End of training
Browse files- README.md +34 -25
- all_results.json +6 -11
- model.safetensors +1 -1
- train_results.json +6 -6
- trainer_state.json +310 -586
README.md
CHANGED
|
@@ -8,6 +8,9 @@ datasets:
|
|
| 8 |
- oxford102_flower_dataset
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
|
|
|
|
|
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: resnet-50-finetuned-oxfordflowers
|
| 13 |
results:
|
|
@@ -23,7 +26,16 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the oxford102_flower_dataset dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Accuracy: 0.
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -63,28 +78,22 @@ The following hyperparameters were used during training:
|
|
| 63 |
|
| 64 |
### Training results
|
| 65 |
|
| 66 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
-
|
| 68 |
-
| 4.
|
| 69 |
-
| 2.
|
| 70 |
-
| 1.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.0028 | 15.0 | 480 | 0.5927 | 0.8441 |
|
| 83 |
-
| 0.0023 | 16.0 | 512 | 0.5878 | 0.8520 |
|
| 84 |
-
| 0.0027 | 17.0 | 544 | 0.5872 | 0.8471 |
|
| 85 |
-
| 0.0028 | 18.0 | 576 | 0.5892 | 0.8451 |
|
| 86 |
-
| 0.002 | 19.0 | 608 | 0.5933 | 0.8412 |
|
| 87 |
-
| 0.0017 | 20.0 | 640 | 0.5915 | 0.85 |
|
| 88 |
|
| 89 |
|
| 90 |
### Framework versions
|
|
|
|
| 8 |
- oxford102_flower_dataset
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
| 11 |
+
- precision
|
| 12 |
+
- recall
|
| 13 |
+
- f1
|
| 14 |
model-index:
|
| 15 |
- name: resnet-50-finetuned-oxfordflowers
|
| 16 |
results:
|
|
|
|
| 26 |
metrics:
|
| 27 |
- name: Accuracy
|
| 28 |
type: accuracy
|
| 29 |
+
value: 0.8284273865669215
|
| 30 |
+
- name: Precision
|
| 31 |
+
type: precision
|
| 32 |
+
value: 0.8492938596426545
|
| 33 |
+
- name: Recall
|
| 34 |
+
type: recall
|
| 35 |
+
value: 0.8284273865669215
|
| 36 |
+
- name: F1
|
| 37 |
+
type: f1
|
| 38 |
+
value: 0.8283468243702176
|
| 39 |
---
|
| 40 |
|
| 41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 45 |
|
| 46 |
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the oxford102_flower_dataset dataset.
|
| 47 |
It achieves the following results on the evaluation set:
|
| 48 |
+
- Loss: 0.6286
|
| 49 |
+
- Accuracy: 0.8284
|
| 50 |
+
- Precision: 0.8493
|
| 51 |
+
- Recall: 0.8284
|
| 52 |
+
- F1: 0.8283
|
| 53 |
|
| 54 |
## Model description
|
| 55 |
|
|
|
|
| 78 |
|
| 79 |
### Training results
|
| 80 |
|
| 81 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 82 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 83 |
+
| 4.5237 | 1.0 | 32 | 4.3400 | 0.3451 | 0.4129 | 0.3451 | 0.2875 |
|
| 84 |
+
| 2.8508 | 2.0 | 64 | 1.9785 | 0.5206 | 0.5610 | 0.5206 | 0.4816 |
|
| 85 |
+
| 1.346 | 3.0 | 96 | 1.1449 | 0.7088 | 0.7738 | 0.7088 | 0.6957 |
|
| 86 |
+
| 0.5544 | 4.0 | 128 | 0.9265 | 0.7539 | 0.8162 | 0.7539 | 0.7480 |
|
| 87 |
+
| 0.1847 | 5.0 | 160 | 0.7754 | 0.8029 | 0.8324 | 0.8029 | 0.7997 |
|
| 88 |
+
| 0.0863 | 6.0 | 192 | 0.7393 | 0.8020 | 0.8450 | 0.8020 | 0.8000 |
|
| 89 |
+
| 0.0516 | 7.0 | 224 | 0.6631 | 0.8284 | 0.8569 | 0.8284 | 0.8259 |
|
| 90 |
+
| 0.023 | 8.0 | 256 | 0.5880 | 0.8471 | 0.8631 | 0.8471 | 0.8429 |
|
| 91 |
+
| 0.011 | 9.0 | 288 | 0.5422 | 0.8569 | 0.8686 | 0.8569 | 0.8520 |
|
| 92 |
+
| 0.0079 | 10.0 | 320 | 0.5335 | 0.8510 | 0.8637 | 0.8510 | 0.8470 |
|
| 93 |
+
| 0.0072 | 11.0 | 352 | 0.5107 | 0.8647 | 0.8735 | 0.8647 | 0.8605 |
|
| 94 |
+
| 0.0086 | 12.0 | 384 | 0.5290 | 0.8578 | 0.8720 | 0.8578 | 0.8548 |
|
| 95 |
+
| 0.0058 | 13.0 | 416 | 0.5161 | 0.8569 | 0.8658 | 0.8569 | 0.8523 |
|
| 96 |
+
| 0.0027 | 14.0 | 448 | 0.5139 | 0.8588 | 0.8702 | 0.8588 | 0.8538 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
|
| 98 |
|
| 99 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,13 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"total_flos": 4.36977436041216e+17,
|
| 9 |
-
"train_loss": 0.5368185924002319,
|
| 10 |
-
"train_runtime": 902.6693,
|
| 11 |
-
"train_samples_per_second": 22.6,
|
| 12 |
-
"train_steps_per_second": 0.709
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 14.0,
|
| 3 |
+
"total_flos": 3.058842052288512e+17,
|
| 4 |
+
"train_loss": 0.7544229235707982,
|
| 5 |
+
"train_runtime": 674.4917,
|
| 6 |
+
"train_samples_per_second": 30.245,
|
| 7 |
+
"train_steps_per_second": 0.949
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 95122680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fda6a9820f2992de0ff984ceec1a98f0df2dd245077d01a5db17936e7e095e2
|
| 3 |
size 95122680
|
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": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 14.0,
|
| 3 |
+
"total_flos": 3.058842052288512e+17,
|
| 4 |
+
"train_loss": 0.7544229235707982,
|
| 5 |
+
"train_runtime": 674.4917,
|
| 6 |
+
"train_samples_per_second": 30.245,
|
| 7 |
+
"train_steps_per_second": 0.949
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1097 +1,812 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "resnet-50-finetuned-oxfordflowers/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": 0.15625,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
"learning_rate": 0.0009921875,
|
| 15 |
-
"loss": 4.
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.3125,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
"learning_rate": 0.000984375,
|
| 22 |
-
"loss": 4.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.46875,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
"learning_rate": 0.0009765625,
|
| 29 |
-
"loss": 4.
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.625,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
"learning_rate": 0.00096875,
|
| 36 |
-
"loss": 4.
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.78125,
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
"learning_rate": 0.0009609375,
|
| 43 |
-
"loss": 4.
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.9375,
|
| 48 |
-
"grad_norm": 1.
|
| 49 |
"learning_rate": 0.000953125,
|
| 50 |
-
"loss": 4.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.0,
|
| 55 |
-
"eval_accuracy": 0.
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
|
|
|
|
|
|
|
|
|
| 60 |
"step": 32
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 1.09375,
|
| 64 |
-
"grad_norm":
|
| 65 |
"learning_rate": 0.0009453125,
|
| 66 |
-
"loss": 4.
|
| 67 |
"step": 35
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"epoch": 1.25,
|
| 71 |
-
"grad_norm": 1.
|
| 72 |
"learning_rate": 0.0009375,
|
| 73 |
-
"loss":
|
| 74 |
"step": 40
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 1.40625,
|
| 78 |
-
"grad_norm": 2.
|
| 79 |
"learning_rate": 0.0009296875000000001,
|
| 80 |
-
"loss": 3.
|
| 81 |
"step": 45
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 1.5625,
|
| 85 |
-
"grad_norm": 2.
|
| 86 |
"learning_rate": 0.0009218750000000001,
|
| 87 |
-
"loss": 3.
|
| 88 |
"step": 50
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.71875,
|
| 92 |
-
"grad_norm": 2.
|
| 93 |
"learning_rate": 0.0009140625,
|
| 94 |
-
"loss": 3.
|
| 95 |
"step": 55
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.875,
|
| 99 |
-
"grad_norm":
|
| 100 |
"learning_rate": 0.00090625,
|
| 101 |
-
"loss": 2.
|
| 102 |
"step": 60
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 2.0,
|
| 106 |
-
"eval_accuracy": 0.
|
| 107 |
-
"
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
-
"
|
|
|
|
|
|
|
|
|
|
| 111 |
"step": 64
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 2.03125,
|
| 115 |
-
"grad_norm":
|
| 116 |
"learning_rate": 0.0008984375,
|
| 117 |
-
"loss": 2.
|
| 118 |
"step": 65
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 2.1875,
|
| 122 |
-
"grad_norm": 2.
|
| 123 |
"learning_rate": 0.000890625,
|
| 124 |
-
"loss": 2.
|
| 125 |
"step": 70
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 2.34375,
|
| 129 |
-
"grad_norm": 2.
|
| 130 |
"learning_rate": 0.0008828125,
|
| 131 |
-
"loss": 1.
|
| 132 |
"step": 75
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.5,
|
| 136 |
-
"grad_norm":
|
| 137 |
"learning_rate": 0.000875,
|
| 138 |
-
"loss": 1.
