End of training
Browse files- README.md +2 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan13_18-43-01_a732f801c5be/events.out.tfevents.1705172535.a732f801c5be.827.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +451 -0
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/resnet-101](https://huggingface.co/microsoft/resnet-101) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/resnet-101](https://huggingface.co/microsoft/resnet-101) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.4237
|
| 21 |
+
- Accuracy: 0.5471
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.94,
|
| 3 |
+
"eval_accuracy": 0.5470588235294118,
|
| 4 |
+
"eval_loss": 1.4236853122711182,
|
| 5 |
+
"eval_runtime": 27.2595,
|
| 6 |
+
"eval_samples_per_second": 74.836,
|
| 7 |
+
"eval_steps_per_second": 2.348,
|
| 8 |
+
"total_flos": 1.5485654902849044e+18,
|
| 9 |
+
"train_loss": 1.918136742001488,
|
| 10 |
+
"train_runtime": 1116.4453,
|
| 11 |
+
"train_samples_per_second": 36.54,
|
| 12 |
+
"train_steps_per_second": 0.282
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.94,
|
| 3 |
+
"eval_accuracy": 0.5470588235294118,
|
| 4 |
+
"eval_loss": 1.4236853122711182,
|
| 5 |
+
"eval_runtime": 27.2595,
|
| 6 |
+
"eval_samples_per_second": 74.836,
|
| 7 |
+
"eval_steps_per_second": 2.348
|
| 8 |
+
}
|
runs/Jan13_18-43-01_a732f801c5be/events.out.tfevents.1705172535.a732f801c5be.827.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccfd12ac3bd34234a279b65adf0bd40ed5133436734bec72c64c4df96b2fc381
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.94,
|
| 3 |
+
"total_flos": 1.5485654902849044e+18,
|
| 4 |
+
"train_loss": 1.918136742001488,
|
| 5 |
+
"train_runtime": 1116.4453,
|
| 6 |
+
"train_samples_per_second": 36.54,
|
| 7 |
+
"train_steps_per_second": 0.282
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,451 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5470588235294118,
|
| 3 |
+
"best_model_checkpoint": "resnet-101-finetuned-CivilEng11k/checkpoint-255",
|
| 4 |
+
"epoch": 4.9411764705882355,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 315,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 7.8125e-06,
|
| 14 |
+
"loss": 2.6457,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.16,
|
| 19 |
+
"learning_rate": 1.5625e-05,
|
| 20 |
+
"loss": 2.6463,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.24,
|
| 25 |
+
"learning_rate": 2.34375e-05,
|
| 26 |
+
"loss": 2.6388,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.31,
|
| 31 |
+
"learning_rate": 3.125e-05,
|
| 32 |
+
"loss": 2.6285,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.39,
|
| 37 |
+
"learning_rate": 3.90625e-05,
|
| 38 |
+
"loss": 2.6151,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.47,
|
| 43 |
+
"learning_rate": 4.6875e-05,
|
| 44 |
+
"loss": 2.6003,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.55,
|
| 49 |
+
"learning_rate": 4.946996466431096e-05,
|
| 50 |
+
"loss": 2.5829,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.63,
|
| 55 |
+
"learning_rate": 4.858657243816255e-05,
|
| 56 |
+
"loss": 2.5598,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.71,
|
| 61 |
+
"learning_rate": 4.7703180212014135e-05,
|
| 62 |
+
"loss": 2.5384,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.78,
|
| 67 |
+
"learning_rate": 4.6819787985865726e-05,
|
| 68 |
+
"loss": 2.5162,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.86,
|
| 73 |
+
"learning_rate": 4.593639575971732e-05,
|
| 74 |
+
