 119
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 34.29,
|
| 385 |
"learning_rate": 0.0,
|
| 386 |
-
"loss": 112.
|
| 387 |
"step": 120
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 34.29,
|
| 391 |
"eval_accuracy": 0.10869565217391304,
|
| 392 |
-
"eval_loss":
|
| 393 |
-
"eval_runtime": 0.
|
| 394 |
-
"eval_samples_per_second":
|
| 395 |
-
"eval_steps_per_second":
|
| 396 |
"step": 120
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 34.29,
|
| 400 |
"step": 120,
|
| 401 |
"total_flos": 2.0027429927092224e+16,
|
| 402 |
-
"train_loss": 112.
|
| 403 |
-
"train_runtime":
|
| 404 |
-
"train_samples_per_second":
|
| 405 |
-
"train_steps_per_second": 0.
|
| 406 |
}
|
| 407 |
],
|
| 408 |
"logging_steps": 10,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.86,
|
| 13 |
"eval_accuracy": 0.10869565217391304,
|
| 14 |
+
"eval_loss": 113.73644256591797,
|
| 15 |
+
"eval_runtime": 0.6432,
|
| 16 |
+
"eval_samples_per_second": 71.522,
|
| 17 |
+
"eval_steps_per_second": 4.664,
|
| 18 |
"step": 3
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
"eval_accuracy": 0.10869565217391304,
|
| 23 |
+
"eval_loss": 113.73255157470703,
|
| 24 |
+
"eval_runtime": 0.6031,
|
| 25 |
+
"eval_samples_per_second": 76.268,
|
| 26 |
+
"eval_steps_per_second": 4.974,
|
| 27 |
"step": 7
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 2.86,
|
| 31 |
"learning_rate": 0.000125,
|
| 32 |
+
"loss": 114.0068,
|
| 33 |
"step": 10
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 2.86,
|
| 37 |
"eval_accuracy": 0.10869565217391304,
|
| 38 |
+
"eval_loss": 113.72559356689453,
|
| 39 |
+
"eval_runtime": 0.8182,
|
| 40 |
+
"eval_samples_per_second": 56.221,
|
| 41 |
+
"eval_steps_per_second": 3.667,
|
| 42 |
"step": 10
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 4.0,
|
| 46 |
"eval_accuracy": 0.10869565217391304,
|
| 47 |
+
"eval_loss": 113.71858215332031,
|
| 48 |
+
"eval_runtime": 0.5882,
|
| 49 |
+
"eval_samples_per_second": 78.211,
|
| 50 |
+
"eval_steps_per_second": 5.101,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 4.86,
|
| 55 |
"eval_accuracy": 0.10869565217391304,
|
| 56 |
+
"eval_loss": 113.7029037475586,
|
| 57 |
+
"eval_runtime": 0.5851,
|
| 58 |
+
"eval_samples_per_second": 78.615,
|
| 59 |
+
"eval_steps_per_second": 5.127,
|
| 60 |
"step": 17
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 5.71,
|
| 64 |
"learning_rate": 0.0001388888888888889,
|
| 65 |
+
"loss": 113.3375,
|
| 66 |
"step": 20
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 6.0,
|
| 70 |
"eval_accuracy": 0.10869565217391304,
|
| 71 |
+
"eval_loss": 113.67913818359375,
|
| 72 |
+
"eval_runtime": 0.5952,
|
| 73 |
+
"eval_samples_per_second": 77.291,
|
| 74 |
+
"eval_steps_per_second": 5.041,
|
| 75 |
"step": 21
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 6.86,
|
| 79 |
"eval_accuracy": 0.10869565217391304,
|
| 80 |
+
"eval_loss": 113.62146759033203,
|
| 81 |
+
"eval_runtime": 0.5841,
|
| 82 |
+
"eval_samples_per_second": 78.749,
|
| 83 |
+
"eval_steps_per_second": 5.136,
|
| 84 |
"step": 24
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 8.0,
|
| 88 |
"eval_accuracy": 0.10869565217391304,
|
| 89 |
+
"eval_loss": 113.5252456665039,
|
| 90 |
+
"eval_runtime": 0.5881,
|
| 91 |
+
"eval_samples_per_second": 78.214,
|
| 92 |
+
"eval_steps_per_second": 5.101,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 8.57,
