Commit
•
df3785f
1
Parent(s):
2a32571
End of training
Browse files- README.md +1 -1
- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +409 -0
README.md
CHANGED
|
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
- Accuracy: 1.0
|
| 37 |
|
| 38 |
## Model description
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.0378
|
| 36 |
- Accuracy: 1.0
|
| 37 |
|
| 38 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.94,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.03780711442232132,
|
| 5 |
+
"eval_runtime": 8.3239,
|
| 6 |
+
"eval_samples_per_second": 7.328,
|
| 7 |
+
"eval_steps_per_second": 0.24,
|
| 8 |
+
"train_loss": 0.24504653518753391,
|
| 9 |
+
"train_runtime": 7099.5042,
|
| 10 |
+
"train_samples_per_second": 2.677,
|
| 11 |
+
"train_steps_per_second": 0.02
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.94,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.03780711442232132,
|
| 5 |
+
"eval_runtime": 8.3239,
|
| 6 |
+
"eval_samples_per_second": 7.328,
|
| 7 |
+
"eval_steps_per_second": 0.24
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.94,
|
| 3 |
+
"train_loss": 0.24504653518753391,
|
| 4 |
+
"train_runtime": 7099.5042,
|
| 5 |
+
"train_samples_per_second": 2.677,
|
| 6 |
+
"train_steps_per_second": 0.02
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-herbify\\checkpoint-29",
|
| 4 |
+
"epoch": 32.94117647058823,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.94,
|
| 13 |
+
"eval_accuracy": 0.2786885245901639,
|
| 14 |
+
"eval_loss": 1.8722529411315918,
|
| 15 |
+
"eval_runtime": 10.4984,
|
| 16 |
+
"eval_samples_per_second": 5.81,
|
| 17 |
+
"eval_steps_per_second": 0.191,
|
| 18 |
+
"step": 4
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.88,
|
| 22 |
+
"eval_accuracy": 0.6885245901639344,
|
| 23 |
+
"eval_loss": 1.589874029159546,
|
| 24 |
+
"eval_runtime": 9.7804,
|
| 25 |
+
"eval_samples_per_second": 6.237,
|
| 26 |
+
"eval_steps_per_second": 0.204,
|
| 27 |
+
"step": 8
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.35,
|
| 31 |
+
"learning_rate": 3.571428571428572e-05,
|
| 32 |
+
"loss": 1.8465,
|
| 33 |
+
"step": 10
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.82,
|
| 37 |
+
"eval_accuracy": 0.819672131147541,
|
| 38 |
+
"eval_loss": 1.166068434715271,
|
| 39 |
+
"eval_runtime": 9.5359,
|
| 40 |
+
"eval_samples_per_second": 6.397,
|
| 41 |
+
"eval_steps_per_second": 0.21,
|
| 42 |
+
"step": 12
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_accuracy": 0.9508196721311475,
|
| 47 |
+
"eval_loss": 0.5156134963035583,
|
| 48 |
+
"eval_runtime": 10.3911,
|
| 49 |
+
"eval_samples_per_second": 5.87,
|
| 50 |
+
"eval_steps_per_second": 0.192,
|
| 51 |
+
"step": 17
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.71,
|
| 55 |
+
"learning_rate": 4.761904761904762e-05,
|
| 56 |
+
"loss": 0.9675,
|
| 57 |
+
"step": 20
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.94,
|
| 61 |
+
"eval_accuracy": 0.9836065573770492,
|
| 62 |
+
"eval_loss": 0.21767662465572357,
|
| 63 |
+
"eval_runtime": 9.5807,
|
| 64 |
+
"eval_samples_per_second": 6.367,
|
| 65 |
+
"eval_steps_per_second": 0.209,
|
| 66 |
+
"step": 21
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.88,
|
| 70 |
+
"eval_accuracy": 0.9836065573770492,
|
| 71 |
+
"eval_loss": 0.09286772459745407,
|
| 72 |
+
"eval_runtime": 9.6653,
|
| 73 |
+
"eval_samples_per_second": 6.311,
|
| 74 |
+
"eval_steps_per_second": 0.207,
|
| 75 |
+
"step": 25
