Model save
Browse files- README.md +8 -8
- all_results.json +11 -11
- eval_results.json +6 -6
- model.safetensors +1 -1
- runs/Dec15_02-29-03_d2a76fcee09b/events.out.tfevents.1702607830.d2a76fcee09b.2614.8 +3 -0
- runs/Dec15_02-37-22_d2a76fcee09b/events.out.tfevents.1702607847.d2a76fcee09b.2614.9 +3 -0
- train_results.json +6 -6
- trainer_state.json +139 -382
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 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
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -52,7 +52,7 @@ More information needed
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
-
- learning_rate: 0.
|
| 56 |
- train_batch_size: 48
|
| 57 |
- eval_batch_size: 8
|
| 58 |
- seed: 42
|
|
@@ -65,10 +65,10 @@ The following hyperparameters were used during training:
|
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9009259259259259
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5926
|
| 36 |
+
- Accuracy: 0.9009
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 0.0003
|
| 56 |
- train_batch_size: 48
|
| 57 |
- eval_batch_size: 8
|
| 58 |
- seed: 42
|
|
|
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 0.128 | 1.11 | 100 | 0.7718 | 0.8685 |
|
| 69 |
+
| 0.0236 | 2.22 | 200 | 0.6526 | 0.8852 |
|
| 70 |
+
| 0.004 | 3.33 | 300 | 0.5478 | 0.9009 |
|
| 71 |
+
| 0.0024 | 4.44 | 400 | 0.5926 | 0.9009 |
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 14.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 9.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 1.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9092592592592592,
|
| 4 |
+
"eval_loss": 0.5364564061164856,
|
| 5 |
+
"eval_runtime": 14.0587,
|
| 6 |
+
"eval_samples_per_second": 76.821,
|
| 7 |
+
"eval_steps_per_second": 9.603,
|
| 8 |
+
"total_flos": 1.6739319895474176e+18,
|
| 9 |
+
"train_loss": 0.02156418908904824,
|
| 10 |
+
"train_runtime": 434.3833,
|
| 11 |
+
"train_samples_per_second": 49.726,
|
| 12 |
+
"train_steps_per_second": 1.036
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 14.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 9.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9092592592592592,
|
| 4 |
+
"eval_loss": 0.5364564061164856,
|
| 5 |
+
"eval_runtime": 14.0587,
|
| 6 |
+
"eval_samples_per_second": 76.821,
|
| 7 |
+
"eval_steps_per_second": 9.603
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343245508
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:195c22084a8777f5cc7b698a55f748752ec59dfc255766ae2fbf09e121c968ee
|
| 3 |
size 343245508
|
runs/Dec15_02-29-03_d2a76fcee09b/events.out.tfevents.1702607830.d2a76fcee09b.2614.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9070a007c35af5e503973c97c7485e886ab8530c8580b33e0f324622f4f4c95c
|
| 3 |
+
size 411
|
runs/Dec15_02-37-22_d2a76fcee09b/events.out.tfevents.1702607847.d2a76fcee09b.2614.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dbbcad38ec4549bf2e46a47945b4a4bee4f0ec8c542c362b70039596412f7ce
|
| 3 |
+
size 13189
|
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": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 1.6739319895474176e+18,
|
| 4 |
+
"train_loss": 0.02156418908904824,
|
| 5 |
+
"train_runtime": 434.3833,
|
| 6 |
+
"train_samples_per_second": 49.726,
|
| 7 |
+
"train_steps_per_second": 1.036
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,577 +1,334 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"eval_steps":
|
| 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": 0.11,
|
| 13 |
-
"learning_rate": 0.
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.22,
|
| 19 |
-
"learning_rate": 0.
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.33,
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.44,
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.56,
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.67,
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.78,
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.89,
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 1.0,
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 1.11,
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.22,
|
| 73 |
-
"learning_rate": 0.
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 1.33,
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 1.44,
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 1.56,
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 1.67,
|
| 97 |
-
"learning_rate": 0.
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 1.78,
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 160
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 1.89,
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 170
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 2.0,
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 180
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 2.11,
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 190
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 2.22,
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
"step": 200
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 2.33,
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 210
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 2.44,
|
| 139 |
-
"learning_rate": 0.