|
| 139 |
"step": 80
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.65625,
|
| 143 |
-
"grad_norm": 2.
|
| 144 |
"learning_rate": 0.0008671875,
|
| 145 |
-
"loss": 1.
|
| 146 |
"step": 85
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 2.8125,
|
| 150 |
-
"grad_norm":
|
| 151 |
"learning_rate": 0.000859375,
|
| 152 |
-
"loss": 1.
|
| 153 |
"step": 90
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 2.96875,
|
| 157 |
-
"grad_norm": 3.
|
| 158 |
"learning_rate": 0.0008515625,
|
| 159 |
-
"loss": 1.
|
| 160 |
"step": 95
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 3.0,
|
| 164 |
-
"eval_accuracy": 0.
|
| 165 |
-
"
|
| 166 |
-
"
|
| 167 |
-
"
|
| 168 |
-
"
|
|
|
|
|
|
|
|
|
|
| 169 |
"step": 96
|
| 170 |
},
|
| 171 |
{
|
| 172 |
"epoch": 3.125,
|
| 173 |
-
"grad_norm": 2.
|
| 174 |
"learning_rate": 0.00084375,
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 100
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 3.28125,
|
| 180 |
-
"grad_norm": 2.
|
| 181 |
"learning_rate": 0.0008359375,
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 105
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 3.4375,
|
| 187 |
-
"grad_norm": 2.
|
| 188 |
"learning_rate": 0.000828125,
|
| 189 |
-
"loss": 0.
|
| 190 |
"step": 110
|
| 191 |
},
|
| 192 |
{
|
| 193 |
"epoch": 3.59375,
|
| 194 |
-
"grad_norm": 2.
|
| 195 |
"learning_rate": 0.0008203125,
|
| 196 |
-
"loss": 0.
|
| 197 |
"step": 115
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 3.75,
|
| 201 |
-
"grad_norm":
|
| 202 |
"learning_rate": 0.0008125000000000001,
|
| 203 |
-
"loss": 0.
|
| 204 |
"step": 120
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 3.90625,
|
| 208 |
-
"grad_norm": 2.
|
| 209 |
"learning_rate": 0.0008046875000000001,
|
| 210 |
-
"loss": 0.
|
| 211 |
"step": 125
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"epoch": 4.0,
|
| 215 |
-
"eval_accuracy": 0.
|
| 216 |
-
"
|
| 217 |
-
"
|
| 218 |
-
"
|
| 219 |
-
"
|
|
|
|
|
|
|
|
|
|
| 220 |
"step": 128
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 4.0625,
|
| 224 |
-
"grad_norm": 1.
|
| 225 |
"learning_rate": 0.0007968750000000001,
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 130
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 4.21875,
|
| 231 |
-
"grad_norm":
|
| 232 |
"learning_rate": 0.0007890625,
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 135
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 4.375,
|
| 238 |
-
"grad_norm": 1.
|
| 239 |
"learning_rate": 0.00078125,
|
| 240 |
-
"loss": 0.
|
| 241 |
"step": 140
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 4.53125,
|
| 245 |
-
"grad_norm": 1.
|
| 246 |
"learning_rate": 0.0007734375,
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 145
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 4.6875,
|
| 252 |
-
"grad_norm": 1.
|
| 253 |
"learning_rate": 0.000765625,
|
| 254 |
-
"loss": 0.
|
| 255 |
"step": 150
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 4.84375,
|
| 259 |
-
"grad_norm":
|
| 260 |
"learning_rate": 0.0007578125,
|
| 261 |
-
"loss": 0.
|
| 262 |
"step": 155
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 5.0,
|
| 266 |
-
"grad_norm": 1.
|
| 267 |
"learning_rate": 0.00075,
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 160
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 5.0,
|
| 273 |
-
"eval_accuracy": 0.
|
| 274 |
-
"
|
| 275 |
-
"
|
| 276 |
-
"
|
| 277 |
-
"
|
|
|
|
|
|
|
|
|
|
| 278 |
"step": 160
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 5.15625,
|
| 282 |
-
"grad_norm": 0.
|
| 283 |
"learning_rate": 0.0007421875,
|
| 284 |
-
"loss": 0.
|
| 285 |
"step": 165
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 5.3125,
|
| 289 |
-
"grad_norm": 0.
|
| 290 |
"learning_rate": 0.000734375,
|
| 291 |
-
"loss": 0.
|
| 292 |
"step": 170
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 5.46875,
|
| 296 |
-
"grad_norm":
|
| 297 |
"learning_rate": 0.0007265625,
|
| 298 |
-
"loss": 0.
|
| 299 |
"step": 175
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 5.625,
|
| 303 |
-
"grad_norm": 0.
|
| 304 |
"learning_rate": 0.00071875,
|
| 305 |
-
"loss": 0.
|
| 306 |
"step": 180
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 5.78125,
|
| 310 |
-
"grad_norm": 1.
|
| 311 |
"learning_rate": 0.0007109375,
|
| 312 |
-
"loss": 0.
|
| 313 |
"step": 185
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 5.9375,
|
| 317 |
-
"grad_norm":
|
| 318 |
"learning_rate": 0.000703125,
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 190
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 6.0,
|
| 324 |
-
"eval_accuracy": 0.
|
| 325 |
-
"
|
| 326 |
-
"
|
| 327 |
-
"
|
| 328 |
-
"
|
|
|
|
|
|
|
|
|
|
| 329 |
"step": 192
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 6.09375,
|
| 333 |
-
"grad_norm":
|
| 334 |
"learning_rate": 0.0006953125,
|
| 335 |
-
"loss": 0.
|
| 336 |
"step": 195
|
| 337 |
},
|
| 338 |
{
|
| 339 |
"epoch": 6.25,
|
| 340 |
-
"grad_norm":
|
| 341 |
"learning_rate": 0.0006875,
|
| 342 |
-
"loss": 0.
|
| 343 |
"step": 200
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 6.40625,
|
| 347 |
-
"grad_norm": 1.
|
| 348 |
"learning_rate": 0.0006796875000000001,
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 205
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 6.5625,
|
| 354 |
-
"grad_norm":
|
| 355 |
"learning_rate": 0.0006718750000000001,
|
| 356 |
-
"loss": 0.
|
| 357 |
"step": 210
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 6.71875,
|
| 361 |
-
"grad_norm": 0.
|
| 362 |
"learning_rate": 0.0006640625,
|
| 363 |
-
"loss": 0.
|
| 364 |
"step": 215
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 6.875,
|
| 368 |
-
"grad_norm": 0.
|
| 369 |
"learning_rate": 0.00065625,
|
| 370 |
-
"loss": 0.
|
| 371 |
"step": 220
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 7.0,
|
| 375 |
-
"eval_accuracy": 0.
|
| 376 |
-
"
|
| 377 |
-
"
|
| 378 |
-
"
|
| 379 |
-
"
|
|
|
|
|
|
|
|
|
|
| 380 |
"step": 224
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 7.03125,
|
| 384 |
-
"grad_norm": 0.
|
| 385 |
"learning_rate": 0.0006484375,
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 225
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 7.1875,
|
| 391 |
-
"grad_norm": 0.
|
| 392 |
"learning_rate": 0.000640625,
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 230
|
| 395 |
},
|
| 396 |
{
|
| 397 |
"epoch": 7.34375,
|
| 398 |
-
"grad_norm": 0.
|
| 399 |
"learning_rate": 0.0006328125,
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 235
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 7.5,
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
"learning_rate": 0.000625,
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 240
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 7.65625,
|
| 412 |
-
"grad_norm": 0.
|
| 413 |
"learning_rate": 0.0006171875,
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 245
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 7.8125,
|
| 419 |
-
"grad_norm":
|
| 420 |
"learning_rate": 0.000609375,
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 250
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 7.96875,
|
| 426 |
-
"grad_norm":
|
| 427 |
"learning_rate": 0.0006015625,
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 255
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 8.0,
|
| 433 |
-
"eval_accuracy": 0.
|
| 434 |
-
"
|
| 435 |
-
"
|
| 436 |
-
"
|
| 437 |
-
"
|
|
|
|
|
|
|
|
|
|
| 438 |
"step": 256
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 8.125,
|
| 442 |
-
"grad_norm": 0.
|
| 443 |
"learning_rate": 0.00059375,
|
| 444 |
-
"loss": 0.
|
| 445 |
"step": 260
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 8.28125,
|
| 449 |
-
"grad_norm": 0.
|
| 450 |
"learning_rate": 0.0005859375,
|
| 451 |
-
"loss": 0.
|
| 452 |
"step": 265
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 8.4375,
|
| 456 |
-
"grad_norm": 0.
|
| 457 |
"learning_rate": 0.000578125,
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 270
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 8.59375,
|
| 463 |
-
"grad_norm": 0.
|
| 464 |
"learning_rate": 0.0005703125,
|
| 465 |
-
"loss": 0.
|
| 466 |
"step": 275
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 8.75,
|
| 470 |
-
"grad_norm": 0.
|
| 471 |
"learning_rate": 0.0005625000000000001,
|
| 472 |
-
"loss": 0.
|
| 473 |
"step": 280
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 8.90625,
|
| 477 |
-
"grad_norm": 0.
|
| 478 |
"learning_rate": 0.0005546875000000001,
|
| 479 |
-
"loss": 0.
|
| 480 |
"step": 285
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 9.0,
|
| 484 |
-
"eval_accuracy": 0.