|
| 97 |
"learning_rate": 0.000125,
|
| 98 |
+
"loss": 111.4746,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 8.86,
|
| 103 |
"eval_accuracy": 0.10869565217391304,
|
| 104 |
+
"eval_loss": 113.43194580078125,
|
| 105 |
+
"eval_runtime": 0.6071,
|
| 106 |
+
"eval_samples_per_second": 75.766,
|
| 107 |
+
"eval_steps_per_second": 4.941,
|
| 108 |
"step": 31
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 10.0,
|
| 112 |
"eval_accuracy": 0.10869565217391304,
|
| 113 |
+
"eval_loss": 113.33634948730469,
|
| 114 |
+
"eval_runtime": 0.7002,
|
| 115 |
+
"eval_samples_per_second": 65.698,
|
| 116 |
+
"eval_steps_per_second": 4.285,
|
| 117 |
"step": 35
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 10.86,
|
| 121 |
"eval_accuracy": 0.10869565217391304,
|
| 122 |
+
"eval_loss": 113.2650375366211,
|
| 123 |
+
"eval_runtime": 0.5971,
|
| 124 |
+
"eval_samples_per_second": 77.035,
|
| 125 |
+
"eval_steps_per_second": 5.024,
|
| 126 |
"step": 38
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 11.43,
|
| 130 |
"learning_rate": 0.00011111111111111109,
|
| 131 |
+
"loss": 115.4431,
|
| 132 |
"step": 40
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 12.0,
|
| 136 |
"eval_accuracy": 0.10869565217391304,
|
| 137 |
+
"eval_loss": 113.21066284179688,
|
| 138 |
+
"eval_runtime": 0.6032,
|
| 139 |
+
"eval_samples_per_second": 76.266,
|
| 140 |
+
"eval_steps_per_second": 4.974,
|
| 141 |
"step": 42
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 12.86,
|
| 145 |
"eval_accuracy": 0.10869565217391304,
|
| 146 |
+
"eval_loss": 113.073486328125,
|
| 147 |
+
"eval_runtime": 0.6161,
|
| 148 |
+
"eval_samples_per_second": 74.659,
|
| 149 |
+
"eval_steps_per_second": 4.869,
|
| 150 |
"step": 45
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 14.0,
|
| 154 |
"eval_accuracy": 0.10869565217391304,
|
| 155 |
+
"eval_loss": 112.95938873291016,
|
| 156 |
+
"eval_runtime": 0.5966,
|
| 157 |
+
"eval_samples_per_second": 77.098,
|
| 158 |
+
"eval_steps_per_second": 5.028,
|
| 159 |
"step": 49
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 14.29,
|
| 163 |
"learning_rate": 9.722222222222222e-05,
|
| 164 |
+
"loss": 111.5901,
|
| 165 |
"step": 50
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 14.86,
|
| 169 |
"eval_accuracy": 0.10869565217391304,
|
| 170 |
+
"eval_loss": 112.85713195800781,
|
| 171 |
+
"eval_runtime": 0.5917,
|
| 172 |
+
"eval_samples_per_second": 77.748,
|
| 173 |
+
"eval_steps_per_second": 5.071,
|
| 174 |
"step": 52
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 16.0,
|
| 178 |
"eval_accuracy": 0.10869565217391304,
|
| 179 |
+
"eval_loss": 112.6748275756836,
|
| 180 |
+
"eval_runtime": 0.6246,
|
| 181 |
+
"eval_samples_per_second": 73.641,
|
| 182 |
+
"eval_steps_per_second": 4.803,
|
| 183 |
"step": 56
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 16.86,
|
| 187 |
"eval_accuracy": 0.10869565217391304,
|
| 188 |
+
"eval_loss": 112.67044067382812,
|
| 189 |
+
"eval_runtime": 0.5956,
|
| 190 |
+
"eval_samples_per_second": 77.227,
|
| 191 |
+
"eval_steps_per_second": 5.037,
|
| 192 |
"step": 59
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 17.14,
|
| 196 |
"learning_rate": 8.333333333333333e-05,
|
| 197 |
+
"loss": 112.1751,
|
| 198 |
"step": 60
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 18.0,
|
| 202 |
"eval_accuracy": 0.10869565217391304,
|
| 203 |
