Training in progress, epoch 1
Browse files- README.md +15 -15
- all_results.json +11 -11
- config.json +21 -21
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- train_results.json +6 -6
- trainer_state.json +209 -497
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,7 +4,7 @@ base_model: microsoft/swin-tiny-patch4-window7-224
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
-
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
|
@@ -14,15 +14,15 @@ model-index:
|
|
| 14 |
name: Image Classification
|
| 15 |
type: image-classification
|
| 16 |
dataset:
|
| 17 |
-
name:
|
| 18 |
-
type:
|
| 19 |
-
config:
|
| 20 |
split: train
|
| 21 |
-
args:
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 30 |
|
| 31 |
# swin-tiny-patch4-window7-224-finetuned-eurosat
|
| 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
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -67,14 +67,14 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
-
- Transformers 4.33.
|
| 78 |
-
- Pytorch 2.0.
|
| 79 |
-
- Datasets 2.
|
| 80 |
- Tokenizers 0.13.3
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
|
|
|
| 14 |
name: Image Classification
|
| 15 |
type: image-classification
|
| 16 |
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
split: train
|
| 21 |
+
args: default
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9803703703703703
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# swin-tiny-patch4-window7-224-finetuned-eurosat
|
| 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: 0.0592
|
| 36 |
+
- Accuracy: 0.9804
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 0.2484 | 1.0 | 190 | 0.1036 | 0.9685 |
|
| 71 |
+
| 0.219 | 2.0 | 380 | 0.0825 | 0.9730 |
|
| 72 |
+
| 0.121 | 3.0 | 570 | 0.0592 | 0.9804 |
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
+
- Transformers 4.33.2
|
| 78 |
+
- Pytorch 2.0.1+cu117
|
| 79 |
+
- Datasets 2.14.5
|
| 80 |
- Tokenizers 0.13.3
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9803703703703703,
|
| 4 |
+
"eval_loss": 0.059159792959690094,
|
| 5 |
+
"eval_runtime": 4.8853,
|
| 6 |
+
"eval_samples_per_second": 552.68,
|
| 7 |
+
"eval_steps_per_second": 17.399,
|
| 8 |
+
"total_flos": 1.8124066505760768e+18,
|
| 9 |
+
"train_loss": 0.32973566536317794,
|
| 10 |
+
"train_runtime": 250.3967,
|
| 11 |
+
"train_samples_per_second": 291.138,
|
| 12 |
+
"train_steps_per_second": 2.276
|
| 13 |
}
|
config.json
CHANGED
|
@@ -17,30 +17,30 @@
|
|
| 17 |
"hidden_dropout_prob": 0.0,
|
| 18 |
"hidden_size": 768,
|
| 19 |
"id2label": {
|
| 20 |
-
"0": "
|
| 21 |
-
"1": "
|
| 22 |
-
"2": "
|
| 23 |
-
"3": "
|
| 24 |
-
"4": "
|
| 25 |
-
"5": "
|
| 26 |
-
"6": "
|
| 27 |
-
"7": "
|
| 28 |
-
"8": "
|
| 29 |
-
"9": "
|
| 30 |
},
|
| 31 |
"image_size": 224,
|
| 32 |
"initializer_range": 0.02,
|
| 33 |
"label2id": {
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
},
|
| 45 |
"layer_norm_eps": 1e-05,
|
| 46 |
"mlp_ratio": 4.0,
|
|
@@ -71,7 +71,7 @@
|
|
| 71 |
"stage4"
|
| 72 |
],
|
| 73 |
"torch_dtype": "float32",
|
| 74 |
-
"transformers_version": "4.33.