|
| 485 |
-
"
|
| 486 |
-
"
|
| 487 |
-
"
|
| 488 |
-
"
|
|
|
|
|
|
|
|
|
|
| 489 |
"step": 288
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 9.0625,
|
| 493 |
-
"grad_norm": 0.
|
| 494 |
"learning_rate": 0.000546875,
|
| 495 |
-
"loss": 0.
|
| 496 |
"step": 290
|
| 497 |
},
|
| 498 |
{
|
| 499 |
"epoch": 9.21875,
|
| 500 |
-
"grad_norm": 0.
|
| 501 |
"learning_rate": 0.0005390625,
|
| 502 |
-
"loss": 0.
|
| 503 |
"step": 295
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 9.375,
|
| 507 |
-
"grad_norm": 0.
|
| 508 |
"learning_rate": 0.00053125,
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 300
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 9.53125,
|
| 514 |
-
"grad_norm": 0.
|
| 515 |
"learning_rate": 0.0005234375,
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 305
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 9.6875,
|
| 521 |
-
"grad_norm": 0.
|
| 522 |
"learning_rate": 0.000515625,
|
| 523 |
-
"loss": 0.
|
| 524 |
"step": 310
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 9.84375,
|
| 528 |
-
"grad_norm": 0.
|
| 529 |
"learning_rate": 0.0005078125,
|
| 530 |
-
"loss": 0.
|
| 531 |
"step": 315
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 10.0,
|
| 535 |
-
"grad_norm": 0.
|
| 536 |
"learning_rate": 0.0005,
|
| 537 |
-
"loss": 0.
|
| 538 |
"step": 320
|
| 539 |
},
|
| 540 |
{
|
| 541 |
"epoch": 10.0,
|
| 542 |
-
"eval_accuracy": 0.
|
| 543 |
-
"
|
| 544 |
-
"
|
| 545 |
-
"
|
| 546 |
-
"
|
|
|
|
|
|
|
|
|
|
| 547 |
"step": 320
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 10.15625,
|
| 551 |
-
"grad_norm": 0.
|
| 552 |
"learning_rate": 0.0004921875,
|
| 553 |
"loss": 0.0045,
|
| 554 |
"step": 325
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 10.3125,
|
| 558 |
-
"grad_norm":
|
| 559 |
"learning_rate": 0.000484375,
|
| 560 |
-
"loss": 0.
|
| 561 |
"step": 330
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 10.46875,
|
| 565 |
-
"grad_norm": 0.
|
| 566 |
"learning_rate": 0.0004765625,
|
| 567 |
-
"loss": 0.
|
| 568 |
"step": 335
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 10.625,
|
| 572 |
-
"grad_norm": 0.
|
| 573 |
"learning_rate": 0.00046875,
|
| 574 |
-
"loss": 0.
|
| 575 |
"step": 340
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 10.78125,
|
| 579 |
-
"grad_norm": 0.
|
| 580 |
"learning_rate": 0.00046093750000000003,
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 345
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 10.9375,
|
| 586 |
-
"grad_norm": 0.
|
| 587 |
"learning_rate": 0.000453125,
|
| 588 |
-
"loss": 0.
|
| 589 |
"step": 350
|
| 590 |
},
|
| 591 |
{
|
| 592 |
"epoch": 11.0,
|
| 593 |
-
"eval_accuracy": 0.
|
| 594 |
-
"
|
| 595 |
-
"
|
| 596 |
-
"
|
| 597 |
-
"
|
|
|
|
|
|
|
|
|
|
| 598 |
"step": 352
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 11.09375,
|
| 602 |
-
"grad_norm": 0.
|
| 603 |
"learning_rate": 0.0004453125,
|
| 604 |
-
"loss": 0.
|
| 605 |
"step": 355
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 11.25,
|
| 609 |
-
"grad_norm": 0.
|
| 610 |
"learning_rate": 0.0004375,
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 360
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 11.40625,
|
| 616 |
-
"grad_norm": 0.
|
| 617 |
"learning_rate": 0.0004296875,
|
| 618 |
-
"loss": 0.
|
| 619 |
"step": 365
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 11.5625,
|
| 623 |
-
"grad_norm": 0.
|
| 624 |
"learning_rate": 0.000421875,
|
| 625 |
-
"loss": 0.
|
| 626 |
"step": 370
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 11.71875,
|
| 630 |
-
"grad_norm": 0.
|
| 631 |
"learning_rate": 0.0004140625,
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 375
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 11.875,
|
| 637 |
-
"grad_norm": 0.
|
| 638 |
"learning_rate": 0.00040625000000000004,
|
| 639 |
-
"loss": 0.
|
| 640 |
"step": 380
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 12.0,
|
| 644 |
-
"eval_accuracy": 0.
|
| 645 |
-
"
|
| 646 |
-
"
|
| 647 |
-
"
|
| 648 |
-
"
|
|
|
|
|
|
|
|
|
|
| 649 |
"step": 384
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 12.03125,
|
| 653 |
-
"grad_norm": 0.
|
| 654 |
"learning_rate": 0.00039843750000000003,
|
| 655 |
-
"loss": 0.
|
| 656 |
"step": 385
|
| 657 |
},
|
| 658 |
{
|
| 659 |
"epoch": 12.1875,
|
| 660 |
-
"grad_norm": 0.
|
| 661 |
"learning_rate": 0.000390625,
|
| 662 |
-
"loss": 0.
|
| 663 |
"step": 390
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 12.34375,
|
| 667 |
-
"grad_norm": 0.
|
| 668 |
"learning_rate": 0.0003828125,
|
| 669 |
-
"loss": 0.
|
| 670 |
"step": 395
|
| 671 |
},
|
| 672 |
{
|
| 673 |
"epoch": 12.5,
|
| 674 |
-
"grad_norm": 0.
|
| 675 |
"learning_rate": 0.000375,
|
| 676 |
-
"loss": 0.
|
| 677 |
"step": 400
|
| 678 |
},
|
| 679 |
{
|
| 680 |
"epoch": 12.65625,
|
| 681 |
-
"grad_norm": 0.
|
| 682 |
"learning_rate": 0.0003671875,
|
| 683 |
-
"loss": 0.
|
| 684 |
"step": 405
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 12.8125,
|
| 688 |
-
"grad_norm": 0.
|
| 689 |
"learning_rate": 0.000359375,
|
| 690 |
-
"loss": 0.
|
| 691 |
"step": 410
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 12.96875,
|
| 695 |
-
"grad_norm": 0.
|
| 696 |
"learning_rate": 0.0003515625,
|
| 697 |
-
"loss": 0.
|
| 698 |
"step": 415
|
| 699 |
},
|
| 700 |
{
|
| 701 |
"epoch": 13.0,
|
| 702 |
-
"eval_accuracy": 0.
|
| 703 |
-
"
|
| 704 |
-
"
|
| 705 |
-
"
|
| 706 |
-
"
|
|
|
|
|
|
|
|
|
|
| 707 |
"step": 416
|
| 708 |
},
|
| 709 |
{
|
| 710 |
"epoch": 13.125,
|
| 711 |
-
"grad_norm": 0.
|
| 712 |
"learning_rate": 0.00034375,
|
| 713 |
-
"loss": 0.
|
| 714 |
"step": 420
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 13.28125,
|
| 718 |
-
"grad_norm": 0.
|
| 719 |
"learning_rate": 0.00033593750000000003,
|
| 720 |
-
"loss": 0.
|
| 721 |
"step": 425
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 13.4375,
|
| 725 |
-
"grad_norm": 0.
|
| 726 |
"learning_rate": 0.000328125,
|
| 727 |
-
"loss": 0.
|
| 728 |
"step": 430
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"epoch": 13.59375,
|
| 732 |
-
"grad_norm": 0.
|
| 733 |
"learning_rate": 0.0003203125,
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 435
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 13.75,
|
| 739 |
-
"grad_norm": 0.
|
| 740 |
"learning_rate": 0.0003125,
|
| 741 |
-
"loss": 0.
|
| 742 |
"step": 440
|
| 743 |
},
|
| 744 |
{
|
| 745 |
"epoch": 13.90625,
|
| 746 |
-
"grad_norm": 0.
|
| 747 |
"learning_rate": 0.0003046875,
|
| 748 |
-
"loss": 0.
|
| 749 |
"step": 445
|
| 750 |
},
|
| 751 |
{
|
| 752 |
"epoch": 14.0,
|
| 753 |
-
"eval_accuracy": 0.
|
| 754 |
-
"
|
| 755 |
-
"
|
| 756 |
-
"
|
| 757 |
-
"
|
|
|
|
|
|
|
|
|
|
| 758 |
"step": 448
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch": 14.