"loss": 2.4964,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.94,
|
| 79 |
+
"learning_rate": 4.50530035335689e-05,
|
| 80 |
+
"loss": 2.4839,
|
| 81 |
+
"step": 60
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.99,
|
| 85 |
+
"eval_accuracy": 0.5455882352941176,
|
| 86 |
+
"eval_loss": 2.4616942405700684,
|
| 87 |
+
"eval_runtime": 38.0552,
|
| 88 |
+
"eval_samples_per_second": 53.606,
|
| 89 |
+
"eval_steps_per_second": 1.682,
|
| 90 |
+
"step": 63
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.02,
|
| 94 |
+
"learning_rate": 4.416961130742049e-05,
|
| 95 |
+
"loss": 2.4659,
|
| 96 |
+
"step": 65
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.1,
|
| 100 |
+
"learning_rate": 4.328621908127209e-05,
|
| 101 |
+
"loss": 2.4399,
|
| 102 |
+
"step": 70
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.18,
|
| 106 |
+
"learning_rate": 4.240282685512368e-05,
|
| 107 |
+
"loss": 2.4123,
|
| 108 |
+
"step": 75
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.25,
|
| 112 |
+
"learning_rate": 4.1519434628975266e-05,
|
| 113 |
+
"loss": 2.3855,
|
| 114 |
+
"step": 80
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.33,
|
| 118 |
+
"learning_rate": 4.063604240282686e-05,
|
| 119 |
+
"loss": 2.3553,
|
| 120 |
+
"step": 85
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.41,
|
| 124 |
+
"learning_rate": 3.975265017667845e-05,
|
| 125 |
+
"loss": 2.3209,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.49,
|
| 130 |
+
"learning_rate": 3.886925795053003e-05,
|
| 131 |
+
"loss": 2.3022,
|
| 132 |
+
"step": 95
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.57,
|
| 136 |
+
"learning_rate": 3.7985865724381624e-05,
|
| 137 |
+
"loss": 2.2548,
|
| 138 |
+
"step": 100
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.65,
|
| 142 |
+
"learning_rate": 3.710247349823322e-05,
|
| 143 |
+
"loss": 2.2356,
|
| 144 |
+
"step": 105
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.73,
|
| 148 |
+
"learning_rate": 3.621908127208481e-05,
|
| 149 |
+
"loss": 2.2099,
|
| 150 |
+
"step": 110
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.8,
|
| 154 |
+
"learning_rate": 3.53356890459364e-05,
|
| 155 |
+
"loss": 2.1568,
|
| 156 |
+
"step": 115
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.88,
|
| 160 |
+
"learning_rate": 3.445229681978799e-05,
|
| 161 |
+
"loss": 2.1056,
|
| 162 |
+
"step": 120
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.96,
|
| 166 |
+
"learning_rate": 3.356890459363958e-05,
|
| 167 |
+
"loss": 2.0704,
|
| 168 |
+
"step": 125
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.99,
|
| 172 |
+
"eval_accuracy": 0.5441176470588235,
|
| 173 |
+
"eval_loss": 2.03456449508667,
|
| 174 |
+
"eval_runtime": 36.8172,
|
| 175 |
+
"eval_samples_per_second": 55.409,
|
| 176 |
+
"eval_steps_per_second": 1.738,
|
| 177 |
+
"step": 127
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.04,
|
| 181 |
+
"learning_rate": 3.2685512367491163e-05,
|
| 182 |
+
"loss": 2.0245,
|
| 183 |
+
"step": 130
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.12,
|
| 187 |
+
"learning_rate": 3.1802120141342755e-05,
|
| 188 |
+
"loss": 1.9824,
|
| 189 |
+
"step": 135
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.2,
|
| 193 |
+
"learning_rate": 3.0918727915194346e-05,
|
| 194 |
+
"loss": 1.9448,
|
| 195 |
+
"step": 140
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.27,
|
| 199 |
+
"learning_rate": 3.003533568904594e-05,
|
| 200 |
+
"loss": 1.9378,
|
| 201 |
+
"step": 145