|
| 75 |
"use_absolute_embeddings": false,
|
| 76 |
"window_size": 7
|
| 77 |
}
|
|
|
|
| 17 |
"hidden_dropout_prob": 0.0,
|
| 18 |
"hidden_size": 768,
|
| 19 |
"id2label": {
|
| 20 |
+
"0": "AnnualCrop",
|
| 21 |
+
"1": "Forest",
|
| 22 |
+
"2": "HerbaceousVegetation",
|
| 23 |
+
"3": "Highway",
|
| 24 |
+
"4": "Industrial",
|
| 25 |
+
"5": "Pasture",
|
| 26 |
+
"6": "PermanentCrop",
|
| 27 |
+
"7": "Residential",
|
| 28 |
+
"8": "River",
|
| 29 |
+
"9": "SeaLake"
|
| 30 |
},
|
| 31 |
"image_size": 224,
|
| 32 |
"initializer_range": 0.02,
|
| 33 |
"label2id": {
|
| 34 |
+
"AnnualCrop": 0,
|
| 35 |
+
"Forest": 1,
|
| 36 |
+
"HerbaceousVegetation": 2,
|
| 37 |
+
"Highway": 3,
|
| 38 |
+
"Industrial": 4,
|
| 39 |
+
"Pasture": 5,
|
| 40 |
+
"PermanentCrop": 6,
|
| 41 |
+
"Residential": 7,
|
| 42 |
+
"River": 8,
|
| 43 |
+
"SeaLake": 9
|
| 44 |
},
|
| 45 |
"layer_norm_eps": 1e-05,
|
| 46 |
"mlp_ratio": 4.0,
|
|
|
|
| 71 |
"stage4"
|
| 72 |
],
|
| 73 |
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.33.2",
|
| 75 |
"use_absolute_embeddings": false,
|
| 76 |
"window_size": 7
|
| 77 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9803703703703703,
|
| 4 |
+
"eval_loss": 0.059159792959690094,
|
| 5 |
+
"eval_runtime": 4.8853,
|
| 6 |
+
"eval_samples_per_second": 552.68,
|
| 7 |
+
"eval_steps_per_second": 17.399
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110419441
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b3f83e44dcabca5ca5389693ba84eb94e0cc0c17db2be57c34ba08b9afb98ce
|
| 3 |
size 110419441
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.8124066505760768e+18,
|
| 4 |
+
"train_loss": 0.32973566536317794,
|
| 5 |
+
"train_runtime": 250.3967,
|
| 6 |
+
"train_samples_per_second": 291.138,
|
| 7 |
+
"train_steps_per_second": 2.276
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,685 +1,397 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss":
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss":
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss":
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 4.
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 4.
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 4.
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 4.
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 4.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 4.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 4.
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0
|
| 127 |
-
"
|
| 128 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch":
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch":
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 280
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 290
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch":
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 300
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 310
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 320
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 330
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 340
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch": 1.
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 350
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 1.
|
| 223 |
-
"
|
| 224 |
-
"
|
| 225 |
-
"eval_runtime": 20.0773,
|
| 226 |
-
"eval_samples_per_second": 249.038,
|
| 227 |
-
"eval_steps_per_second": 7.82,
|
| 228 |
-
"step": 351
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"epoch": 1.02,
|
| 232 |
-
"learning_rate": 3.658922914466738e-05,
|
| 233 |
-
"loss": 0.4826,
|
| 234 |
"step": 360
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch": 1.
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 370
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"learning_rate":
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 380
|
| 247 |
},
|
| 248 |
{
|
| 249 |
-
"epoch":
|
| 250 |
-
"
|
| 251 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
"step": 390
|
| 253 |
},
|
| 254 |
{
|
| 255 |
-
"epoch":
|
| 256 |
-
"learning_rate":
|
| 257 |
-
"loss": 0.
|
| 258 |
"step": 400
|
| 259 |
},
|
| 260 |
{
|
| 261 |
-
"epoch":
|
| 262 |
-
"learning_rate":
|
| 263 |
-
"loss": 0.
|
| 264 |
"step": 410
|
| 265 |
},
|
| 266 |
{
|
| 267 |
-
"epoch":
|
| 268 |
-
"learning_rate":
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 420
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"epoch":
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 430
|
| 277 |
},
|
| 278 |
{
|
| 279 |
-
"epoch":
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 440
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"learning_rate":
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 450
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch":
|
| 292 |
-
"learning_rate":
|
| 293 |
-
"loss": 0.
|
| 294 |
"step": 460
|
| 295 |
},
|
| 296 |
{
|
| 297 |
-
"epoch":
|
| 298 |
-
"learning_rate":
|
| 299 |
-
"loss": 0.
