End of training
Browse files- README.md +37 -37
- all_results.json +8 -8
- eval_results.json +4 -4
- model.safetensors +1 -1
- runs/Dec02_10-23-47_DESKTOP-SKBE9FB/events.out.tfevents.1733156627.DESKTOP-SKBE9FB.19684.0 +3 -0
- runs/Dec02_10-23-47_DESKTOP-SKBE9FB/events.out.tfevents.1733156758.DESKTOP-SKBE9FB.19684.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +167 -167
- 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
|
|
@@ -51,7 +51,7 @@ More information needed
|
|
| 51 |
### Training hyperparameters
|
| 52 |
|
| 53 |
The following hyperparameters were used during training:
|
| 54 |
-
- learning_rate:
|
| 55 |
- train_batch_size: 16
|
| 56 |
- eval_batch_size: 16
|
| 57 |
- seed: 42
|
|
@@ -65,41 +65,41 @@ The following hyperparameters were used during training:
|
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
-
| No log | 0.86 | 3 | 113.
|
| 69 |
-
| No log | 2.0 | 7 | 113.
|
| 70 |
-
| 114.
|
| 71 |
-
| 114.
|
| 72 |
-
| 114.
|
| 73 |
-
| 113.
|
| 74 |
-
| 113.
|
| 75 |
-
| 113.
|
| 76 |
-
| 111.
|
| 77 |
-
| 111.
|
| 78 |
-
| 111.
|
| 79 |
-
|
|
| 80 |
-
|
|
| 81 |
-
|
|
| 82 |
-
|
|
| 83 |
-
|
|
| 84 |
-
|
|
| 85 |
-
|
|
| 86 |
-
|
|
| 87 |
-
|
|
| 88 |
-
|
|
| 89 |
-
|
|
| 90 |
-
|
|
| 91 |
-
|
|
| 92 |
-
|
|
| 93 |
-
|
|
| 94 |
-
|
|
| 95 |
-
|
|
| 96 |
-
|
|
| 97 |
-
|
|
| 98 |
-
|
|
| 99 |
-
|
|
| 100 |
-
|
|
| 101 |
-
|
|
| 102 |
-
|
|
| 103 |
|
| 104 |
|
| 105 |
### 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: 113.8883
|
| 35 |
- Accuracy: 0.1087
|
| 36 |
|
| 37 |
## Model description
|
|
|
|
| 51 |
### Training hyperparameters
|
| 52 |
|
| 53 |
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 2.5e-05
|
| 55 |
- train_batch_size: 16
|
| 56 |
- eval_batch_size: 16
|
| 57 |
- seed: 42
|
|
|
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| No log | 0.86 | 3 | 113.8883 | 0.1087 |
|
| 69 |
+
| No log | 2.0 | 7 | 113.8868 | 0.1087 |
|
| 70 |
+
| 114.1606 | 2.86 | 10 | 113.8851 | 0.1087 |
|
| 71 |
+
| 114.1606 | 4.0 | 14 | 113.8846 | 0.1087 |
|
| 72 |
+
| 114.1606 | 4.86 | 17 | 113.8832 | 0.1087 |
|
| 73 |
+
| 113.5172 | 6.0 | 21 | 113.8808 | 0.1087 |
|
| 74 |
+
| 113.5172 | 6.86 | 24 | 113.8795 | 0.1087 |
|
| 75 |
+
| 113.5172 | 8.0 | 28 | 113.8794 | 0.1087 |
|
| 76 |
+
| 111.7557 | 8.86 | 31 | 113.8766 | 0.1087 |
|
| 77 |
+
| 111.7557 | 10.0 | 35 | 113.8747 | 0.1087 |
|
| 78 |
+
| 111.7557 | 10.86 | 38 | 113.8735 | 0.1087 |
|
| 79 |
+
| 115.9434 | 12.0 | 42 | 113.8712 | 0.1087 |
|
| 80 |
+
| 115.9434 | 12.86 | 45 | 113.8699 | 0.1087 |
|
| 81 |
+
| 115.9434 | 14.0 | 49 | 113.8671 | 0.1087 |
|
| 82 |
+
| 112.3427 | 14.86 | 52 | 113.8607 | 0.1087 |
|
| 83 |
+
| 112.3427 | 16.0 | 56 | 113.8567 | 0.1087 |
|
| 84 |
+
| 112.3427 | 16.86 | 59 | 113.8570 | 0.1087 |
|
| 85 |
+
| 113.2123 | 18.0 | 63 | 113.8532 | 0.1087 |
|
| 86 |
+
| 113.2123 | 18.86 | 66 | 113.8511 | 0.1087 |
|
| 87 |
+
| 114.0835 | 20.0 | 70 | 113.8500 | 0.1087 |
|
| 88 |
+
| 114.0835 | 20.86 | 73 | 113.8469 | 0.1087 |
|
| 89 |
+
| 114.0835 | 22.0 | 77 | 113.8450 | 0.1087 |
|
| 90 |
+
| 114.5528 | 22.86 | 80 | 113.8422 | 0.1087 |
|
| 91 |
+