|
| 762 |
-
"
|
| 763 |
-
"
|
| 764 |
-
"
|
| 765 |
-
"
|
| 766 |
-
|
| 767 |
-
|
| 768 |
-
"epoch": 14.21875,
|
| 769 |
-
"grad_norm": 0.021257249638438225,
|
| 770 |
-
"learning_rate": 0.0002890625,
|
| 771 |
-
"loss": 0.0026,
|
| 772 |
-
"step": 455
|
| 773 |
-
},
|
| 774 |
-
{
|
| 775 |
-
"epoch": 14.375,
|
| 776 |
-
"grad_norm": 0.032649360597133636,
|
| 777 |
-
"learning_rate": 0.00028125000000000003,
|
| 778 |
-
"loss": 0.002,
|
| 779 |
-
"step": 460
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 14.53125,
|
| 783 |
-
"grad_norm": 0.022741030901670456,
|
| 784 |
-
"learning_rate": 0.0002734375,
|
| 785 |
-
"loss": 0.007,
|
| 786 |
-
"step": 465
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 14.6875,
|
| 790 |
-
"grad_norm": 0.020442800596356392,
|
| 791 |
-
"learning_rate": 0.000265625,
|
| 792 |
-
"loss": 0.0023,
|
| 793 |
-
"step": 470
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"epoch": 14.84375,
|
| 797 |
-
"grad_norm": 0.022834857925772667,
|
| 798 |
-
"learning_rate": 0.0002578125,
|
| 799 |
-
"loss": 0.0031,
|
| 800 |
-
"step": 475
|
| 801 |
-
},
|
| 802 |
-
{
|
| 803 |
-
"epoch": 15.0,
|
| 804 |
-
"grad_norm": 0.014007111079990864,
|
| 805 |
-
"learning_rate": 0.00025,
|
| 806 |
-
"loss": 0.0028,
|
| 807 |
-
"step": 480
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 15.0,
|
| 811 |
-
"eval_accuracy": 0.8441176470588235,
|
| 812 |
-
"eval_loss": 0.5926622748374939,
|
| 813 |
-
"eval_runtime": 16.2356,
|
| 814 |
-
"eval_samples_per_second": 62.825,
|
| 815 |
-
"eval_steps_per_second": 1.971,
|
| 816 |
-
"step": 480
|
| 817 |
-
},
|
| 818 |
-
{
|
| 819 |
-
"epoch": 15.15625,
|
| 820 |
-
"grad_norm": 0.00949984509497881,
|
| 821 |
-
"learning_rate": 0.0002421875,
|
| 822 |
-
"loss": 0.0023,
|
| 823 |
-
"step": 485
|
| 824 |
-
},
|
| 825 |
-
{
|
| 826 |
-
"epoch": 15.3125,
|
| 827 |
-
"grad_norm": 0.04143200442194939,
|
| 828 |
-
"learning_rate": 0.000234375,
|
| 829 |
-
"loss": 0.0021,
|
| 830 |
-
"step": 490
|
| 831 |
-
},
|
| 832 |
-
{
|
| 833 |
-
"epoch": 15.46875,
|
| 834 |
-
"grad_norm": 0.012401225045323372,
|
| 835 |
-
"learning_rate": 0.0002265625,
|
| 836 |
-
"loss": 0.0021,
|
| 837 |
-
"step": 495
|
| 838 |
-
},
|
| 839 |
-
{
|
| 840 |
-
"epoch": 15.625,
|
| 841 |
-
"grad_norm": 0.040582917630672455,
|
| 842 |
-
"learning_rate": 0.00021875,
|
| 843 |
-
"loss": 0.0031,
|
| 844 |
-
"step": 500
|
| 845 |
-
},
|
| 846 |
-
{
|
| 847 |
-
"epoch": 15.78125,
|
| 848 |
-
"grad_norm": 0.025907032191753387,
|
| 849 |
-
"learning_rate": 0.0002109375,
|
| 850 |
-
"loss": 0.0021,
|
| 851 |
-
"step": 505
|
| 852 |
-
},
|
| 853 |
-
{
|
| 854 |
-
"epoch": 15.9375,
|
| 855 |
-
"grad_norm": 0.008175536058843136,
|
| 856 |
-
"learning_rate": 0.00020312500000000002,
|
| 857 |
-
"loss": 0.0023,
|
| 858 |
-
"step": 510
|
| 859 |
-
},
|
| 860 |
-
{
|
| 861 |
-
"epoch": 16.0,
|
| 862 |
-
"eval_accuracy": 0.8519607843137255,
|
| 863 |
-
"eval_loss": 0.5878445506095886,
|
| 864 |
-
"eval_runtime": 16.1518,
|
| 865 |
-
"eval_samples_per_second": 63.151,
|
| 866 |
-
"eval_steps_per_second": 1.981,
|
| 867 |
-
"step": 512
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 16.09375,
|
| 871 |
-
"grad_norm": 0.3129185140132904,
|
| 872 |
-
"learning_rate": 0.0001953125,
|
| 873 |
-
"loss": 0.0044,
|
| 874 |
-
"step": 515
|
| 875 |
-
},
|
| 876 |
-
{
|
| 877 |
-
"epoch": 16.25,
|
| 878 |
-
"grad_norm": 0.030808325856924057,
|
| 879 |
-
"learning_rate": 0.0001875,
|
| 880 |
-
"loss": 0.0036,
|
| 881 |
-
"step": 520
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"epoch": 16.40625,
|
| 885 |
-
"grad_norm": 0.019886957481503487,
|
| 886 |
-
"learning_rate": 0.0001796875,
|
| 887 |
-
"loss": 0.0026,
|
| 888 |
-
"step": 525
|
| 889 |
-
},
|
| 890 |
-
{
|
| 891 |
-
"epoch": 16.5625,
|
| 892 |
-
"grad_norm": 0.019268082454800606,
|
| 893 |
-
"learning_rate": 0.000171875,
|
| 894 |
-
"loss": 0.0034,
|
| 895 |
-
"step": 530
|
| 896 |
-
},
|
| 897 |
-
{
|
| 898 |
-
"epoch": 16.71875,
|
| 899 |
-
"grad_norm": 0.025241246446967125,
|
| 900 |
-
"learning_rate": 0.0001640625,
|
| 901 |
-
"loss": 0.0019,
|
| 902 |
-
"step": 535
|
| 903 |
-
},
|
| 904 |
-
{
|
| 905 |
-
"epoch": 16.875,
|
| 906 |
-
"grad_norm": 0.01479440089315176,
|
| 907 |
-
"learning_rate": 0.00015625,
|
| 908 |
-
"loss": 0.0027,
|
| 909 |
-
"step": 540
|
| 910 |
-
},
|
| 911 |
-
{
|
| 912 |
-
"epoch": 17.0,
|
| 913 |
-
"eval_accuracy": 0.8470588235294118,
|
| 914 |
-
"eval_loss": 0.5872153043746948,
|
| 915 |
-
"eval_runtime": 16.056,
|
| 916 |
-
"eval_samples_per_second": 63.528,
|
| 917 |
-
"eval_steps_per_second": 1.993,
|
| 918 |
-
"step": 544
|
| 919 |
-
},
|
| 920 |
-
{
|
| 921 |
-
"epoch": 17.03125,
|
| 922 |
-
"grad_norm": 0.01011387724429369,
|
| 923 |
-
"learning_rate": 0.0001484375,
|
| 924 |
-
"loss": 0.0019,
|
| 925 |
-
"step": 545
|
| 926 |
-
},
|
| 927 |
-
{
|
| 928 |
-
"epoch": 17.1875,
|
| 929 |
-
"grad_norm": 0.020896941423416138,
|
| 930 |
-
"learning_rate": 0.00014062500000000002,
|
| 931 |
-
"loss": 0.0022,
|
| 932 |
-
"step": 550
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 17.34375,
|
| 936 |
-
"grad_norm": 0.040105391293764114,
|
| 937 |
-
"learning_rate": 0.0001328125,
|
| 938 |
-
"loss": 0.002,
|
| 939 |
-
"step": 555
|
| 940 |
-
},
|
| 941 |
-
{
|
| 942 |
-
"epoch": 17.5,
|
| 943 |
-
"grad_norm": 0.016236811876296997,
|
| 944 |
-
"learning_rate": 0.000125,
|
| 945 |
-
"loss": 0.0024,
|
| 946 |
-
"step": 560
|
| 947 |
-
},
|
| 948 |
-
{
|
| 949 |
-
"epoch": 17.65625,
|
| 950 |
-
"grad_norm": 0.010203810408711433,
|
| 951 |
-
"learning_rate": 0.0001171875,
|
| 952 |
-
"loss": 0.002,
|
| 953 |
-
"step": 565
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 17.8125,
|
| 957 |
-
"grad_norm": 0.01675267145037651,
|
| 958 |
-
"learning_rate": 0.000109375,
|
| 959 |
-
"loss": 0.0019,
|
| 960 |
-
"step": 570
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"epoch": 17.96875,
|
| 964 |
-
"grad_norm": 0.08755680918693542,
|
| 965 |
-
"learning_rate": 0.00010156250000000001,
|
| 966 |
-
"loss": 0.0028,
|
| 967 |
-
"step": 575
|
| 968 |
-
},
|
| 969 |
-
{
|
| 970 |
-
"epoch": 18.0,
|
| 971 |
-
"eval_accuracy": 0.8450980392156863,
|
| 972 |
-
"eval_loss": 0.5891793966293335,
|
| 973 |
-
"eval_runtime": 15.883,
|
| 974 |
-
"eval_samples_per_second": 64.22,
|
| 975 |
-
"eval_steps_per_second": 2.015,
|
| 976 |
-
"step": 576
|
| 977 |
-
},
|
| 978 |
-
{
|
| 979 |
-
"epoch": 18.125,
|
| 980 |
-
"grad_norm": 0.060470979660749435,
|
| 981 |
-
"learning_rate": 9.375e-05,
|
| 982 |
-
"loss": 0.003,
|
| 983 |
-
"step": 580
|
| 984 |
-
},
|
| 985 |
-
{
|
| 986 |
-
"epoch": 18.28125,
|
| 987 |
-
"grad_norm": 0.02452988736331463,
|
| 988 |
-
"learning_rate": 8.59375e-05,
|
| 989 |
-
"loss": 0.0017,
|
| 990 |
-
"step": 585
|
| 991 |
-
},
|
| 992 |
-
{
|
| 993 |
-
"epoch": 18.4375,
|
| 994 |
-
"grad_norm": 0.02058909274637699,
|
| 995 |
-
"learning_rate": 7.8125e-05,
|
| 996 |
-
"loss": 0.002,
|
| 997 |
-
"step": 590
|
| 998 |
-
},
|
| 999 |
-
{
|
| 1000 |
-
"epoch": 18.59375,
|
| 1001 |
-
"grad_norm": 0.01303939614444971,
|
| 1002 |
-