|
| 300 |
"step": 470
|
| 301 |
},
|
| 302 |
{
|
| 303 |
-
"epoch":
|
| 304 |
-
"learning_rate":
|
| 305 |
-
"loss": 0.
|
| 306 |
"step": 480
|
| 307 |
},
|
| 308 |
{
|
| 309 |
-
"epoch":
|
| 310 |
-
"learning_rate":
|
| 311 |
-
"loss": 0.
|
| 312 |
"step": 490
|
| 313 |
},
|
| 314 |
{
|
| 315 |
-
"epoch":
|
| 316 |
-
"learning_rate":
|
| 317 |
-
"loss": 0.
|
| 318 |
"step": 500
|
| 319 |
},
|
| 320 |
{
|
| 321 |
-
"epoch":
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 510
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch":
|
| 328 |
-
"learning_rate":
|
| 329 |
-
"loss": 0.
|
| 330 |
"step": 520
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"epoch":
|
| 334 |
-
"learning_rate":
|
| 335 |
-
"loss": 0.
|
| 336 |
"step": 530
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch":
|
| 340 |
-
"learning_rate": 2.
|
| 341 |
-
"loss": 0.
|
| 342 |
"step": 540
|
| 343 |
},
|
| 344 |
{
|
| 345 |
-
"epoch":
|
| 346 |
-
"learning_rate":
|
| 347 |
-
"loss": 0.
|
| 348 |
"step": 550
|
| 349 |
},
|
| 350 |
{
|
| 351 |
-
"epoch":
|
| 352 |
-
"learning_rate":
|
| 353 |
-
"loss": 0.
|
| 354 |
"step": 560
|
| 355 |
},
|
| 356 |
{
|
| 357 |
-
"epoch":
|
| 358 |
-
"learning_rate":
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 570
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch":
|
| 364 |
-
"
|
| 365 |
-
"
|
| 366 |
-
"
|
| 367 |
-
|
| 368 |
-
|
| 369 |
-
"
|
| 370 |
-
"learning_rate": 2.4445617740232313e-05,
|
| 371 |
-
"loss": 0.4156,
|
| 372 |
-
"step": 590
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 1.71,
|
| 376 |
-
"learning_rate": 2.391763463569166e-05,
|
| 377 |
-
"loss": 0.4268,
|
| 378 |
-
"step": 600
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 1.73,
|
| 382 |
-
"learning_rate": 2.3389651531151003e-05,
|
| 383 |
-
"loss": 0.436,
|
| 384 |
-
"step": 610
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 1.76,
|
| 388 |
-
"learning_rate": 2.286166842661035e-05,
|
| 389 |
-
"loss": 0.392,
|
| 390 |
-
"step": 620
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 1.79,
|
| 394 |
-
"learning_rate": 2.2333685322069694e-05,
|
| 395 |
-
"loss": 0.4059,
|
| 396 |
-
"step": 630
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 1.82,
|
| 400 |
-
"learning_rate": 2.180570221752904e-05,
|
| 401 |
-
"loss": 0.4014,
|
| 402 |
-
"step": 640
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"epoch": 1.85,
|
| 406 |
-
"learning_rate": 2.1277719112988384e-05,
|
| 407 |
-
"loss": 0.4304,
|
| 408 |
-
"step": 650
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 1.88,
|
| 412 |
-
"learning_rate": 2.074973600844773e-05,
|
| 413 |
-
"loss": 0.3908,
|
| 414 |
-
"step": 660
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 1.9,
|
| 418 |
-
"learning_rate": 2.0221752903907075e-05,
|
| 419 |
-
"loss": 0.3963,
|
| 420 |
-
"step": 670
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 1.93,
|
| 424 |
-
"learning_rate": 1.9693769799366422e-05,
|
| 425 |
-
"loss": 0.3438,
|
| 426 |
-
"step": 680
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"epoch": 1.96,
|
| 430 |
-
"learning_rate": 1.9165786694825765e-05,
|
| 431 |
-
"loss": 0.3941,
|
| 432 |
-
"step": 690
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 1.99,
|
| 436 |
-
"learning_rate": 1.863780359028511e-05,