| 114.5528 | 24.0 | 84 | 113.8341 | 0.1087 |
|
| 92 |
+
| 114.5528 | 24.86 | 87 | 113.8315 | 0.1087 |
|
| 93 |
+
| 114.5432 | 26.0 | 91 | 113.8268 | 0.1087 |
|
| 94 |
+
| 114.5432 | 26.86 | 94 | 113.8247 | 0.1087 |
|
| 95 |
+
| 114.5432 | 28.0 | 98 | 113.8250 | 0.1087 |
|
| 96 |
+
| 112.7825 | 28.86 | 101 | 113.8207 | 0.1087 |
|
| 97 |
+
| 112.7825 | 30.0 | 105 | 113.8155 | 0.1087 |
|
| 98 |
+
| 112.7825 | 30.86 | 108 | 113.8183 | 0.1087 |
|
| 99 |
+
| 114.2965 | 32.0 | 112 | 113.8187 | 0.1087 |
|
| 100 |
+
| 114.2965 | 32.86 | 115 | 113.8187 | 0.1087 |
|
| 101 |
+
| 114.2965 | 34.0 | 119 | 113.8124 | 0.1087 |
|
| 102 |
+
| 114.0925 | 34.29 | 120 | 113.8146 | 0.1087 |
|
| 103 |
|
| 104 |
|
| 105 |
### 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": 72.
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
-
"train_loss":
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second": 65.
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
"eval_accuracy": 0.10869565217391304,
|
| 4 |
+
"eval_loss": 113.88832092285156,
|
| 5 |
+
"eval_runtime": 0.6376,
|
| 6 |
+
"eval_samples_per_second": 72.14,
|
| 7 |
+
"eval_steps_per_second": 4.705,
|
| 8 |
+
"train_loss": 113.7735809326172,
|
| 9 |
+
"train_runtime": 129.8431,
|
| 10 |
+
"train_samples_per_second": 65.618,
|
| 11 |
+
"train_steps_per_second": 0.924
|
| 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": 72.
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
"eval_accuracy": 0.10869565217391304,
|
| 4 |
+
"eval_loss": 113.88832092285156,
|
| 5 |
+
"eval_runtime": 0.6376,
|
| 6 |
+
"eval_samples_per_second": 72.14,
|
| 7 |
+
"eval_steps_per_second": 4.705
|
| 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:fd253f136dfe3348ed3c408b8e3c4cb2dc70ebcd178addaee7cca00fdd69500d
|
| 3 |
size 12203648
|
runs/Dec02_10-23-47_DESKTOP-SKBE9FB/events.out.tfevents.1733156627.DESKTOP-SKBE9FB.19684.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:758bb3a53546fefa16d401a1e735a5aa3c003ee380b1d3c0f92bfcd95b5797fe
|
| 3 |
+
size 17833
|
runs/Dec02_10-23-47_DESKTOP-SKBE9FB/events.out.tfevents.1733156758.DESKTOP-SKBE9FB.19684.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c07ec804dac672b35cde8e400e8f120932d2866340da6bd2d5add429a4f2d13
|
| 3 |
+
size 405
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second": 65.
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 34.29,
|
| 3 |
+
"train_loss": 113.7735809326172,
|
| 4 |
+
"train_runtime": 129.8431,
|
| 5 |
+
"train_samples_per_second": 65.618,
|
| 6 |
+
"train_steps_per_second": 0.924
|
| 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": 5.
|
| 27 |
"step": 7
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 2.86,
|
| 31 |
-
"learning_rate":
|
| 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": 4.
|
| 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": 4.
|
| 60 |
"step": 17
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 5.71,
|
| 64 |
-
"learning_rate":
|
| 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":
|
| 90 |
-
"eval_runtime": 0.
|
| 91 |
-
"eval_samples_per_second":
|
| 92 |
-
"eval_steps_per_second": 4.