"learning_rate": 7.031250000000001e-05,
|
| 1003 |
-
"loss": 0.0025,
|
| 1004 |
-
"step": 595
|
| 1005 |
-
},
|
| 1006 |
-
{
|
| 1007 |
-
"epoch": 18.75,
|
| 1008 |
-
"grad_norm": 0.006279917433857918,
|
| 1009 |
-
"learning_rate": 6.25e-05,
|
| 1010 |
-
"loss": 0.0027,
|
| 1011 |
-
"step": 600
|
| 1012 |
-
},
|
| 1013 |
-
{
|
| 1014 |
-
"epoch": 18.90625,
|
| 1015 |
-
"grad_norm": 0.022672630846500397,
|
| 1016 |
-
"learning_rate": 5.46875e-05,
|
| 1017 |
-
"loss": 0.002,
|
| 1018 |
-
"step": 605
|
| 1019 |
-
},
|
| 1020 |
-
{
|
| 1021 |
-
"epoch": 19.0,
|
| 1022 |
-
"eval_accuracy": 0.8411764705882353,
|
| 1023 |
-
"eval_loss": 0.5932831764221191,
|
| 1024 |
-
"eval_runtime": 16.4628,
|
| 1025 |
-
"eval_samples_per_second": 61.958,
|
| 1026 |
-
"eval_steps_per_second": 1.944,
|
| 1027 |
-
"step": 608
|
| 1028 |
-
},
|
| 1029 |
-
{
|
| 1030 |
-
"epoch": 19.0625,
|
| 1031 |
-
"grad_norm": 0.15350750088691711,
|
| 1032 |
-
"learning_rate": 4.6875e-05,
|
| 1033 |
-
"loss": 0.0034,
|
| 1034 |
-
"step": 610
|
| 1035 |
-
},
|
| 1036 |
-
{
|
| 1037 |
-
"epoch": 19.21875,
|
| 1038 |
-
"grad_norm": 0.01092343870550394,
|
| 1039 |
-
"learning_rate": 3.90625e-05,
|
| 1040 |
-
"loss": 0.002,
|
| 1041 |
-
"step": 615
|
| 1042 |
-
},
|
| 1043 |
-
{
|
| 1044 |
-
"epoch": 19.375,
|
| 1045 |
-
"grad_norm": 0.008441799320280552,
|
| 1046 |
-
"learning_rate": 3.125e-05,
|
| 1047 |
-
"loss": 0.0022,
|
| 1048 |
-
"step": 620
|
| 1049 |
-
},
|
| 1050 |
-
{
|
| 1051 |
-
"epoch": 19.53125,
|
| 1052 |
-
"grad_norm": 0.012427592650055885,
|
| 1053 |
-
"learning_rate": 2.34375e-05,
|
| 1054 |
-
"loss": 0.0026,
|
| 1055 |
-
"step": 625
|
| 1056 |
-
},
|
| 1057 |
-
{
|
| 1058 |
-
"epoch": 19.6875,
|
| 1059 |
-
"grad_norm": 0.019600288942456245,
|
| 1060 |
-
"learning_rate": 1.5625e-05,
|
| 1061 |
-
"loss": 0.0016,
|
| 1062 |
-
"step": 630
|
| 1063 |
-
},
|
| 1064 |
-
{
|
| 1065 |
-
"epoch": 19.84375,
|
| 1066 |
-
"grad_norm": 0.0400865413248539,
|
| 1067 |
-
"learning_rate": 7.8125e-06,
|
| 1068 |
-
"loss": 0.0031,
|
| 1069 |
-
"step": 635
|
| 1070 |
-
},
|
| 1071 |
-
{
|
| 1072 |
-
"epoch": 20.0,
|
| 1073 |
-
"grad_norm": 0.03250521048903465,
|
| 1074 |
-
"learning_rate": 0.0,
|
| 1075 |
-
"loss": 0.0017,
|
| 1076 |
-
"step": 640
|
| 1077 |
-
},
|
| 1078 |
-
{
|
| 1079 |
-
"epoch": 20.0,
|
| 1080 |
-
"eval_accuracy": 0.85,
|
| 1081 |
-
"eval_loss": 0.5915272235870361,
|
| 1082 |
-
"eval_runtime": 17.7209,
|
| 1083 |
-
"eval_samples_per_second": 57.559,
|
| 1084 |
-
"eval_steps_per_second": 1.806,
|
| 1085 |
-
"step": 640
|
| 1086 |
-
},
|
| 1087 |
-
{
|
| 1088 |
-
"epoch": 20.0,
|
| 1089 |
-
"step": 640,
|
| 1090 |
-
"total_flos": 4.36977436041216e+17,
|
| 1091 |
-
"train_loss": 0.5368185924002319,
|
| 1092 |
-
"train_runtime": 902.6693,
|
| 1093 |
-
"train_samples_per_second": 22.6,
|
| 1094 |
-
"train_steps_per_second": 0.709
|
| 1095 |
}
|
| 1096 |
],
|
| 1097 |
"logging_steps": 5,
|
|
@@ -1100,6 +815,15 @@
|
|
| 1100 |
"num_train_epochs": 20,
|
| 1101 |
"save_steps": 500,
|
| 1102 |
"stateful_callbacks": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1103 |
"TrainerControl": {
|
| 1104 |
"args": {
|
| 1105 |
"should_epoch_stop": false,
|
|
@@ -1111,7 +835,7 @@
|
|
| 1111 |
"attributes": {}
|
| 1112 |
}
|
| 1113 |
},
|
| 1114 |
-
"total_flos":
|
| 1115 |
"train_batch_size": 32,
|
| 1116 |
"trial_name": null,
|
| 1117 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8647058823529412,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-finetuned-oxfordflowers/checkpoint-352",
|
| 4 |
+
"epoch": 14.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 448,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.15625,
|
| 13 |
+
"grad_norm": 1.7320846319198608,
|
| 14 |
"learning_rate": 0.0009921875,
|
| 15 |
+
"loss": 4.6558,
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.3125,
|
| 20 |
+
"grad_norm": 1.359827995300293,
|
| 21 |
"learning_rate": 0.000984375,
|
| 22 |
+
"loss": 4.6228,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.46875,
|
| 27 |
+
"grad_norm": 1.5728328227996826,
|
| 28 |
"learning_rate": 0.0009765625,
|
| 29 |
+
"loss": 4.6629,
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.625,
|
| 34 |
+
"grad_norm": 1.514758586883545,
|
| 35 |
"learning_rate": 0.00096875,
|
| 36 |
+
"loss": 4.6269,
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.78125,
|
| 41 |
+
"grad_norm": 1.0490564107894897,
|
| 42 |
"learning_rate": 0.0009609375,
|
| 43 |
+
"loss": 4.5619,
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.9375,
|
| 48 |
+
"grad_norm": 1.087933897972107,
|
| 49 |
"learning_rate": 0.000953125,
|
| 50 |
+
"loss": 4.5237,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.0,
|
| 55 |
+
"eval_accuracy": 0.34509803921568627,
|
| 56 |
+
"eval_f1": 0.2874778237337216,
|
| 57 |
+
"eval_loss": 4.340012073516846,
|
| 58 |
+
"eval_precision": 0.4128804980040239,
|
| 59 |
+
"eval_recall": 0.34509803921568627,
|
| 60 |
+
"eval_runtime": 16.4984,
|
| 61 |
+
"eval_samples_per_second": 61.824,
|
| 62 |
+
"eval_steps_per_second": 1.94,
|
| 63 |
"step": 32
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 1.09375,
|
| 67 |
+
"grad_norm": 1.3993674516677856,
|
| 68 |
"learning_rate": 0.0009453125,
|
| 69 |
+
"loss": 4.3376,
|
| 70 |
"step": 35
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"epoch": 1.25,
|
| 74 |
+
"grad_norm": 1.5965288877487183,
|
| 75 |
"learning_rate": 0.0009375,
|
| 76 |
+
"loss": 4.0528,
|
| 77 |
"step": 40
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 1.40625,
|
| 81 |
+
"grad_norm": 2.107327938079834,
|
| 82 |
"learning_rate": 0.0009296875000000001,
|
| 83 |
+
"loss": 3.7811,
|
| 84 |
"step": 45
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 1.5625,
|
| 88 |
+
"grad_norm": 2.1875929832458496,
|
| 89 |
"learning_rate": 0.0009218750000000001,
|
| 90 |
+
"loss": 3.3976,
|
| 91 |
"step": 50
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.71875,
|
| 95 |
+
"grad_norm": 2.3979506492614746,
|
| 96 |
"learning_rate": 0.0009140625,
|
| 97 |
+
"loss": 3.0782,
|
| 98 |
"step": 55
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 1.875,
|
| 102 |
+
"grad_norm": 3.099531888961792,
|
| 103 |
"learning_rate": 0.00090625,
|
| 104 |
+
"loss": 2.8508,
|
| 105 |
"step": 60
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 2.0,
|
| 109 |
+
"eval_accuracy": 0.5205882352941177,
|
| 110 |
+
"eval_f1": 0.4815844148221795,
|
| 111 |
+
"eval_loss": 1.9784579277038574,
|
| 112 |
+
"eval_precision": 0.5609503268219397,
|
| 113 |
+
"eval_recall": 0.5205882352941177,
|
| 114 |
+
"eval_runtime": 14.6742,
|
| 115 |
+
"eval_samples_per_second": 69.51,
|
| 116 |
+
"eval_steps_per_second": 2.181,
|
| 117 |
"step": 64
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 2.03125,
|
| 121 |
+
"grad_norm": 3.019045829772949,
|
| 122 |
"learning_rate": 0.0008984375,
|
| 123 |
+
"loss": 2.5847,
|
| 124 |
"step": 65
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 2.1875,
|
| 128 |
+
"grad_norm": 2.6212832927703857,
|
| 129 |
"learning_rate": 0.000890625,
|
| 130 |
+
"loss": 2.0135,
|
| 131 |
"step": 70
|