|
| 437 |
-
"loss": 0.3708,
|
| 438 |
-
"step": 700
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 2.0,
|
| 442 |
-
"eval_accuracy": 0.9688,
|
| 443 |
-
"eval_loss": 0.09748782962560654,
|
| 444 |
-
"eval_runtime": 20.0916,
|
| 445 |
-
"eval_samples_per_second": 248.86,
|
| 446 |
-
"eval_steps_per_second": 7.814,
|
| 447 |
-
"step": 703
|
| 448 |
-
},
|
| 449 |
-
{
|
| 450 |
-
"epoch": 2.02,
|
| 451 |
-
"learning_rate": 1.810982048574446e-05,
|
| 452 |
-
"loss": 0.3771,
|
| 453 |
-
"step": 710
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 2.05,
|
| 457 |
-
"learning_rate": 1.7581837381203803e-05,
|
| 458 |
-
"loss": 0.3559,
|
| 459 |
-
"step": 720
|
| 460 |
-
},
|
| 461 |
-
{
|
| 462 |
-
"epoch": 2.08,
|
| 463 |
-
"learning_rate": 1.7053854276663146e-05,
|
| 464 |
-
"loss": 0.379,
|
| 465 |
-
"step": 730
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 2.1,
|
| 469 |
-
"learning_rate": 1.6525871172122493e-05,
|
| 470 |
-
"loss": 0.3301,
|
| 471 |
-
"step": 740
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 2.13,
|
| 475 |
-
"learning_rate": 1.5997888067581837e-05,
|
| 476 |
-
"loss": 0.3691,
|
| 477 |
-
"step": 750
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 2.16,
|
| 481 |
-
"learning_rate": 1.5469904963041184e-05,
|
| 482 |
-
"loss": 0.3257,
|
| 483 |
-
"step": 760
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch": 2.19,
|
| 487 |
-
"learning_rate": 1.4941921858500529e-05,
|
| 488 |
-
"loss": 0.3673,
|
| 489 |
-
"step": 770
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 2.22,
|
| 493 |
-
"learning_rate": 1.4413938753959874e-05,
|
| 494 |
-
"loss": 0.3701,
|
| 495 |
-
"step": 780
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 2.25,
|
| 499 |
-
"learning_rate": 1.388595564941922e-05,
|
| 500 |
-
"loss": 0.3434,
|
| 501 |
-
"step": 790
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"epoch": 2.27,
|
| 505 |
-
"learning_rate": 1.3357972544878563e-05,
|
| 506 |
-
"loss": 0.3811,
|
| 507 |
-
"step": 800
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 2.3,
|
| 511 |
-
"learning_rate": 1.2829989440337912e-05,
|
| 512 |
-
"loss": 0.3483,
|
| 513 |
-
"step": 810
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 2.33,
|
| 517 |
-
"learning_rate": 1.2302006335797255e-05,
|
| 518 |
-
"loss": 0.369,
|
| 519 |
-
"step": 820
|
| 520 |
-
},
|
| 521 |
-
{
|
| 522 |
-
"epoch": 2.36,
|
| 523 |
-
"learning_rate": 1.17740232312566e-05,
|
| 524 |
-
"loss": 0.4224,
|
| 525 |
-
"step": 830
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"epoch": 2.39,
|
| 529 |
-
"learning_rate": 1.1246040126715946e-05,
|
| 530 |
-
"loss": 0.3386,
|
| 531 |
-
"step": 840
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 2.42,
|
| 535 |
-
"learning_rate": 1.0718057022175291e-05,
|
| 536 |
-
"loss": 0.3552,
|
| 537 |
-
"step": 850
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 2.44,
|
| 541 |
-
"learning_rate": 1.0190073917634636e-05,
|
| 542 |
-
"loss": 0.3818,
|
| 543 |
-
"step": 860
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 2.47,
|
| 547 |
-
"learning_rate": 9.662090813093982e-06,
|
| 548 |
-
"loss": 0.3485,
|
| 549 |
-
"step": 870
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 2.5,
|
| 553 |
-
"learning_rate": 9.134107708553327e-06,