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 8.57,
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 111.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 8.86,
|
| 103 |
"eval_accuracy": 0.10869565217391304,
|
| 104 |
-
"eval_loss":
|
| 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":
|
| 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":
|
| 123 |
-
"eval_runtime": 0.
|
| 124 |
-
"eval_samples_per_second":
|
| 125 |
-
"eval_steps_per_second": 4.
|
| 126 |
"step": 38
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 11.43,
|
| 130 |
-
"learning_rate":
|
| 131 |
-
"loss":
|
| 132 |
"step": 40
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 12.0,
|
| 136 |
"eval_accuracy": 0.10869565217391304,
|
| 137 |
-
"eval_loss":
|
| 138 |
-
"eval_runtime": 0.
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second": 5.
|
| 141 |
"step": 42
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 12.86,
|
| 145 |
"eval_accuracy": 0.10869565217391304,
|
| 146 |
-
"eval_loss":
|
| 147 |
-
"eval_runtime": 0.
|
| 148 |
-
"eval_samples_per_second":
|
| 149 |
-
"eval_steps_per_second":
|
| 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": 4.
|
| 159 |
"step": 49
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 14.29,
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss":
|
| 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":
|
| 180 |
-
"eval_runtime": 0.
|
| 181 |
-
"eval_samples_per_second":
|
| 182 |
-
"eval_steps_per_second":
|
| 183 |
"step": 56
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 16.86,
|
| 187 |
"eval_accuracy": 0.10869565217391304,
|
| 188 |
-
"eval_loss":
|
| 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":
|
| 197 |
-
"loss":
|
| 198 |
"step": 60
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 18.0,
|
| 202 |
"eval_accuracy": 0.10869565217391304,
|
| 203 |
-
"eval_loss":
|
| 204 |
-
"eval_runtime": 0.
|
| 205 |
-
"eval_samples_per_second": 75.
|
| 206 |
-
"eval_steps_per_second": 4.
|
| 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":
|
| 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":
|
| 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":
|
| 246 |
-
"eval_runtime": 0.
|
| 247 |
-
"eval_samples_per_second":
|
| 248 |
-
"eval_steps_per_second": 5.
|
| 249 |
"step": 77
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 22.86,
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss":
|
| 255 |
"step": 80
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 22.86,
|
| 259 |
"eval_accuracy": 0.10869565217391304,
|
| 260 |
-
"eval_loss":
|
| 261 |
-
"eval_runtime": 0.
|
| 262 |
-
"eval_samples_per_second":
|
| 263 |
-
"eval_steps_per_second": 4.
|
| 264 |
"step": 80
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 24.0,
|
| 268 |
"eval_accuracy": 0.10869565217391304,
|
| 269 |
-
"eval_loss":
|
| 270 |
-
"eval_runtime": 0.
|
| 271 |
-
"eval_samples_per_second":
|
| 272 |
-
"eval_steps_per_second":
|
| 273 |
"step": 84
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 24.86,
|
| 277 |
"eval_accuracy": 0.10869565217391304,
|
| 278 |
-
"eval_loss":
|
| 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":
|
| 287 |
-
"loss":
|
| 288 |
"step": 90
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 26.0,
|
| 292 |
"eval_accuracy": 0.10869565217391304,
|
| 293 |
-
"eval_loss":
|
| 294 |
-
"eval_runtime": 0.
|
| 295 |
-
"eval_samples_per_second": 75.
|
| 296 |
-
"eval_steps_per_second": 4.
|
| 297 |
"step": 91
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 26.86,
|
| 301 |
"eval_accuracy": 0.10869565217391304,
|
| 302 |
-
"eval_loss":
|
| 303 |
-
"eval_runtime": 0.
|
| 304 |
-
"eval_samples_per_second":
|
| 305 |
-
"eval_steps_per_second":
|
| 306 |
"step": 94
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 28.0,
|
| 310 |
"eval_accuracy": 0.10869565217391304,
|
| 311 |
-
"eval_loss":
|
| 312 |
-
"eval_runtime": 0.
|
| 313 |
-
"eval_samples_per_second":
|
| 314 |
-
"eval_steps_per_second": 4.