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 6.82,
|
| 79 |
+
"eval_accuracy": 1.0,
|
| 80 |
+
"eval_loss": 0.03780711442232132,
|
| 81 |
+
"eval_runtime": 9.4191,
|
| 82 |
+
"eval_samples_per_second": 6.476,
|
| 83 |
+
"eval_steps_per_second": 0.212,
|
| 84 |
+
"step": 29
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 7.06,
|
| 88 |
+
"learning_rate": 4.3650793650793655e-05,
|
| 89 |
+
"loss": 0.2342,
|
| 90 |
+
"step": 30
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 8.0,
|
| 94 |
+
"eval_accuracy": 1.0,
|
| 95 |
+
"eval_loss": 0.012785395607352257,
|
| 96 |
+
"eval_runtime": 10.5856,
|
| 97 |
+
"eval_samples_per_second": 5.763,
|
| 98 |
+
"eval_steps_per_second": 0.189,
|
| 99 |
+
"step": 34
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 8.94,
|
| 103 |
+
"eval_accuracy": 1.0,
|
| 104 |
+
"eval_loss": 0.007455253973603249,
|
| 105 |
+
"eval_runtime": 9.5836,
|
| 106 |
+
"eval_samples_per_second": 6.365,
|
| 107 |
+
"eval_steps_per_second": 0.209,
|
| 108 |
+
"step": 38
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 9.41,
|
| 112 |
+
"learning_rate": 3.968253968253968e-05,
|
| 113 |
+
"loss": 0.1022,
|
| 114 |
+
"step": 40
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 9.88,
|
| 118 |
+
"eval_accuracy": 1.0,
|
| 119 |
+
"eval_loss": 0.005343626253306866,
|
| 120 |
+
"eval_runtime": 9.6049,
|
| 121 |
+
"eval_samples_per_second": 6.351,
|
| 122 |
+
"eval_steps_per_second": 0.208,
|
| 123 |
+
"step": 42
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 10.82,
|
| 127 |
+
"eval_accuracy": 1.0,
|
| 128 |
+
"eval_loss": 0.004873768892139196,
|
| 129 |
+
"eval_runtime": 9.5084,
|
| 130 |
+
"eval_samples_per_second": 6.415,
|
| 131 |
+
"eval_steps_per_second": 0.21,
|
| 132 |
+
"step": 46
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 11.76,
|
| 136 |
+
"learning_rate": 3.571428571428572e-05,
|
| 137 |
+
"loss": 0.0553,
|
| 138 |
+
"step": 50
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 12.0,
|
| 142 |
+
"eval_accuracy": 1.0,
|
| 143 |
+
"eval_loss": 0.0031864838674664497,
|
| 144 |
+
"eval_runtime": 9.4987,
|
| 145 |
+
"eval_samples_per_second": 6.422,
|
| 146 |
+
"eval_steps_per_second": 0.211,
|
| 147 |
+
"step": 51
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 12.94,
|
| 151 |
+
"eval_accuracy": 1.0,
|
| 152 |
+
"eval_loss": 0.0021553540136665106,
|
| 153 |
+
"eval_runtime": 9.4997,
|
| 154 |
+
"eval_samples_per_second": 6.421,
|
| 155 |
+
"eval_steps_per_second": 0.211,
|
| 156 |
+
"step": 55
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 13.88,
|
| 160 |
+
"eval_accuracy": 1.0,
|
| 161 |
+
"eval_loss": 0.0016564505640417337,
|
| 162 |
+
"eval_runtime": 9.438,
|
| 163 |
+
"eval_samples_per_second": 6.463,
|
| 164 |
+
"eval_steps_per_second": 0.212,
|
| 165 |
+
"step": 59
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 14.12,
|
| 169 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 170 |
+
"loss": 0.0278,
|
| 171 |
+
"step": 60
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 14.82,
|
| 175 |
+
"eval_accuracy": 1.0,
|
| 176 |
+
"eval_loss": 0.0018015095265582204,
|
| 177 |
+
"eval_runtime": 9.3989,
|
| 178 |
+
"eval_samples_per_second": 6.49,
|
| 179 |
+
"eval_steps_per_second": 0.213,
|
| 180 |
+
"step": 63
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 16.0,
|
| 184 |
+
"eval_accuracy": 1.0,
|
| 185 |
+
"eval_loss": 0.0011610292131081223,
|
| 186 |
+
"eval_runtime": 9.6243,
|
| 187 |
+
"eval_samples_per_second": 6.338,
|
| 188 |