|
| 554 |
-
"loss": 0.3713,
|
| 555 |
-
"step": 880
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 2.53,
|
| 559 |
-
"learning_rate": 8.606124604012672e-06,
|
| 560 |
-
"loss": 0.3233,
|
| 561 |
-
"step": 890
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 2.56,
|
| 565 |
-
"learning_rate": 8.078141499472017e-06,
|
| 566 |
-
"loss": 0.3931,
|
| 567 |
-
"step": 900
|
| 568 |
-
},
|
| 569 |
-
{
|
| 570 |
-
"epoch": 2.59,
|
| 571 |
-
"learning_rate": 7.5501583949313625e-06,
|
| 572 |
-
"loss": 0.3595,
|
| 573 |
-
"step": 910
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 2.62,
|
| 577 |
-
"learning_rate": 7.022175290390708e-06,
|
| 578 |
-
"loss": 0.368,
|
| 579 |
-
"step": 920
|
| 580 |
-
},
|
| 581 |
-
{
|
| 582 |
-
"epoch": 2.64,
|
| 583 |
-
"learning_rate": 6.494192185850054e-06,
|
| 584 |
-
"loss": 0.3494,
|
| 585 |
-
"step": 930
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 2.67,
|
| 589 |
-
"learning_rate": 5.966209081309398e-06,
|
| 590 |
-
"loss": 0.3388,
|
| 591 |
-
"step": 940
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 2.7,
|
| 595 |
-
"learning_rate": 5.438225976768744e-06,
|
| 596 |
-
"loss": 0.3311,
|
| 597 |
-
"step": 950
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"epoch": 2.73,
|
| 601 |
-
"learning_rate": 4.910242872228089e-06,
|
| 602 |
-
"loss": 0.3335,
|
| 603 |
-
"step": 960
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 2.76,
|
| 607 |
-
"learning_rate": 4.382259767687434e-06,
|
| 608 |
-
"loss": 0.3763,
|
| 609 |
-
"step": 970
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 2.79,
|
| 613 |
-
"learning_rate": 3.854276663146779e-06,
|
| 614 |
-
"loss": 0.3199,
|
| 615 |
-
"step": 980
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"epoch": 2.81,
|
| 619 |
-
"learning_rate": 3.326293558606125e-06,
|
| 620 |
-
"loss": 0.3904,
|
| 621 |
-
"step": 990
|
| 622 |
-
},
|
| 623 |
-
{
|
| 624 |
-
"epoch": 2.84,
|
| 625 |
-
"learning_rate": 2.79831045406547e-06,
|
| 626 |
-
"loss": 0.3893,
|
| 627 |
-
"step": 1000
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 2.87,
|
| 631 |
-
"learning_rate": 2.2703273495248154e-06,
|
| 632 |
-
"loss": 0.36,
|
| 633 |
-
"step": 1010
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 2.9,
|
| 637 |
-
"learning_rate": 1.7423442449841606e-06,
|
| 638 |
-
"loss": 0.3613,
|
| 639 |
-
"step": 1020
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 2.93,
|
| 643 |
-
"learning_rate": 1.2143611404435059e-06,
|
| 644 |
-
"loss": 0.3556,
|
| 645 |
-
"step": 1030
|
| 646 |
-
},
|
| 647 |
-
{
|
| 648 |
-
"epoch": 2.96,
|
| 649 |
-
"learning_rate": 6.863780359028511e-07,
|
| 650 |
-
"loss": 0.3358,
|
| 651 |
-
"step": 1040
|
| 652 |
-
},
|
| 653 |
-
{
|
| 654 |
-
"epoch": 2.99,
|
| 655 |
-
"learning_rate": 1.5839493136219642e-07,
|
| 656 |
-
"loss": 0.3201,
|
| 657 |
-
"step": 1050
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 2.99,
|
| 661 |
-
"eval_accuracy": 0.973,
|
| 662 |
-
"eval_loss": 0.079922154545784,
|
| 663 |
-
"eval_runtime": 20.1022,
|
| 664 |
-
"eval_samples_per_second": 248.73,
|
| 665 |
-
"eval_steps_per_second": 7.81,
|
| 666 |
-
"step": 1053
|
| 667 |
},
|
| 668 |
{
|
| 669 |
-
"epoch":
|
| 670 |
-
"step":
|
| 671 |
-
"total_flos":
|
| 672 |
-
"train_loss": 0.