|
| 315 |
"step": 98
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 28.57,
|
| 319 |
-
"learning_rate": 4.
|
| 320 |
-
"loss":
|
| 321 |
"step": 100
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 28.86,
|
| 325 |
"eval_accuracy": 0.10869565217391304,
|
| 326 |
-
"eval_loss":
|
| 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":
|
| 336 |
-
"eval_runtime": 0.
|
| 337 |
-
"eval_samples_per_second": 74.
|
| 338 |
-
"eval_steps_per_second": 4.
|
| 339 |
"step": 105
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 30.86,
|
| 343 |
"eval_accuracy": 0.10869565217391304,
|
| 344 |
-
"eval_loss":
|
| 345 |
-
"eval_runtime": 0.
|
| 346 |
-
"eval_samples_per_second":
|
| 347 |
-
"eval_steps_per_second": 4.
|
| 348 |
"step": 108
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 31.43,
|
| 352 |
-
"learning_rate": 2.
|
| 353 |
-
"loss":
|
| 354 |
"step": 110
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 32.0,
|
| 358 |
"eval_accuracy": 0.10869565217391304,
|
| 359 |
-
"eval_loss":
|
| 360 |
-
"eval_runtime": 0.
|
| 361 |
-
"eval_samples_per_second":
|
| 362 |
-
"eval_steps_per_second":
|
| 363 |
"step": 112
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 32.86,
|
| 367 |
"eval_accuracy": 0.10869565217391304,
|
| 368 |
-
"eval_loss":
|
| 369 |
-
"eval_runtime": 0.
|
| 370 |
-
"eval_samples_per_second":
|
| 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": 4.
|
| 381 |
"step": 119
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 34.29,
|
| 385 |
"learning_rate": 0.0,
|
| 386 |
-
"loss":
|
| 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":
|
| 403 |
-
"train_runtime":
|
| 404 |
-
"train_samples_per_second": 65.
|
| 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": 113.88832092285156,
|
| 15 |
+
"eval_runtime": 0.6507,
|
| 16 |
+
"eval_samples_per_second": 70.697,
|
| 17 |
+
"eval_steps_per_second": 4.611,
|
| 18 |
"step": 3
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 2.0,
|
| 22 |
"eval_accuracy": 0.10869565217391304,
|
| 23 |
+
"eval_loss": 113.88676452636719,
|
| 24 |
+
"eval_runtime": 0.5971,
|
| 25 |
+
"eval_samples_per_second": 77.035,
|
| 26 |
+
"eval_steps_per_second": 5.024,
|
| 27 |
"step": 7
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 2.86,
|
| 31 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 32 |
+
"loss": 114.1606,
|
| 33 |
"step": 10
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 2.86,
|
| 37 |
"eval_accuracy": 0.10869565217391304,
|
| 38 |
+
"eval_loss": 113.88513946533203,
|
| 39 |
+
"eval_runtime": 0.6292,
|
| 40 |
+
"eval_samples_per_second": 73.113,
|
| 41 |
+
"eval_steps_per_second": 4.768,
|
| 42 |
"step": 10
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 4.0,
|
| 46 |
"eval_accuracy": 0.10869565217391304,
|
| 47 |
+
"eval_loss": 113.8846206665039,
|
| 48 |
+
"eval_runtime": 0.6036,
|
| 49 |
+
"eval_samples_per_second": 76.204,
|
| 50 |
+
"eval_steps_per_second": 4.97,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 4.86,
|
| 55 |
"eval_accuracy": 0.10869565217391304,
|
| 56 |
+
"eval_loss": 113.88324737548828,
|
| 57 |
+
"eval_runtime": 0.6196,
|
| 58 |
+
"eval_samples_per_second": 74.236,
|
| 59 |
+
"eval_steps_per_second": 4.841,
|
| 60 |
"step": 17
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 5.71,
|
| 64 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 65 |
+
"loss": 113.5172,
|
| 66 |
"step": 20
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 6.0,
|
| 70 |
"eval_accuracy": 0.10869565217391304,
|
| 71 |
+
"eval_loss": 113.8808364868164,
|
| 72 |
+
"eval_runtime": 0.6092,
|
| 73 |
+
"eval_samples_per_second": 75.515,