+
"eval_steps_per_second": 0.208,
|
| 189 |
+
"step": 68
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 16.47,
|
| 193 |
+
"learning_rate": 2.777777777777778e-05,
|
| 194 |
+
"loss": 0.0266,
|
| 195 |
+
"step": 70
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 16.94,
|
| 199 |
+
"eval_accuracy": 1.0,
|
| 200 |
+
"eval_loss": 0.0010830130195245147,
|
| 201 |
+
"eval_runtime": 9.7929,
|
| 202 |
+
"eval_samples_per_second": 6.229,
|
| 203 |
+
"eval_steps_per_second": 0.204,
|
| 204 |
+
"step": 72
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 17.88,
|
| 208 |
+
"eval_accuracy": 1.0,
|
| 209 |
+
"eval_loss": 0.0005534554948098958,
|
| 210 |
+
"eval_runtime": 9.458,
|
| 211 |
+
"eval_samples_per_second": 6.45,
|
| 212 |
+
"eval_steps_per_second": 0.211,
|
| 213 |
+
"step": 76
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 18.82,
|
| 217 |
+
"learning_rate": 2.380952380952381e-05,
|
| 218 |
+
"loss": 0.046,
|
| 219 |
+
"step": 80
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 18.82,
|
| 223 |
+
"eval_accuracy": 1.0,
|
| 224 |
+
"eval_loss": 0.0006528783706016839,
|
| 225 |
+
"eval_runtime": 9.3985,
|
| 226 |
+
"eval_samples_per_second": 6.49,
|
| 227 |
+
"eval_steps_per_second": 0.213,
|
| 228 |
+
"step": 80
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 20.0,
|
| 232 |
+
"eval_accuracy": 1.0,
|
| 233 |
+
"eval_loss": 0.0006630417774431407,
|
| 234 |
+
"eval_runtime": 11.0531,
|
| 235 |
+
"eval_samples_per_second": 5.519,
|
| 236 |
+
"eval_steps_per_second": 0.181,
|
| 237 |
+
"step": 85
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 20.94,
|
| 241 |
+
"eval_accuracy": 1.0,
|
| 242 |
+
"eval_loss": 0.0011503107380121946,
|
| 243 |
+
"eval_runtime": 9.3611,
|
| 244 |
+
"eval_samples_per_second": 6.516,
|
| 245 |
+
"eval_steps_per_second": 0.214,
|
| 246 |
+
"step": 89
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 21.18,
|
| 250 |
+
"learning_rate": 1.984126984126984e-05,
|
| 251 |
+
"loss": 0.0245,
|
| 252 |
+
"step": 90
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 21.88,
|
| 256 |
+
"eval_accuracy": 1.0,
|
| 257 |
+
"eval_loss": 0.001531698857434094,
|
| 258 |
+
"eval_runtime": 9.4768,
|
| 259 |
+
"eval_samples_per_second": 6.437,
|
| 260 |
+
"eval_steps_per_second": 0.211,
|
| 261 |
+
"step": 93
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 22.82,
|
| 265 |
+
"eval_accuracy": 1.0,
|
| 266 |
+
"eval_loss": 0.001126309740357101,
|
| 267 |
+
"eval_runtime": 9.6421,
|
| 268 |
+
"eval_samples_per_second": 6.326,
|
| 269 |
+
"eval_steps_per_second": 0.207,
|
| 270 |
+
"step": 97
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 23.53,
|
| 274 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 275 |
+
"loss": 0.0249,
|
| 276 |
+
"step": 100
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 24.0,
|
| 280 |
+
"eval_accuracy": 1.0,
|
| 281 |
+
"eval_loss": 0.0007032424327917397,
|
| 282 |
+
"eval_runtime": 9.3882,
|
| 283 |
+
"eval_samples_per_second": 6.498,
|
| 284 |
+
"eval_steps_per_second": 0.213,
|
| 285 |
+
"step": 102
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 24.94,
|
| 289 |
+
"eval_accuracy": 1.0,
|
| 290 |
+
"eval_loss": 0.0005956963868811727,
|
| 291 |
+
"eval_runtime": 9.8945,
|
| 292 |
+
"eval_samples_per_second": 6.165,
|
| 293 |
+
"eval_steps_per_second": 0.202,
|
| 294 |
+
"step": 106
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 25.88,
|
| 298 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 299 |