|
| 673 |
-
"train_runtime":
|
| 674 |
-
"train_samples_per_second":
|
| 675 |
-
"train_steps_per_second":
|
| 676 |
}
|
| 677 |
],
|
| 678 |
"logging_steps": 10,
|
| 679 |
-
"max_steps":
|
| 680 |
"num_train_epochs": 3,
|
| 681 |
"save_steps": 500,
|
| 682 |
-
"total_flos":
|
| 683 |
"trial_name": null,
|
| 684 |
"trial_params": null
|
| 685 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9803703703703703,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-570",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 570,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 8.771929824561403e-06,
|
| 14 |
+
"loss": 2.2734,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 20 |
+
"loss": 2.0923,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.16,
|
| 25 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 26 |
+
"loss": 1.6401,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.21,
|
| 31 |
+
"learning_rate": 3.508771929824561e-05,
|
| 32 |
+
"loss": 0.9479,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.26,
|
| 37 |
+
"learning_rate": 4.3859649122807014e-05,
|
| 38 |
+
"loss": 0.5664,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.32,
|
| 43 |
+
"learning_rate": 4.970760233918128e-05,
|
| 44 |
+
"loss": 0.476,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.37,
|
| 49 |
+
"learning_rate": 4.8732943469785574e-05,
|
| 50 |
+
"loss": 0.4555,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.42,
|
| 55 |
+
"learning_rate": 4.7758284600389865e-05,
|
| 56 |
+
"loss": 0.3879,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.47,
|
| 61 |
+
"learning_rate": 4.678362573099415e-05,
|
| 62 |
+
"loss": 0.3706,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.53,
|
| 67 |
+
"learning_rate": 4.580896686159844e-05,
|
| 68 |
+
"loss": 0.394,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.58,
|
| 73 |
+
"learning_rate": 4.483430799220273e-05,
|
| 74 |
+
"loss": 0.344,
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.63,
|
| 79 |
+
"learning_rate": 4.3859649122807014e-05,
|
| 80 |
+
"loss": 0.2958,
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.68,
|
| 85 |
+
"learning_rate": 4.2884990253411305e-05,
|
| 86 |
+
"loss": 0.2769,
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.74,
|
| 91 |
+
"learning_rate": 4.1910331384015596e-05,
|
| 92 |
+
"loss": 0.3316,
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.79,
|
| 97 |
+
"learning_rate": 4.093567251461988e-05,
|
| 98 |
+
"loss": 0.2917,
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.84,
|
| 103 |
+
"learning_rate": 3.996101364522417e-05,
|
| 104 |
+
"loss": 0.2905,
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.89,
|
| 109 |
+
"learning_rate": 3.898635477582846e-05,
|
| 110 |
+
"loss": 0.2667,
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.95,
|
| 115 |
+
"learning_rate": 3.8011695906432746e-05,
|
| 116 |
+
"loss": 0.2338,
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 1.0,
|
| 121 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 122 |
+
"loss": 0.2484,
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.0,
|
| 127 |
+
"eval_accuracy": 0.9685185185185186,
|
| 128 |
+
"eval_loss": 0.1036255806684494,
|
| 129 |
+
"eval_runtime": 5.1297,
|
| 130 |
+
"eval_samples_per_second": 526.346,
|
| 131 |
+
"eval_steps_per_second": 16.57,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.05,
|
| 136 |
+
"learning_rate": 3.606237816764133e-05,
|
| 137 |
+
"loss": 0.2245,
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 1.11,
|
| 142 |
+
"learning_rate": 3.508771929824561e-05,
|
| 143 |
+
"loss": 0.2082,
|
| 144 |
"step": 210