|
| 74 |
+
"eval_steps_per_second": 4.925,
|
| 75 |
"step": 21
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 6.86,
|
| 79 |
"eval_accuracy": 0.10869565217391304,
|
| 80 |
+
"eval_loss": 113.87947082519531,
|
| 81 |
+
"eval_runtime": 0.6912,
|
| 82 |
+
"eval_samples_per_second": 66.555,
|
| 83 |
+
"eval_steps_per_second": 4.341,
|
| 84 |
"step": 24
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 8.0,
|
| 88 |
"eval_accuracy": 0.10869565217391304,
|
| 89 |
+
"eval_loss": 113.87939453125,
|
| 90 |
+
"eval_runtime": 0.6041,
|
| 91 |
+
"eval_samples_per_second": 76.14,
|
| 92 |
+
"eval_steps_per_second": 4.966,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 8.57,
|
| 97 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 98 |
+
"loss": 111.7557,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 8.86,
|
| 103 |
"eval_accuracy": 0.10869565217391304,
|
| 104 |
+
"eval_loss": 113.87659454345703,
|
| 105 |
+
"eval_runtime": 0.6201,
|
| 106 |
+
"eval_samples_per_second": 74.177,
|
| 107 |
+
"eval_steps_per_second": 4.838,
|
| 108 |
"step": 31
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 10.0,
|
| 112 |
"eval_accuracy": 0.10869565217391304,
|
| 113 |
+
"eval_loss": 113.87474822998047,
|
| 114 |
+
"eval_runtime": 0.6842,
|
| 115 |
+
"eval_samples_per_second": 67.234,
|
| 116 |
+
"eval_steps_per_second": 4.385,
|
| 117 |
"step": 35
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 10.86,
|
| 121 |
"eval_accuracy": 0.10869565217391304,
|
| 122 |
+
"eval_loss": 113.87353515625,
|
| 123 |
+
"eval_runtime": 0.6136,
|
| 124 |
+
"eval_samples_per_second": 74.962,
|
| 125 |
+
"eval_steps_per_second": 4.889,
|
| 126 |
"step": 38
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 11.43,
|
| 130 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 131 |
+
"loss": 115.9434,
|
| 132 |
"step": 40
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 12.0,
|
| 136 |
"eval_accuracy": 0.10869565217391304,
|
| 137 |
+
"eval_loss": 113.8711929321289,
|
| 138 |
+
"eval_runtime": 0.5921,
|
| 139 |
+
"eval_samples_per_second": 77.685,
|
| 140 |
+
"eval_steps_per_second": 5.066,
|
| 141 |
"step": 42
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 12.86,
|
| 145 |
"eval_accuracy": 0.10869565217391304,
|
| 146 |
+
"eval_loss": 113.86994934082031,
|
| 147 |
+
"eval_runtime": 0.6321,
|
| 148 |
+
"eval_samples_per_second": 72.768,
|
| 149 |
+
"eval_steps_per_second": 4.746,
|
| 150 |
"step": 45
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 14.0,
|
| 154 |
"eval_accuracy": 0.10869565217391304,
|
| 155 |
+
"eval_loss": 113.86713409423828,
|
| 156 |
+
"eval_runtime": 0.6061,
|
| 157 |
+
"eval_samples_per_second": 75.891,
|
| 158 |
+
"eval_steps_per_second": 4.949,
|
| 159 |
"step": 49
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 14.29,
|
| 163 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 164 |
+
"loss": 112.3427,
|
| 165 |
"step": 50
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 14.86,
|
| 169 |
"eval_accuracy": 0.10869565217391304,
|
| 170 |
+
"eval_loss": 113.8606948852539,
|
| 171 |
+
"eval_runtime": 0.6062,
|
| 172 |
+
"eval_samples_per_second": 75.889,
|
| 173 |
+
"eval_steps_per_second": 4.949,
|
| 174 |
"step": 52
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 16.0,
|
| 178 |
"eval_accuracy": 0.10869565217391304,
|
| 179 |
+
"eval_loss": 113.8567123413086,
|
| 180 |
+
"eval_runtime": 0.5916,
|
| 181 |
+
"eval_samples_per_second": 77.75,
|
| 182 |
+
"eval_steps_per_second": 5.071,
|
| 183 |
"step": 56
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 16.86,
|
| 187 |