| 132 |
},
|
| 133 |
{
|
| 134 |
"epoch": 2.34375,
|
| 135 |
+
"grad_norm": 2.5014185905456543,
|
| 136 |
"learning_rate": 0.0008828125,
|
| 137 |
+
"loss": 1.6579,
|
| 138 |
"step": 75
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 2.5,
|
| 142 |
+
"grad_norm": 2.89278244972229,
|
| 143 |
"learning_rate": 0.000875,
|
| 144 |
+
"loss": 1.5167,
|
| 145 |
"step": 80
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 2.65625,
|
| 149 |
+
"grad_norm": 2.6624577045440674,
|
| 150 |
"learning_rate": 0.0008671875,
|
| 151 |
+
"loss": 1.3679,
|
| 152 |
"step": 85
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 2.8125,
|
| 156 |
+
"grad_norm": 2.6109840869903564,
|
| 157 |
"learning_rate": 0.000859375,
|
| 158 |
+
"loss": 1.2521,
|
| 159 |
"step": 90
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 2.96875,
|
| 163 |
+
"grad_norm": 3.0059635639190674,
|
| 164 |
"learning_rate": 0.0008515625,
|
| 165 |
+
"loss": 1.346,
|
| 166 |
"step": 95
|
| 167 |
},
|
| 168 |
{
|
| 169 |
"epoch": 3.0,
|
| 170 |
+
"eval_accuracy": 0.7088235294117647,
|
| 171 |
+
"eval_f1": 0.695694394140452,
|
| 172 |
+
"eval_loss": 1.1449469327926636,
|
| 173 |
+
"eval_precision": 0.7737617026219967,
|
| 174 |
+
"eval_recall": 0.7088235294117647,
|
| 175 |
+
"eval_runtime": 15.7476,
|
| 176 |
+
"eval_samples_per_second": 64.772,
|
| 177 |
+
"eval_steps_per_second": 2.032,
|
| 178 |
"step": 96
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 3.125,
|
| 182 |
+
"grad_norm": 2.714418411254883,
|
| 183 |
"learning_rate": 0.00084375,
|
| 184 |
+
"loss": 0.6888,
|
| 185 |
"step": 100
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 3.28125,
|
| 189 |
+
"grad_norm": 2.7836403846740723,
|
| 190 |
"learning_rate": 0.0008359375,
|
| 191 |
+
"loss": 0.7027,
|
| 192 |
"step": 105
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 3.4375,
|
| 196 |
+
"grad_norm": 2.305562973022461,
|
| 197 |
"learning_rate": 0.000828125,
|
| 198 |
+
"loss": 0.5808,
|
| 199 |
"step": 110
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 3.59375,
|
| 203 |
+
"grad_norm": 2.350442409515381,
|
| 204 |
"learning_rate": 0.0008203125,
|
| 205 |
+
"loss": 0.5346,
|
| 206 |
"step": 115
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 3.75,
|
| 210 |
+
"grad_norm": 1.3235565423965454,
|
| 211 |
"learning_rate": 0.0008125000000000001,
|
| 212 |
+
"loss": 0.4357,
|
| 213 |
"step": 120
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 3.90625,
|
| 217 |
+
"grad_norm": 2.181887626647949,
|
| 218 |
"learning_rate": 0.0008046875000000001,
|
| 219 |
+
"loss": 0.5544,
|
| 220 |
"step": 125
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 4.0,
|
| 224 |
+
"eval_accuracy": 0.753921568627451,
|
| 225 |
+
"eval_f1": 0.7480454731222893,
|
| 226 |
+
"eval_loss": 0.9264965653419495,
|
| 227 |
+
"eval_precision": 0.8162285484733582,
|
| 228 |
+
"eval_recall": 0.753921568627451,
|
| 229 |
+
"eval_runtime": 16.1579,
|
| 230 |
+
"eval_samples_per_second": 63.127,
|
| 231 |
+
"eval_steps_per_second": 1.98,
|
| 232 |
"step": 128
|
| 233 |
},
|
| 234 |
{
|
| 235 |
"epoch": 4.0625,
|
| 236 |
+
"grad_norm": 1.2976504564285278,
|
| 237 |
"learning_rate": 0.0007968750000000001,
|
| 238 |
+
"loss": 0.4729,
|
| 239 |
"step": 130
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 4.21875,
|
| 243 |
+
"grad_norm": 1.4201076030731201,
|
| 244 |
"learning_rate": 0.0007890625,
|
| 245 |
+
"loss": 0.2202,
|
| 246 |
"step": 135
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 4.375,
|
| 250 |
+
"grad_norm": 1.6992279291152954,
|
| 251 |
"learning_rate": 0.00078125,
|
| 252 |
+
"loss": 0.2482,
|
| 253 |
"step": 140
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 4.53125,
|
| 257 |
+
"grad_norm": 1.4370797872543335,
|
| 258 |
"learning_rate": 0.0007734375,
|
| 259 |
+
"loss": 0.2159,
|
| 260 |
"step": 145
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 4.6875,
|
| 264 |
+
"grad_norm": 1.7889351844787598,
|
| 265 |
"learning_rate": 0.000765625,
|
| 266 |
+
"loss": 0.2127,
|
| 267 |
"step": 150
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 4.84375,
|
| 271 |
+
"grad_norm": 0.961966872215271,
|
| 272 |
"learning_rate": 0.0007578125,
|
| 273 |
+
"loss": 0.2415,
|
| 274 |
"step": 155
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 5.0,
|
| 278 |
+
"grad_norm": 1.1151365041732788,
|
| 279 |
"learning_rate": 0.00075,
|
| 280 |
+
"loss": 0.1847,
|
| 281 |
"step": 160
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 5.0,
|
| 285 |
+
"eval_accuracy": 0.8029411764705883,
|
| 286 |
+
"eval_f1": 0.7996802939138055,
|
| 287 |
+
"eval_loss": 0.775350034236908,
|
| 288 |
+
"eval_precision": 0.8323794596323556,
|
| 289 |
+
"eval_recall": 0.8029411764705883,
|
| 290 |
+
"eval_runtime": 16.7669,
|
| 291 |
+
"eval_samples_per_second": 60.834,
|
| 292 |
+
"eval_steps_per_second": 1.909,
|
| 293 |
"step": 160
|
| 294 |
},
|
| 295 |
{
|
| 296 |
"epoch": 5.15625,
|
| 297 |
+
"grad_norm": 0.6469184756278992,
|
| 298 |
"learning_rate": 0.0007421875,
|
| 299 |
+
"loss": 0.1029,
|
| 300 |
"step": 165
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 5.3125,
|
| 304 |
+
"grad_norm": 0.43876633048057556,
|
| 305 |
"learning_rate": 0.000734375,
|
| 306 |
+
"loss": 0.0573,
|
| 307 |
"step": 170
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 5.46875,
|
| 311 |
+
"grad_norm": 0.9715489149093628,
|
| 312 |
"learning_rate": 0.0007265625,
|
| 313 |
+
"loss": 0.073,
|
| 314 |
"step": 175
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 5.625,
|
| 318 |
+
"grad_norm": 0.6452958583831787,
|
| 319 |
"learning_rate": 0.00071875,
|
| 320 |
+
"loss": 0.1527,
|
| 321 |
"step": 180
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 5.78125,
|
| 325 |
+
"grad_norm": 1.4150739908218384,
|
| 326 |
"learning_rate": 0.0007109375,
|
| 327 |
+
"loss": 0.0969,
|
| 328 |
"step": 185
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 5.9375,
|
| 332 |
+
"grad_norm": 0.9330568313598633,
|
| 333 |
"learning_rate": 0.000703125,
|
| 334 |
+
"loss": 0.0863,
|
| 335 |
"step": 190
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 6.0,
|
| 339 |
+
"eval_accuracy": 0.8019607843137255,
|
| 340 |
+
"eval_f1": 0.80000704547531,
|
| 341 |
+
"eval_loss": 0.7392613887786865,
|
| 342 |
+
"eval_precision": 0.8450064476152622,
|
| 343 |
+
"eval_recall": 0.8019607843137255,
|
| 344 |
+
"eval_runtime": 14.7972,
|
| 345 |
+
"eval_samples_per_second": 68.932,
|
| 346 |
+
"eval_steps_per_second": 2.163,
|
| 347 |
"step": 192
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 6.09375,
|
| 351 |
+
"grad_norm": 0.7720392346382141,
|
| 352 |
"learning_rate": 0.0006953125,
|
| 353 |
+
"loss": 0.071,
|
| 354 |
"step": 195
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 6.25,
|
| 358 |
+
"grad_norm": 1.0389519929885864,
|
| 359 |
"learning_rate": 0.0006875,
|
| 360 |
+
"loss": 0.0748,
|
| 361 |
"step": 200
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 6.40625,
|
| 365 |
+
"grad_norm": 1.150804042816162,
|
| 366 |
"learning_rate": 0.0006796875000000001,
|
| 367 |
+
"loss": 0.0419,
|
| 368 |
"step": 205