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.16,
|
| 148 |
+
"learning_rate": 3.41130604288499e-05,
|
| 149 |
+
"loss": 0.2787,
|
| 150 |
"step": 220
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 1.21,
|
| 154 |
+
"learning_rate": 3.313840155945419e-05,
|
| 155 |
+
"loss": 0.2265,
|
| 156 |
"step": 230
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 1.26,
|
| 160 |
+
"learning_rate": 3.216374269005848e-05,
|
| 161 |
+
"loss": 0.2218,
|
| 162 |
"step": 240
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 1.32,
|
| 166 |
+
"learning_rate": 3.118908382066277e-05,
|
| 167 |
+
"loss": 0.2426,
|
| 168 |
"step": 250
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"epoch": 1.37,
|
| 172 |
+
"learning_rate": 3.0214424951267055e-05,
|
| 173 |
+
"loss": 0.2044,
|
| 174 |
"step": 260
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 1.42,
|
| 178 |
+
"learning_rate": 2.9239766081871346e-05,
|
| 179 |
+
"loss": 0.2025,
|
| 180 |
"step": 270
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"epoch": 1.47,
|
| 184 |
+
"learning_rate": 2.8265107212475634e-05,
|
| 185 |
+
"loss": 0.2021,
|
| 186 |
"step": 280
|
| 187 |
},
|
| 188 |
{
|
| 189 |
+
"epoch": 1.53,
|
| 190 |
+
"learning_rate": 2.729044834307992e-05,
|
| 191 |
+
"loss": 0.1925,
|
| 192 |
"step": 290
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 1.58,
|
| 196 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 197 |
+
"loss": 0.2151,
|
| 198 |
"step": 300
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 1.63,
|
| 202 |
+
"learning_rate": 2.53411306042885e-05,
|
| 203 |
+
"loss": 0.1906,
|
| 204 |
"step": 310
|
| 205 |
},
|
| 206 |
{
|
| 207 |
+
"epoch": 1.68,
|
| 208 |
+
"learning_rate": 2.4366471734892787e-05,
|
| 209 |
+
"loss": 0.1787,
|
| 210 |
"step": 320
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"epoch": 1.74,
|
| 214 |
+
"learning_rate": 2.3391812865497074e-05,
|
| 215 |
+
"loss": 0.1393,
|
| 216 |
"step": 330
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 1.79,
|
| 220 |
+
"learning_rate": 2.2417153996101365e-05,
|
| 221 |
+
"loss": 0.1516,
|
| 222 |
"step": 340
|
| 223 |
},
|
| 224 |
{
|
| 225 |
+
"epoch": 1.84,
|
| 226 |
+
"learning_rate": 2.1442495126705653e-05,
|
| 227 |
+
"loss": 0.164,
|
| 228 |
"step": 350
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 1.89,
|
| 232 |
+
"learning_rate": 2.046783625730994e-05,
|
| 233 |
+
"loss": 0.1747,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 234 |
"step": 360
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 1.95,
|
| 238 |
+
"learning_rate": 1.949317738791423e-05,
|
| 239 |
+
"loss": 0.1964,
|
| 240 |
"step": 370
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 2.0,
|
| 244 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 245 |
+
"loss": 0.219,
|
| 246 |
"step": 380
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 2.0,
|
| 250 |
+
"eval_accuracy": 0.9729629629629629,
|
| 251 |
+
"eval_loss": 0.08252211660146713,
|
| 252 |
+
"eval_runtime": 4.4943,
|
| 253 |
+
"eval_samples_per_second": 600.762,
|
| 254 |
+
"eval_steps_per_second": 18.913,
|
| 255 |
+
"step": 380
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.05,
|
| 259 |
+
"learning_rate": 1.7543859649122806e-05,
|
| 260 |
+
"loss": 0.2044,
|
| 261 |
"step": 390
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 2.11,
|
| 265 |
+
"learning_rate": 1.6569200779727097e-05,
|
| 266 |
+
"loss": 0.1499,
|
| 267 |
"step": 400
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 2.16,
|
| 271 |
+
"learning_rate": 1.5594541910331384e-05,
|
| 272 |
+
"loss": 0.1401,
|
| 273 |
"step": 410