+
"eval_loss": 112.64176177978516,
|
| 204 |
+
"eval_runtime": 0.5781,
|
| 205 |
+
"eval_samples_per_second": 79.567,
|
| 206 |
+
"eval_steps_per_second": 5.189,
|
| 207 |
"step": 63
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 18.86,
|
| 211 |
"eval_accuracy": 0.10869565217391304,
|
| 212 |
+
"eval_loss": 112.83734130859375,
|
| 213 |
+
"eval_runtime": 0.5902,
|
| 214 |
+
"eval_samples_per_second": 77.946,
|
| 215 |
+
"eval_steps_per_second": 5.083,
|
| 216 |
"step": 66
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 20.0,
|
| 220 |
"learning_rate": 6.944444444444444e-05,
|
| 221 |
+
"loss": 112.9078,
|
| 222 |
"step": 70
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 20.0,
|
| 226 |
"eval_accuracy": 0.10869565217391304,
|
| 227 |
+
"eval_loss": 112.83795166015625,
|
| 228 |
+
"eval_runtime": 0.6191,
|
| 229 |
+
"eval_samples_per_second": 74.297,
|
| 230 |
+
"eval_steps_per_second": 4.845,
|
| 231 |
"step": 70
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 20.86,
|
| 235 |
"eval_accuracy": 0.10869565217391304,
|
| 236 |
+
"eval_loss": 112.79137420654297,
|
| 237 |
+
"eval_runtime": 0.6136,
|
| 238 |
+
"eval_samples_per_second": 74.962,
|
| 239 |
+
"eval_steps_per_second": 4.889,
|
| 240 |
"step": 73
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 22.0,
|
| 244 |
"eval_accuracy": 0.10869565217391304,
|
| 245 |
+
"eval_loss": 112.58869934082031,
|
| 246 |
+
"eval_runtime": 0.5846,
|
| 247 |
+
"eval_samples_per_second": 78.681,
|
| 248 |
+
"eval_steps_per_second": 5.131,
|
| 249 |
"step": 77
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 22.86,
|
| 253 |
"learning_rate": 5.5555555555555545e-05,
|
| 254 |
+
"loss": 113.1403,
|
| 255 |
"step": 80
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 22.86,
|
| 259 |
"eval_accuracy": 0.10869565217391304,
|
| 260 |
+
"eval_loss": 112.61984252929688,
|
| 261 |
+
"eval_runtime": 0.6196,
|
| 262 |
+
"eval_samples_per_second": 74.236,
|
| 263 |
+
"eval_steps_per_second": 4.841,
|
| 264 |
"step": 80
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 24.0,
|
| 268 |
"eval_accuracy": 0.10869565217391304,
|
| 269 |
+
"eval_loss": 112.25711059570312,
|
| 270 |
+
"eval_runtime": 0.6051,
|
| 271 |
+
"eval_samples_per_second": 76.016,
|
| 272 |
+
"eval_steps_per_second": 4.958,
|
| 273 |
"step": 84
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 24.86,
|
| 277 |
"eval_accuracy": 0.10869565217391304,
|
| 278 |
+
"eval_loss": 112.2410659790039,
|
| 279 |
+
"eval_runtime": 0.5831,
|
| 280 |
+
"eval_samples_per_second": 78.884,
|
| 281 |
+
"eval_steps_per_second": 5.145,
|
| 282 |
"step": 87
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 25.71,
|
| 286 |
"learning_rate": 4.1666666666666665e-05,
|
| 287 |
+
"loss": 112.9338,
|
| 288 |
"step": 90
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 26.0,
|
| 292 |
"eval_accuracy": 0.10869565217391304,
|
| 293 |
+
"eval_loss": 112.16959381103516,
|
| 294 |
+
"eval_runtime": 0.6226,
|
| 295 |
+
"eval_samples_per_second": 73.878,
|
| 296 |
+
"eval_steps_per_second": 4.818,
|
| 297 |
"step": 91
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 26.86,
|
| 301 |
"eval_accuracy": 0.10869565217391304,
|
| 302 |
+
"eval_loss": 112.15655517578125,
|
| 303 |
+
"eval_runtime": 0.6151,
|
| 304 |
+
"eval_samples_per_second": 74.78,
|
| 305 |
+
"eval_steps_per_second": 4.877,
|
| 306 |
"step": 94