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 6.5625,
|
| 372 |
+
"grad_norm": 2.15278959274292,
|
| 373 |
"learning_rate": 0.0006718750000000001,
|
| 374 |
+
"loss": 0.0953,
|
| 375 |
"step": 210
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 6.71875,
|
| 379 |
+
"grad_norm": 0.3684898912906647,
|
| 380 |
"learning_rate": 0.0006640625,
|
| 381 |
+
"loss": 0.051,
|
| 382 |
"step": 215
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"epoch": 6.875,
|
| 386 |
+
"grad_norm": 0.40336862206459045,
|
| 387 |
"learning_rate": 0.00065625,
|
| 388 |
+
"loss": 0.0516,
|
| 389 |
"step": 220
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 7.0,
|
| 393 |
+
"eval_accuracy": 0.8284313725490197,
|
| 394 |
+
"eval_f1": 0.8258508358061349,
|
| 395 |
+
"eval_loss": 0.6630767583847046,
|
| 396 |
+
"eval_precision": 0.8569142400730454,
|
| 397 |
+
"eval_recall": 0.8284313725490197,
|
| 398 |
+
"eval_runtime": 14.5794,
|
| 399 |
+
"eval_samples_per_second": 69.962,
|
| 400 |
+
"eval_steps_per_second": 2.195,
|
| 401 |
"step": 224
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 7.03125,
|
| 405 |
+
"grad_norm": 0.3206132650375366,
|
| 406 |
"learning_rate": 0.0006484375,
|
| 407 |
+
"loss": 0.0309,
|
| 408 |
"step": 225
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 7.1875,
|
| 412 |
+
"grad_norm": 0.5986069440841675,
|
| 413 |
"learning_rate": 0.000640625,
|
| 414 |
+
"loss": 0.0247,
|
| 415 |
"step": 230
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 7.34375,
|
| 419 |
+
"grad_norm": 0.12066510319709778,
|
| 420 |
"learning_rate": 0.0006328125,
|
| 421 |
+
"loss": 0.0395,
|
| 422 |
"step": 235
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 7.5,
|
| 426 |
+
"grad_norm": 0.16991862654685974,
|
| 427 |
"learning_rate": 0.000625,
|
| 428 |
+
"loss": 0.0355,
|
| 429 |
"step": 240
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 7.65625,
|
| 433 |
+
"grad_norm": 0.12674580514431,
|
| 434 |
"learning_rate": 0.0006171875,
|
| 435 |
+
"loss": 0.0223,
|
| 436 |
"step": 245
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 7.8125,
|
| 440 |
+
"grad_norm": 0.26299160718917847,
|
| 441 |
"learning_rate": 0.000609375,
|
| 442 |
+
"loss": 0.0229,
|
| 443 |
"step": 250
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 7.96875,
|
| 447 |
+
"grad_norm": 1.2256274223327637,
|
| 448 |
"learning_rate": 0.0006015625,
|
| 449 |
+
"loss": 0.023,
|
| 450 |
"step": 255
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"epoch": 8.0,
|
| 454 |
+
"eval_accuracy": 0.8470588235294118,
|
| 455 |
+
"eval_f1": 0.8428671541662826,
|
| 456 |
+
"eval_loss": 0.587995171546936,
|
| 457 |
+
"eval_precision": 0.863074478385897,
|
| 458 |
+
"eval_recall": 0.8470588235294118,
|
| 459 |
+
"eval_runtime": 14.5991,
|
| 460 |
+
"eval_samples_per_second": 69.867,
|
| 461 |
+
"eval_steps_per_second": 2.192,
|
| 462 |
"step": 256
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 8.125,
|
| 466 |
+
"grad_norm": 0.1445535123348236,
|
| 467 |
"learning_rate": 0.00059375,
|
| 468 |
+
"loss": 0.0148,
|
| 469 |
"step": 260
|
| 470 |
},
|
| 471 |
{
|
| 472 |
"epoch": 8.28125,
|
| 473 |
+
"grad_norm": 0.80363529920578,
|
| 474 |
"learning_rate": 0.0005859375,
|
| 475 |
+
"loss": 0.0138,
|
| 476 |
"step": 265
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 8.4375,
|
| 480 |
+
"grad_norm": 0.08668403327465057,
|
| 481 |
"learning_rate": 0.000578125,
|
| 482 |
+
"loss": 0.0133,
|
| 483 |
"step": 270
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 8.59375,
|
| 487 |
+
"grad_norm": 0.14351984858512878,
|
| 488 |
"learning_rate": 0.0005703125,
|
| 489 |
+
"loss": 0.0091,
|
| 490 |
"step": 275
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 8.75,
|
| 494 |
+
"grad_norm": 0.21965286135673523,
|
| 495 |
"learning_rate": 0.0005625000000000001,
|
| 496 |
+
"loss": 0.0096,
|
| 497 |
"step": 280
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 8.90625,
|
| 501 |
+
"grad_norm": 0.2289452701807022,
|
| 502 |
"learning_rate": 0.0005546875000000001,
|
| 503 |
+
"loss": 0.011,
|
| 504 |
"step": 285
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 9.0,
|
| 508 |
+
"eval_accuracy": 0.8568627450980392,
|
| 509 |
+
"eval_f1": 0.8520284357156945,
|
| 510 |
+
"eval_loss": 0.5421529412269592,
|
| 511 |
+
"eval_precision": 0.8685615038556214,
|
| 512 |
+
"eval_recall": 0.8568627450980392,
|
| 513 |
+
"eval_runtime": 15.0954,
|
| 514 |
+
"eval_samples_per_second": 67.57,
|
| 515 |
+
"eval_steps_per_second": 2.12,
|
| 516 |
"step": 288
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 9.0625,
|
| 520 |
+
"grad_norm": 0.08616359531879425,
|
| 521 |
"learning_rate": 0.000546875,
|
| 522 |
+
"loss": 0.028,
|
| 523 |
"step": 290
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 9.21875,
|
| 527 |
+
"grad_norm": 0.09607744216918945,
|
| 528 |
"learning_rate": 0.0005390625,
|
| 529 |
+
"loss": 0.0066,
|
| 530 |
"step": 295
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 9.375,
|
| 534 |
+
"grad_norm": 0.08231505751609802,
|
| 535 |
"learning_rate": 0.00053125,
|
| 536 |
+
"loss": 0.0059,
|
| 537 |
"step": 300
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 9.53125,
|
| 541 |
+
"grad_norm": 0.1094212606549263,
|
| 542 |
"learning_rate": 0.0005234375,
|
| 543 |
+
"loss": 0.0071,
|
| 544 |
"step": 305
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"epoch": 9.6875,
|
| 548 |
+
"grad_norm": 0.2680395841598511,
|
| 549 |
"learning_rate": 0.000515625,
|
| 550 |
+
"loss": 0.0097,
|
| 551 |
"step": 310
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 9.84375,
|
| 555 |
+
"grad_norm": 0.059513527899980545,
|
| 556 |
"learning_rate": 0.0005078125,
|
| 557 |
+
"loss": 0.0088,
|
| 558 |
"step": 315
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 10.0,
|
| 562 |
+
"grad_norm": 0.05216934159398079,
|
| 563 |
"learning_rate": 0.0005,
|
| 564 |
+
"loss": 0.0079,
|
| 565 |
"step": 320
|
| 566 |
},
|
| 567 |
{
|
| 568 |
"epoch": 10.0,
|
| 569 |
+
"eval_accuracy": 0.8509803921568627,
|
| 570 |
+
"eval_f1": 0.8469890554498172,
|
| 571 |
+
"eval_loss": 0.5335255265235901,
|
| 572 |
+
"eval_precision": 0.8636809133132662,
|
| 573 |
+
"eval_recall": 0.8509803921568627,
|
| 574 |
+
"eval_runtime": 15.0591,
|
| 575 |
+
"eval_samples_per_second": 67.733,
|
| 576 |
+
"eval_steps_per_second": 2.125,
|
| 577 |
"step": 320
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 10.15625,
|
| 581 |
+
"grad_norm": 0.031231796368956566,
|
| 582 |
"learning_rate": 0.0004921875,
|
| 583 |
"loss": 0.0045,
|
| 584 |
"step": 325
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 10.3125,
|
| 588 |
+
"grad_norm": 0.03108547069132328,
|
| 589 |
"learning_rate": 0.000484375,
|
| 590 |
+
"loss": 0.0041,
|
| 591 |
"step": 330
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 10.46875,
|
| 595 |
+
"grad_norm": 0.04625704139471054,
|
| 596 |
"learning_rate": 0.0004765625,
|
| 597 |
+
"loss": 0.0033,
|
| 598 |
"step": 335
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 10.625,
|
| 602 |
+
"grad_norm": 0.0934106633067131,
|
| 603 |
"learning_rate": 0.00046875,