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 2.21,
|
| 277 |
+
"learning_rate": 1.4619883040935673e-05,
|
| 278 |
+
"loss": 0.1596,
|
| 279 |
"step": 420
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 2.26,
|
| 283 |
+
"learning_rate": 1.364522417153996e-05,
|
| 284 |
+
"loss": 0.163,
|
| 285 |
"step": 430
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 2.32,
|
| 289 |
+
"learning_rate": 1.267056530214425e-05,
|
| 290 |
+
"loss": 0.1403,
|
| 291 |
"step": 440
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 2.37,
|
| 295 |
+
"learning_rate": 1.1695906432748537e-05,
|
| 296 |
+
"loss": 0.1767,
|
| 297 |
"step": 450
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 2.42,
|
| 301 |
+
"learning_rate": 1.0721247563352826e-05,
|
| 302 |
+
"loss": 0.134,
|
| 303 |
"step": 460
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 2.47,
|
| 307 |
+
"learning_rate": 9.746588693957115e-06,
|
| 308 |
+
"loss": 0.1522,
|
| 309 |
"step": 470
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 2.53,
|
| 313 |
+
"learning_rate": 8.771929824561403e-06,
|
| 314 |
+
"loss": 0.14,
|
| 315 |
"step": 480
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 2.58,
|
| 319 |
+
"learning_rate": 7.797270955165692e-06,
|
| 320 |
+
"loss": 0.129,
|
| 321 |
"step": 490
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 2.63,
|
| 325 |
+
"learning_rate": 6.82261208576998e-06,
|
| 326 |
+
"loss": 0.1437,
|
| 327 |
"step": 500
|
| 328 |
},
|
| 329 |
{
|
| 330 |
+
"epoch": 2.68,
|
| 331 |
+
"learning_rate": 5.8479532163742686e-06,
|
| 332 |
+
"loss": 0.1594,
|
| 333 |
"step": 510
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 2.74,
|
| 337 |
+
"learning_rate": 4.873294346978558e-06,
|
| 338 |
+
"loss": 0.1436,
|
| 339 |
"step": 520
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 2.79,
|
| 343 |
+
"learning_rate": 3.898635477582846e-06,
|
| 344 |
+
"loss": 0.1386,
|
| 345 |
"step": 530
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 2.84,
|
| 349 |
+
"learning_rate": 2.9239766081871343e-06,
|
| 350 |
+
"loss": 0.1363,
|
| 351 |
"step": 540
|
| 352 |
},
|
| 353 |
{
|
| 354 |
+
"epoch": 2.89,
|
| 355 |
+
"learning_rate": 1.949317738791423e-06,
|
| 356 |
+
"loss": 0.105,
|
| 357 |
"step": 550
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 2.95,
|
| 361 |
+
"learning_rate": 9.746588693957115e-07,
|
| 362 |
+
"loss": 0.1413,
|
| 363 |
"step": 560
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 3.0,
|
| 367 |
+
"learning_rate": 0.0,
|
| 368 |
+
"loss": 0.121,
|
| 369 |
"step": 570
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 3.0,
|
| 373 |
+
"eval_accuracy": 0.9803703703703703,
|
| 374 |
+
"eval_loss": 0.059159792959690094,
|
| 375 |
+
"eval_runtime": 4.6082,
|
| 376 |
+
"eval_samples_per_second": 585.917,
|
| 377 |
+
"eval_steps_per_second": 18.446,
|
| 378 |
+
"step": 570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 379 |
},
|
| 380 |
{
|
| 381 |
+
"epoch": 3.0,
|
| 382 |
+
"step": 570,
|
| 383 |
+
"total_flos": 1.8124066505760768e+18,
|
| 384 |
+
"train_loss": 0.32973566536317794,
|
| 385 |
+
"train_runtime": 250.3967,
|
| 386 |
+
"train_samples_per_second": 291.138,
|
| 387 |
+
"train_steps_per_second": 2.276
|
| 388 |
}
|
| 389 |
],
|
| 390 |
"logging_steps": 10,
|
| 391 |
+
"max_steps": 570,
|
| 392 |
"num_train_epochs": 3,
|
| 393 |
"save_steps": 500,
|
| 394 |
+
"total_flos": 1.8124066505760768e+18,
|
| 395 |
"trial_name": null,
|
| 396 |
"trial_params": null
|
| 397 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:970cd5a0062561b5253d54acfb6e6f947d5f5a6529c933acf60a03d0c624934c
|
| 3 |
size 4091
|