"eval_accuracy": 0.10869565217391304,
|
| 188 |
+
"eval_loss": 113.85698699951172,
|
| 189 |
+
"eval_runtime": 0.6427,
|
| 190 |
+
"eval_samples_per_second": 71.578,
|
| 191 |
+
"eval_steps_per_second": 4.668,
|
| 192 |
"step": 59
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 17.14,
|
| 196 |
+
"learning_rate": 1.25e-05,
|
| 197 |
+
"loss": 113.2123,
|
| 198 |
"step": 60
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 18.0,
|
| 202 |
"eval_accuracy": 0.10869565217391304,
|
| 203 |
+
"eval_loss": 113.85321807861328,
|
| 204 |
+
"eval_runtime": 0.6122,
|
| 205 |
+
"eval_samples_per_second": 75.144,
|
| 206 |
+
"eval_steps_per_second": 4.901,
|
| 207 |
"step": 63
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 18.86,
|
| 211 |
"eval_accuracy": 0.10869565217391304,
|
| 212 |
+
"eval_loss": 113.85108184814453,
|
| 213 |
+
"eval_runtime": 0.6031,
|
| 214 |
+
"eval_samples_per_second": 76.268,
|
| 215 |
+
"eval_steps_per_second": 4.974,
|
| 216 |
"step": 66
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 20.0,
|
| 220 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 221 |
+
"loss": 114.0835,
|
| 222 |
"step": 70
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 20.0,
|
| 226 |
"eval_accuracy": 0.10869565217391304,
|
| 227 |
+
"eval_loss": 113.85003662109375,
|
| 228 |
+
"eval_runtime": 0.6361,
|
| 229 |
+
"eval_samples_per_second": 72.311,
|
| 230 |
+
"eval_steps_per_second": 4.716,
|
| 231 |
"step": 70
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 20.86,
|
| 235 |
"eval_accuracy": 0.10869565217391304,
|
| 236 |
+
"eval_loss": 113.84687805175781,
|
| 237 |
+
"eval_runtime": 0.6076,
|
| 238 |
+
"eval_samples_per_second": 75.702,
|
| 239 |
+
"eval_steps_per_second": 4.937,
|
| 240 |
"step": 73
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 22.0,
|
| 244 |
"eval_accuracy": 0.10869565217391304,
|
| 245 |
+
"eval_loss": 113.84497833251953,
|
| 246 |
+
"eval_runtime": 0.5921,
|
| 247 |
+
"eval_samples_per_second": 77.683,
|
| 248 |
+
"eval_steps_per_second": 5.066,
|
| 249 |
"step": 77
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 22.86,
|
| 253 |
+
"learning_rate": 8.333333333333334e-06,
|
| 254 |
+
"loss": 114.5528,
|
| 255 |
"step": 80
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 22.86,
|
| 259 |
"eval_accuracy": 0.10869565217391304,
|
| 260 |
+
"eval_loss": 113.84217834472656,
|
| 261 |
+
"eval_runtime": 0.6551,
|
| 262 |
+
"eval_samples_per_second": 70.213,
|
| 263 |
+
"eval_steps_per_second": 4.579,
|
| 264 |
"step": 80
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 24.0,
|
| 268 |
"eval_accuracy": 0.10869565217391304,
|
| 269 |
+
"eval_loss": 113.83406829833984,
|
| 270 |
+
"eval_runtime": 0.5936,
|
| 271 |
+
"eval_samples_per_second": 77.488,
|
| 272 |
+
"eval_steps_per_second": 5.054,
|
| 273 |
"step": 84
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 24.86,
|
| 277 |
"eval_accuracy": 0.10869565217391304,
|
| 278 |
+
"eval_loss": 113.83149719238281,
|
| 279 |
+
"eval_runtime": 0.6102,
|
| 280 |
+
"eval_samples_per_second": 75.391,
|
| 281 |
+
"eval_steps_per_second": 4.917,
|
| 282 |
"step": 87
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 25.71,
|
| 286 |
+
"learning_rate": 6.25e-06,
|
| 287 |
+
"loss": 114.5432,
|
| 288 |
"step": 90
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 26.0,
|
| 292 |
"eval_accuracy": 0.10869565217391304,
|
| 293 |
+
"eval_loss": 113.82682037353516,
|
| 294 |
+
"eval_runtime": 0.6111,
|
| 295 |
+
"eval_samples_per_second": 75.27,
|
| 296 |
+
"eval_steps_per_second": 4.909,
|
| 297 |
"step": 91
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 26.86,