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.35,
|
| 205 |
+
"learning_rate": 2.915194346289753e-05,
|
| 206 |
+
"loss": 1.8728,
|
| 207 |
+
"step": 150
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.43,
|
| 211 |
+
"learning_rate": 2.826855123674912e-05,
|
| 212 |
+
"loss": 1.8321,
|
| 213 |
+
"step": 155
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.51,
|
| 217 |
+
"learning_rate": 2.738515901060071e-05,
|
| 218 |
+
"loss": 1.7669,
|
| 219 |
+
"step": 160
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.59,
|
| 223 |
+
"learning_rate": 2.6501766784452298e-05,
|
| 224 |
+
"loss": 1.7718,
|
| 225 |
+
"step": 165
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.67,
|
| 229 |
+
"learning_rate": 2.5618374558303885e-05,
|
| 230 |
+
"loss": 1.7076,
|
| 231 |
+
"step": 170
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.75,
|
| 235 |
+
"learning_rate": 2.473498233215548e-05,
|
| 236 |
+
"loss": 1.6902,
|
| 237 |
+
"step": 175
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.82,
|
| 241 |
+
"learning_rate": 2.3851590106007068e-05,
|
| 242 |
+
"loss": 1.668,
|
| 243 |
+
"step": 180
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.9,
|
| 247 |
+
"learning_rate": 2.296819787985866e-05,
|
| 248 |
+
"loss": 1.6735,
|
| 249 |
+
"step": 185
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.98,
|
| 253 |
+
"learning_rate": 2.2084805653710246e-05,
|
| 254 |
+
"loss": 1.6431,
|
| 255 |
+
"step": 190
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 3.0,
|
| 259 |
+
"eval_accuracy": 0.5431372549019607,
|
| 260 |
+
"eval_loss": 1.5776699781417847,
|
| 261 |
+
"eval_runtime": 39.0457,
|
| 262 |
+
"eval_samples_per_second": 52.246,
|
| 263 |
+
"eval_steps_per_second": 1.639,
|
| 264 |
+
"step": 191
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.06,
|
| 268 |
+
"learning_rate": 2.120141342756184e-05,
|
| 269 |
+
"loss": 1.5668,
|
| 270 |
+
"step": 195
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.14,
|
| 274 |
+
"learning_rate": 2.031802120141343e-05,
|
| 275 |
+
"loss": 1.5775,
|
| 276 |
+
"step": 200
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.22,
|
| 280 |
+
"learning_rate": 1.9434628975265016e-05,
|
| 281 |
+
"loss": 1.6037,
|
| 282 |
+
"step": 205
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.29,
|
| 286 |
+
"learning_rate": 1.855123674911661e-05,
|
| 287 |
+
"loss": 1.4961,
|
| 288 |
+
"step": 210
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.37,
|
| 292 |
+
"learning_rate": 1.76678445229682e-05,
|
| 293 |
+
"loss": 1.5583,
|
| 294 |
+
"step": 215
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.45,
|
| 298 |
+
"learning_rate": 1.678445229681979e-05,
|
| 299 |
+
"loss": 1.4957,
|
| 300 |
+
"step": 220
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.53,
|
| 304 |
+
"learning_rate": 1.5901060070671377e-05,
|
| 305 |
+
"loss": 1.4385,
|
| 306 |
+
"step": 225
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.61,
|
| 310 |
+
"learning_rate": 1.501766784452297e-05,
|
| 311 |
+
"loss": 1.4659,
|
| 312 |
+
"step": 230
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 3.69,
|
| 316 |
+
"learning_rate": 1.413427561837456e-05,
|
| 317 |
+
"loss": 1.5334,
|
| 318 |
+
"step": 235
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.76,
|
| 322 |
+
"learning_rate": 1.3250883392226149e-05,
|
| 323 |
+
"loss": 1.4619,
|
| 324 |
+
"step": 240
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.84,
|
| 328 |
+
"learning_rate": 1.236749116607774e-05,
|