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 28.0,
|
| 310 |
"eval_accuracy": 0.10869565217391304,
|
| 311 |
+
"eval_loss": 112.32354736328125,
|
| 312 |
+
"eval_runtime": 0.5866,
|
| 313 |
+
"eval_samples_per_second": 78.413,
|
| 314 |
+
"eval_steps_per_second": 5.114,
|
| 315 |
"step": 98
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 28.57,
|
| 319 |
"learning_rate": 2.7777777777777772e-05,
|
| 320 |
+
"loss": 111.1035,
|
| 321 |
"step": 100
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 28.86,
|
| 325 |
"eval_accuracy": 0.10869565217391304,
|
| 326 |
+
"eval_loss": 112.26287841796875,
|
| 327 |
+
"eval_runtime": 0.5856,
|
| 328 |
+
"eval_samples_per_second": 78.547,
|
| 329 |
+
"eval_steps_per_second": 5.123,
|
| 330 |
"step": 101
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 30.0,
|
| 334 |
"eval_accuracy": 0.10869565217391304,
|
| 335 |
+
"eval_loss": 112.05860137939453,
|
| 336 |
+
"eval_runtime": 0.6191,
|
| 337 |
+
"eval_samples_per_second": 74.297,
|
| 338 |
+
"eval_steps_per_second": 4.845,
|
| 339 |
"step": 105
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 30.86,
|
| 343 |
"eval_accuracy": 0.10869565217391304,
|
| 344 |
+
"eval_loss": 112.09107208251953,
|
| 345 |
+
"eval_runtime": 0.5961,
|
| 346 |
+
"eval_samples_per_second": 77.164,
|
| 347 |
+
"eval_steps_per_second": 5.032,
|
| 348 |
"step": 108
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 31.43,
|
| 352 |
"learning_rate": 1.3888888888888886e-05,
|
| 353 |
+
"loss": 112.5756,
|
| 354 |
"step": 110
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 32.0,
|
| 358 |
"eval_accuracy": 0.10869565217391304,
|
| 359 |
+
"eval_loss": 112.2091293334961,
|
| 360 |
+
"eval_runtime": 0.6056,
|
| 361 |
+
"eval_samples_per_second": 75.952,
|
| 362 |
+
"eval_steps_per_second": 4.953,
|
| 363 |
"step": 112
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 32.86,
|
| 367 |
"eval_accuracy": 0.10869565217391304,
|
| 368 |
+
"eval_loss": 112.1567611694336,
|
| 369 |
+
"eval_runtime": 0.6136,
|
| 370 |
+
"eval_samples_per_second": 74.962,
|
| 371 |
+
"eval_steps_per_second": 4.889,
|
| 372 |
"step": 115
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 34.0,
|
| 376 |
"eval_accuracy": 0.10869565217391304,
|
| 377 |
+
"eval_loss": 111.84735870361328,
|
| 378 |
+
"eval_runtime": 0.5926,
|
| 379 |
+
"eval_samples_per_second": 77.618,
|
| 380 |
+
"eval_steps_per_second": 5.062,
|
| 381 |
"step": 119
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 34.29,
|
| 385 |
"learning_rate": 0.0,
|
| 386 |
+
"loss": 112.2756,
|
| 387 |
"step": 120
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 34.29,
|
| 391 |
"eval_accuracy": 0.10869565217391304,
|
| 392 |
+
"eval_loss": 111.86297607421875,
|
| 393 |
+
"eval_runtime": 0.5896,
|
| 394 |
+
"eval_samples_per_second": 78.014,
|
| 395 |
+
"eval_steps_per_second": 5.088,
|
| 396 |
"step": 120
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 34.29,
|
| 400 |
"step": 120,
|
| 401 |
"total_flos": 2.0027429927092224e+16,
|
| 402 |
+
"train_loss": 112.74697774251302,
|
| 403 |
+
"train_runtime": 128.6494,
|
| 404 |
+
"train_samples_per_second": 66.226,
|
| 405 |
+
"train_steps_per_second": 0.933
|
| 406 |
}
|
| 407 |
],
|
| 408 |
"logging_steps": 10,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3167ae056426e39cedb2d2abec62f92123cfad39beb1fe893e34fb5f5a3a4aa2
|
| 3 |
size 4728
|