|
| 301 |
"eval_accuracy": 0.10869565217391304,
|
| 302 |
+
"eval_loss": 113.82469940185547,
|
| 303 |
+
"eval_runtime": 0.6141,
|
| 304 |
+
"eval_samples_per_second": 74.902,
|
| 305 |
+
"eval_steps_per_second": 4.885,
|
| 306 |
"step": 94
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 28.0,
|
| 310 |
"eval_accuracy": 0.10869565217391304,
|
| 311 |
+
"eval_loss": 113.82501220703125,
|
| 312 |
+
"eval_runtime": 0.6132,
|
| 313 |
+
"eval_samples_per_second": 75.022,
|
| 314 |
+
"eval_steps_per_second": 4.893,
|
| 315 |
"step": 98
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 28.57,
|
| 319 |
+
"learning_rate": 4.166666666666667e-06,
|
| 320 |
+
"loss": 112.7825,
|
| 321 |
"step": 100
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 28.86,
|
| 325 |
"eval_accuracy": 0.10869565217391304,
|
| 326 |
+
"eval_loss": 113.8207015991211,
|
| 327 |
+
"eval_runtime": 0.6082,
|
| 328 |
+
"eval_samples_per_second": 75.639,
|
| 329 |
+
"eval_steps_per_second": 4.933,
|
| 330 |
"step": 101
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 30.0,
|
| 334 |
"eval_accuracy": 0.10869565217391304,
|
| 335 |
+
"eval_loss": 113.8154525756836,
|
| 336 |
+
"eval_runtime": 0.6136,
|
| 337 |
+
"eval_samples_per_second": 74.962,
|
| 338 |
+
"eval_steps_per_second": 4.889,
|
| 339 |
"step": 105
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 30.86,
|
| 343 |
"eval_accuracy": 0.10869565217391304,
|
| 344 |
+
"eval_loss": 113.81825256347656,
|
| 345 |
+
"eval_runtime": 0.6111,
|
| 346 |
+
"eval_samples_per_second": 75.27,
|
| 347 |
+
"eval_steps_per_second": 4.909,
|
| 348 |
"step": 108
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 31.43,
|
| 352 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 353 |
+
"loss": 114.2965,
|
| 354 |
"step": 110
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 32.0,
|
| 358 |
"eval_accuracy": 0.10869565217391304,
|
| 359 |
+
"eval_loss": 113.8187484741211,
|
| 360 |
+
"eval_runtime": 0.6492,
|
| 361 |
+
"eval_samples_per_second": 70.86,
|
| 362 |
+
"eval_steps_per_second": 4.621,
|
| 363 |
"step": 112
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 32.86,
|
| 367 |
"eval_accuracy": 0.10869565217391304,
|
| 368 |
+
"eval_loss": 113.81865692138672,
|
| 369 |
+
"eval_runtime": 0.6381,
|
| 370 |
+
"eval_samples_per_second": 72.084,
|
| 371 |
+
"eval_steps_per_second": 4.701,
|
| 372 |
"step": 115
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 34.0,
|
| 376 |
"eval_accuracy": 0.10869565217391304,
|
| 377 |
+
"eval_loss": 113.81236267089844,
|
| 378 |
+
"eval_runtime": 0.6046,
|
| 379 |
+
"eval_samples_per_second": 76.078,
|
| 380 |
+
"eval_steps_per_second": 4.962,
|
| 381 |
"step": 119
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 34.29,
|
| 385 |
"learning_rate": 0.0,
|
| 386 |
+
"loss": 114.0925,
|
| 387 |
"step": 120
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 34.29,
|
| 391 |
"eval_accuracy": 0.10869565217391304,
|
| 392 |
+
"eval_loss": 113.81463623046875,
|
| 393 |
+
"eval_runtime": 0.6637,
|
| 394 |
+
"eval_samples_per_second": 69.313,
|
| 395 |
+
"eval_steps_per_second": 4.52,
|
| 396 |
"step": 120
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 34.29,
|
| 400 |
"step": 120,
|
| 401 |
"total_flos": 2.0027429927092224e+16,
|
| 402 |
+
"train_loss": 113.7735809326172,
|
| 403 |
+
"train_runtime": 129.8431,
|
| 404 |
+
"train_samples_per_second": 65.618,
|
| 405 |
+
"train_steps_per_second": 0.924
|
| 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 sha256:15dffc887f0abc9caee2e18a2b30612e3655124e57b6e83dea493f5517e66aea
|
| 3 |
size 4728
|