| 329 |
+
"loss": 1.4785,
|
| 330 |
+
"step": 245
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.92,
|
| 334 |
+
"learning_rate": 1.148409893992933e-05,
|
| 335 |
+
"loss": 1.4503,
|
| 336 |
+
"step": 250
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.0,
|
| 340 |
+
"learning_rate": 1.060070671378092e-05,
|
| 341 |
+
"loss": 1.4766,
|
| 342 |
+
"step": 255
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 4.0,
|
| 346 |
+
"eval_accuracy": 0.5470588235294118,
|
| 347 |
+
"eval_loss": 1.4236853122711182,
|
| 348 |
+
"eval_runtime": 36.8606,
|
| 349 |
+
"eval_samples_per_second": 55.344,
|
| 350 |
+
"eval_steps_per_second": 1.736,
|
| 351 |
+
"step": 255
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.08,
|
| 355 |
+
"learning_rate": 9.717314487632508e-06,
|
| 356 |
+
"loss": 1.4636,
|
| 357 |
+
"step": 260
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.16,
|
| 361 |
+
"learning_rate": 8.8339222614841e-06,
|
| 362 |
+
"loss": 1.4563,
|
| 363 |
+
"step": 265
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.24,
|
| 367 |
+
"learning_rate": 7.950530035335689e-06,
|
| 368 |
+
"loss": 1.4113,
|
| 369 |
+
"step": 270
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.31,
|
| 373 |
+
"learning_rate": 7.06713780918728e-06,
|
| 374 |
+
"loss": 1.4478,
|
| 375 |
+
"step": 275
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.39,
|
| 379 |
+
"learning_rate": 6.18374558303887e-06,
|
| 380 |
+
"loss": 1.3906,
|
| 381 |
+
"step": 280
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.47,
|
| 385 |
+
"learning_rate": 5.30035335689046e-06,
|
| 386 |
+
"loss": 1.4368,
|
| 387 |
+
"step": 285
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.55,
|
| 391 |
+
"learning_rate": 4.41696113074205e-06,
|
| 392 |
+
"loss": 1.4866,
|
| 393 |
+
"step": 290
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.63,
|
| 397 |
+
"learning_rate": 3.53356890459364e-06,
|
| 398 |
+
"loss": 1.3677,
|
| 399 |
+
"step": 295
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.71,
|
| 403 |
+
"learning_rate": 2.65017667844523e-06,
|
| 404 |
+
"loss": 1.4778,
|
| 405 |
+
"step": 300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.78,
|
| 409 |
+
"learning_rate": 1.76678445229682e-06,
|
| 410 |
+
"loss": 1.3468,
|
| 411 |
+
"step": 305
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.86,
|
| 415 |
+
"learning_rate": 8.8339222614841e-07,
|
| 416 |
+
"loss": 1.4025,
|
| 417 |
+
"step": 310
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.94,
|
| 421 |
+
"learning_rate": 0.0,
|
| 422 |
+
"loss": 1.3687,
|
| 423 |
+
"step": 315
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.94,
|
| 427 |
+
"eval_accuracy": 0.5455882352941176,
|
| 428 |
+
"eval_loss": 1.4038941860198975,
|
| 429 |
+
"eval_runtime": 38.0413,
|
| 430 |
+
"eval_samples_per_second": 53.626,
|
| 431 |
+
"eval_steps_per_second": 1.682,
|
| 432 |
+
"step": 315
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.94,
|
| 436 |
+
"step": 315,
|
| 437 |
+
"total_flos": 1.5485654902849044e+18,
|
| 438 |
+
"train_loss": 1.918136742001488,
|
| 439 |
+
"train_runtime": 1116.4453,
|
| 440 |
+
"train_samples_per_second": 36.54,
|
| 441 |
+
"train_steps_per_second": 0.282
|
| 442 |
+
}
|
| 443 |
+
],
|
| 444 |
+
"logging_steps": 5,
|
| 445 |
+
"max_steps": 315,
|
| 446 |
+
"num_train_epochs": 5,
|
| 447 |
+
"save_steps": 500,
|
| 448 |
+
"total_flos": 1.5485654902849044e+18,
|
| 449 |
+
"trial_name": null,
|
| 450 |
+
"trial_params": null
|
| 451 |
+
}
|