|
| 604 |
+
"loss": 0.005,
|
| 605 |
"step": 340
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 10.78125,
|
| 609 |
+
"grad_norm": 0.031285736709833145,
|
| 610 |
"learning_rate": 0.00046093750000000003,
|
| 611 |
+
"loss": 0.004,
|
| 612 |
"step": 345
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 10.9375,
|
| 616 |
+
"grad_norm": 0.052936799824237823,
|
| 617 |
"learning_rate": 0.000453125,
|
| 618 |
+
"loss": 0.0072,
|
| 619 |
"step": 350
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 11.0,
|
| 623 |
+
"eval_accuracy": 0.8647058823529412,
|
| 624 |
+
"eval_f1": 0.8604589215066042,
|
| 625 |
+
"eval_loss": 0.5107002854347229,
|
| 626 |
+
"eval_precision": 0.8735360179996857,
|
| 627 |
+
"eval_recall": 0.8647058823529412,
|
| 628 |
+
"eval_runtime": 14.8358,
|
| 629 |
+
"eval_samples_per_second": 68.753,
|
| 630 |
+
"eval_steps_per_second": 2.157,
|
| 631 |
"step": 352
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 11.09375,
|
| 635 |
+
"grad_norm": 0.02143882028758526,
|
| 636 |
"learning_rate": 0.0004453125,
|
| 637 |
+
"loss": 0.0039,
|
| 638 |
"step": 355
|
| 639 |
},
|
| 640 |
{
|
| 641 |
"epoch": 11.25,
|
| 642 |
+
"grad_norm": 0.06976446509361267,
|
| 643 |
"learning_rate": 0.0004375,
|
| 644 |
+
"loss": 0.0033,
|
| 645 |
"step": 360
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 11.40625,
|
| 649 |
+
"grad_norm": 0.08110585063695908,
|
| 650 |
"learning_rate": 0.0004296875,
|
| 651 |
+
"loss": 0.0039,
|
| 652 |
"step": 365
|
| 653 |
},
|
| 654 |
{
|
| 655 |
"epoch": 11.5625,
|
| 656 |
+
"grad_norm": 0.025856945663690567,
|
| 657 |
"learning_rate": 0.000421875,
|
| 658 |
+
"loss": 0.0052,
|
| 659 |
"step": 370
|
| 660 |
},
|
| 661 |
{
|
| 662 |
"epoch": 11.71875,
|
| 663 |
+
"grad_norm": 0.059996578842401505,
|
| 664 |
"learning_rate": 0.0004140625,
|
| 665 |
+
"loss": 0.0076,
|
| 666 |
"step": 375
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 11.875,
|
| 670 |
+
"grad_norm": 0.1558006852865219,
|
| 671 |
"learning_rate": 0.00040625000000000004,
|
| 672 |
+
"loss": 0.0086,
|
| 673 |
"step": 380
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 12.0,
|
| 677 |
+
"eval_accuracy": 0.8578431372549019,
|
| 678 |
+
"eval_f1": 0.8548177831549634,
|
| 679 |
+
"eval_loss": 0.5290006995201111,
|
| 680 |
+
"eval_precision": 0.8719719142513259,
|
| 681 |
+
"eval_recall": 0.8578431372549019,
|
| 682 |
+
"eval_runtime": 14.675,
|
| 683 |
+
"eval_samples_per_second": 69.506,
|
| 684 |
+
"eval_steps_per_second": 2.181,
|
| 685 |
"step": 384
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 12.03125,
|
| 689 |
+
"grad_norm": 0.2643249034881592,
|
| 690 |
"learning_rate": 0.00039843750000000003,
|
| 691 |
+
"loss": 0.0052,
|
| 692 |
"step": 385
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 12.1875,
|
| 696 |
+
"grad_norm": 0.03377879783511162,
|
| 697 |
"learning_rate": 0.000390625,
|
| 698 |
+
"loss": 0.0042,
|
| 699 |
"step": 390
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 12.34375,
|
| 703 |
+
"grad_norm": 0.4935762286186218,
|
| 704 |
"learning_rate": 0.0003828125,
|
| 705 |
+
"loss": 0.0044,
|
| 706 |
"step": 395
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"epoch": 12.5,
|
| 710 |
+
"grad_norm": 0.011438349261879921,
|
| 711 |
"learning_rate": 0.000375,
|
| 712 |
+
"loss": 0.0026,
|
| 713 |
"step": 400
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 12.65625,
|
| 717 |
+
"grad_norm": 0.0676066130399704,
|
| 718 |
"learning_rate": 0.0003671875,
|
| 719 |
+
"loss": 0.004,
|
| 720 |
"step": 405
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 12.8125,
|
| 724 |
+
"grad_norm": 0.014333638362586498,
|
| 725 |
"learning_rate": 0.000359375,
|
| 726 |
+
"loss": 0.0033,
|
| 727 |
"step": 410
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 12.96875,
|
| 731 |
+
"grad_norm": 0.11364184319972992,
|
| 732 |
"learning_rate": 0.0003515625,
|
| 733 |
+
"loss": 0.0058,
|
| 734 |
"step": 415
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 13.0,
|
| 738 |
+
"eval_accuracy": 0.8568627450980392,
|
| 739 |
+
"eval_f1": 0.8523334959912007,
|
| 740 |
+
"eval_loss": 0.5160782933235168,
|
| 741 |
+
"eval_precision": 0.865809422059422,
|
| 742 |
+
"eval_recall": 0.8568627450980392,
|
| 743 |
+
"eval_runtime": 14.822,
|
| 744 |
+
"eval_samples_per_second": 68.817,
|
| 745 |
+
"eval_steps_per_second": 2.159,
|
| 746 |
"step": 416
|
| 747 |
},
|
| 748 |
{
|
| 749 |
"epoch": 13.125,
|
| 750 |
+
"grad_norm": 0.013512840494513512,
|
| 751 |
"learning_rate": 0.00034375,
|
| 752 |
+
"loss": 0.0023,
|
| 753 |
"step": 420
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 13.28125,
|
| 757 |
+
"grad_norm": 0.16694830358028412,
|
| 758 |
"learning_rate": 0.00033593750000000003,
|
| 759 |
+
"loss": 0.0076,
|
| 760 |
"step": 425
|
| 761 |
},
|
| 762 |
{
|
| 763 |
"epoch": 13.4375,
|
| 764 |
+
"grad_norm": 0.025320900604128838,
|
| 765 |
"learning_rate": 0.000328125,
|
| 766 |
+
"loss": 0.0023,
|
| 767 |
"step": 430
|
| 768 |
},
|
| 769 |
{
|
| 770 |
"epoch": 13.59375,
|
| 771 |
+
"grad_norm": 0.015468744561076164,
|
| 772 |
"learning_rate": 0.0003203125,
|
| 773 |
+
"loss": 0.0035,
|
| 774 |
"step": 435
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 13.75,
|
| 778 |
+
"grad_norm": 0.03578919544816017,
|
| 779 |
"learning_rate": 0.0003125,
|
| 780 |
+
"loss": 0.0027,
|
| 781 |
"step": 440
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 13.90625,
|
| 785 |
+
"grad_norm": 0.023722629994153976,
|
| 786 |
"learning_rate": 0.0003046875,
|
| 787 |
+
"loss": 0.0027,
|
| 788 |
"step": 445
|
| 789 |
},
|
| 790 |
{
|
| 791 |
"epoch": 14.0,
|
| 792 |
+
"eval_accuracy": 0.8588235294117647,
|
| 793 |
+
"eval_f1": 0.8538315193219463,
|
| 794 |
+
"eval_loss": 0.5138522982597351,
|
| 795 |
+
"eval_precision": 0.8702200713230125,
|
| 796 |
+
"eval_recall": 0.8588235294117647,
|
| 797 |
+
"eval_runtime": 15.3283,
|
| 798 |
+
"eval_samples_per_second": 66.544,
|
| 799 |
+
"eval_steps_per_second": 2.088,
|
| 800 |
"step": 448
|
| 801 |
},
|
| 802 |
{
|
| 803 |
+
"epoch": 14.0,
|
| 804 |
+
"step": 448,
|
| 805 |
+
"total_flos": 3.058842052288512e+17,
|
| 806 |
+
"train_loss": 0.7544229235707982,
|
| 807 |
+
"train_runtime": 674.4917,
|
| 808 |
+
"train_samples_per_second": 30.245,
|
| 809 |
+
"train_steps_per_second": 0.949
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 810 |
}
|
| 811 |
],
|
| 812 |
"logging_steps": 5,
|
|
|
|
| 815 |
"num_train_epochs": 20,
|
| 816 |
"save_steps": 500,
|
| 817 |
"stateful_callbacks": {
|
| 818 |
+
"EarlyStoppingCallback": {
|
| 819 |
+
"args": {
|
| 820 |
+
"early_stopping_patience": 3,
|
| 821 |
+
"early_stopping_threshold": 0.0
|
| 822 |
+
},
|
| 823 |
+
"attributes": {
|
| 824 |
+
"early_stopping_patience_counter": 3
|
| 825 |
+
}
|
| 826 |
+
},
|
| 827 |
"TrainerControl": {
|
| 828 |
"args": {
|
| 829 |
"should_epoch_stop": false,
|
|
|
|
| 835 |
"attributes": {}
|
| 836 |
}
|
| 837 |
},
|
| 838 |
+
"total_flos": 3.058842052288512e+17,
|
| 839 |
"train_batch_size": 32,
|
| 840 |
"trial_name": null,
|
| 841 |
"trial_params": null
|