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 220
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 2.56,
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 230
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 2.67,
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 240
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 2.78,
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 250
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 2.89,
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 260
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 3.0,
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 270
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 3.11,
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 280
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 3.22,
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 290
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 3.33,
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
"step": 300
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 3.44,
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 310
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 3.56,
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 320
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 3.67,
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 330
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 3.78,
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 340
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 3.89,
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 350
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 4.0,
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 360
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 4.11,
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 370
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 4.22,
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 380
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 4.33,
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 0.
|
| 243 |
"step": 390
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 4.44,
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 249 |
"step": 400
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 4.56,
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss": 0.
|
| 255 |
"step": 410
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 4.67,
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 420
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 4.78,
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 430
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 4.89,
|
| 271 |
-
"learning_rate":
|
| 272 |
-
"loss": 0.
|
| 273 |
"step": 440
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 5.0,
|
| 277 |
-
"learning_rate": 0.0001,
|
| 278 |
-
"loss": 0.0009,
|
| 279 |
-
"step": 450
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 5.11,
|
| 283 |
-
"learning_rate": 9.777777777777778e-05,
|
| 284 |
-
"loss": 0.0012,
|
| 285 |
-
"step": 460
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"epoch": 5.22,
|
| 289 |
-
"learning_rate": 9.555555555555557e-05,
|
| 290 |
-
"loss": 0.0006,
|
| 291 |
-
"step": 470
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 5.33,
|
| 295 |
-
"learning_rate": 9.333333333333334e-05,
|
| 296 |
-
"loss": 0.0041,
|
| 297 |
-
"step": 480
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 5.44,
|
| 301 |
-
"learning_rate": 9.111111111111112e-05,
|
| 302 |
-
"loss": 0.0019,
|
| 303 |
-
"step": 490
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 5.56,
|
| 307 |
-
"learning_rate": 8.888888888888889e-05,
|
| 308 |
-
"loss": 0.0017,
|
| 309 |
-
"step": 500
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"epoch": 5.56,
|
| 313 |
-
"eval_accuracy": 0.9101851851851852,
|
| 314 |
-
"eval_loss": 0.5352890491485596,
|
| 315 |
-
"eval_runtime": 12.7384,
|
| 316 |
-
"eval_samples_per_second": 84.783,
|
| 317 |
-
"eval_steps_per_second": 10.598,
|
| 318 |
-
"step": 500
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 5.67,
|
| 322 |
-
"learning_rate": 8.666666666666667e-05,
|
| 323 |
-
"loss": 0.0091,
|
| 324 |
-
"step": 510
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 5.78,
|
| 328 |
-
"learning_rate": 8.444444444444444e-05,
|
| 329 |
-
"loss": 0.0015,
|
| 330 |
-
"step": 520
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 5.89,
|
| 334 |
-
"learning_rate": 8.222222222222222e-05,
|
| 335 |
-
"loss": 0.0059,
|
| 336 |
-
"step": 530
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 6.0,
|
| 340 |
-
"learning_rate": 8e-05,
|
| 341 |
-
"loss": 0.0028,
|
| 342 |