+
"loss": 0.0201,
|
| 300 |
+
"step": 110
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 25.88,
|
| 304 |
+
"eval_accuracy": 1.0,
|
| 305 |
+
"eval_loss": 0.0005172533565200865,
|
| 306 |
+
"eval_runtime": 9.3758,
|
| 307 |
+
"eval_samples_per_second": 6.506,
|
| 308 |
+
"eval_steps_per_second": 0.213,
|
| 309 |
+
"step": 110
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 26.82,
|
| 313 |
+
"eval_accuracy": 1.0,
|
| 314 |
+
"eval_loss": 0.00046070647658780217,
|
| 315 |
+
"eval_runtime": 9.339,
|
| 316 |
+
"eval_samples_per_second": 6.532,
|
| 317 |
+
"eval_steps_per_second": 0.214,
|
| 318 |
+
"step": 114
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 28.0,
|
| 322 |
+
"eval_accuracy": 1.0,
|
| 323 |
+
"eval_loss": 0.0004155620699748397,
|
| 324 |
+
"eval_runtime": 9.3776,
|
| 325 |
+
"eval_samples_per_second": 6.505,
|
| 326 |
+
"eval_steps_per_second": 0.213,
|
| 327 |
+
"step": 119
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 28.24,
|
| 331 |
+
"learning_rate": 7.936507936507936e-06,
|
| 332 |
+
"loss": 0.0208,
|
| 333 |
+
"step": 120
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 28.94,
|
| 337 |
+
"eval_accuracy": 1.0,
|
| 338 |
+
"eval_loss": 0.00039234571158885956,
|
| 339 |
+
"eval_runtime": 9.1924,
|
| 340 |
+
"eval_samples_per_second": 6.636,
|
| 341 |
+
"eval_steps_per_second": 0.218,
|
| 342 |
+
"step": 123
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 29.88,
|
| 346 |
+
"eval_accuracy": 1.0,
|
| 347 |
+
"eval_loss": 0.0003777274105232209,
|
| 348 |
+
"eval_runtime": 9.4986,
|
| 349 |
+
"eval_samples_per_second": 6.422,
|
| 350 |
+
"eval_steps_per_second": 0.211,
|
| 351 |
+
"step": 127
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 30.59,
|
| 355 |
+
"learning_rate": 3.968253968253968e-06,
|
| 356 |
+
"loss": 0.0122,
|
| 357 |
+
"step": 130
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 30.82,
|
| 361 |
+
"eval_accuracy": 1.0,
|
| 362 |
+
"eval_loss": 0.00038062228122726083,
|
| 363 |
+
"eval_runtime": 9.3421,
|
| 364 |
+
"eval_samples_per_second": 6.53,
|
| 365 |
+
"eval_steps_per_second": 0.214,
|
| 366 |
+
"step": 131
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 32.0,
|
| 370 |
+
"eval_accuracy": 1.0,
|
| 371 |
+
"eval_loss": 0.00039040297269821167,
|
| 372 |
+
"eval_runtime": 9.6115,
|
| 373 |
+
"eval_samples_per_second": 6.347,
|
| 374 |
+
"eval_steps_per_second": 0.208,
|
| 375 |
+
"step": 136
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 32.94,
|
| 379 |
+
"learning_rate": 0.0,
|
| 380 |
+
"loss": 0.0222,
|
| 381 |
+
"step": 140
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 32.94,
|
| 385 |
+
"eval_accuracy": 1.0,
|
| 386 |
+
"eval_loss": 0.00039268023101612926,
|
| 387 |
+
"eval_runtime": 9.5598,
|
| 388 |
+
"eval_samples_per_second": 6.381,
|
| 389 |
+
"eval_steps_per_second": 0.209,
|
| 390 |
+
"step": 140
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 32.94,
|
| 394 |
+
"step": 140,
|
| 395 |
+
"total_flos": 4.446860502960046e+17,
|
| 396 |
+
"train_loss": 0.24504653518753391,
|
| 397 |
+
"train_runtime": 7099.5042,
|
| 398 |
+
"train_samples_per_second": 2.677,
|
| 399 |
+
"train_steps_per_second": 0.02
|
| 400 |
+
}
|
| 401 |
+
],
|
| 402 |
+
"logging_steps": 10,
|
| 403 |
+
"max_steps": 140,
|
| 404 |
+
"num_train_epochs": 35,
|
| 405 |
+
"save_steps": 500,
|
| 406 |
+
"total_flos": 4.446860502960046e+17,
|
| 407 |
+
"trial_name": null,
|
| 408 |
+
"trial_params": null
|
| 409 |
+
}
|