-
"step": 540
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 6.11,
|
| 346 |
-
"learning_rate": 7.777777777777778e-05,
|
| 347 |
-
"loss": 0.0004,
|
| 348 |
-
"step": 550
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 6.22,
|
| 352 |
-
"learning_rate": 7.555555555555556e-05,
|
| 353 |
-
"loss": 0.0024,
|
| 354 |
-
"step": 560
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 6.33,
|
| 358 |
-
"learning_rate": 7.333333333333333e-05,
|
| 359 |
-
"loss": 0.0004,
|
| 360 |
-
"step": 570
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 6.44,
|
| 364 |
-
"learning_rate": 7.111111111111112e-05,
|
| 365 |
-
"loss": 0.0024,
|
| 366 |
-
"step": 580
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 6.56,
|
| 370 |
-
"learning_rate": 6.88888888888889e-05,
|
| 371 |
-
"loss": 0.0004,
|
| 372 |
-
"step": 590
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 6.67,
|
| 376 |
-
"learning_rate": 6.666666666666667e-05,
|
| 377 |
-
"loss": 0.0019,
|
| 378 |
-
"step": 600
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 6.78,
|
| 382 |
-
"learning_rate": 6.444444444444446e-05,
|
| 383 |
-
"loss": 0.0005,
|
| 384 |
-
"step": 610
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 6.89,
|
| 388 |
-
"learning_rate": 6.222222222222222e-05,
|
| 389 |
-
"loss": 0.004,
|
| 390 |
-
"step": 620
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 7.0,
|
| 394 |
-
"learning_rate": 6e-05,
|
| 395 |
-
"loss": 0.0047,
|
| 396 |
-
"step": 630
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 7.11,
|
| 400 |
-
"learning_rate": 5.7777777777777776e-05,
|
| 401 |
-
"loss": 0.0004,
|
| 402 |
-
"step": 640
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"epoch": 7.22,
|
| 406 |
-
"learning_rate": 5.555555555555556e-05,
|
| 407 |
-
"loss": 0.003,
|
| 408 |
-
"step": 650
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 7.33,
|
| 412 |
-
"learning_rate": 5.333333333333333e-05,
|
| 413 |
-
"loss": 0.0027,
|
| 414 |
-
"step": 660
|
| 415 |
-
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 7.44,
|
| 418 |
-
"learning_rate": 5.111111111111111e-05,
|
| 419 |
-
"loss": 0.0022,
|
| 420 |
-
"step": 670
|
| 421 |
-
},
|
| 422 |
-
{
|
| 423 |
-
"epoch": 7.56,
|
| 424 |
-
"learning_rate": 4.888888888888889e-05,
|
| 425 |
-
"loss": 0.0004,
|
| 426 |
-
"step": 680
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"epoch": 7.67,
|
| 430 |
-
"learning_rate": 4.666666666666667e-05,
|
| 431 |
-
"loss": 0.0031,
|
| 432 |
-
"step": 690
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 7.78,
|
| 436 |
-
"learning_rate": 4.4444444444444447e-05,
|
| 437 |
-
"loss": 0.002,
|
| 438 |
-
"step": 700
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 7.89,
|
| 442 |
-
"learning_rate": 4.222222222222222e-05,
|
| 443 |
-
"loss": 0.0004,
|
| 444 |
-
"step": 710
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 8.0,
|
| 448 |
-
"learning_rate": 4e-05,
|
| 449 |
-
"loss": 0.0021,
|
| 450 |
-
"step": 720
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 8.11,
|
| 454 |
-
"learning_rate": 3.777777777777778e-05,
|
| 455 |
-
"loss": 0.0019,
|
| 456 |
-
"step": 730
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 8.22,
|
| 460 |
-
"learning_rate": 3.555555555555556e-05,
|
| 461 |
-
"loss": 0.0033,
|
| 462 |
-
"step": 740
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 8.33,
|
| 466 |
-
"learning_rate": 3.3333333333333335e-05,
|
| 467 |
-
"loss": 0.0022,
|
| 468 |
-
"step": 750
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 8.44,
|
| 472 |
-
"learning_rate": 3.111111111111111e-05,
|
| 473 |
-
"loss": 0.0018,
|
| 474 |
-
"step": 760
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 8.56,
|
| 478 |
-
"learning_rate": 2.8888888888888888e-05,
|
| 479 |
-
"loss": 0.0017,
|
| 480 |
-
"step": 770
|
| 481 |
-
},
|
| 482 |
-
{
|
| 483 |
-
"epoch": 8.67,
|
| 484 |
-
"learning_rate": 2.6666666666666667e-05,
|
| 485 |
-
"loss": 0.002,
|
| 486 |
-
"step": 780
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 8.78,
|
| 490 |
-
"learning_rate": 2.4444444444444445e-05,
|
| 491 |
-
"loss": 0.0004,
|
| 492 |
-
"step": 790
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 8.89,
|
| 496 |
-
"learning_rate": 2.2222222222222223e-05,
|
| 497 |
-
"loss": 0.0003,
|
| 498 |
-
"step": 800
|
| 499 |
-
},
|
| 500 |
-
{
|
| 501 |
-
"epoch": 9.0,
|
| 502 |
-
"learning_rate": 2e-05,
|
| 503 |
-
"loss": 0.0022,
|
| 504 |
-
"step": 810
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"epoch": 9.11,
|
| 508 |
-
"learning_rate": 1.777777777777778e-05,
|
| 509 |
-
"loss": 0.0017,
|
| 510 |
-
"step": 820
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 9.22,
|
| 514 |
-
"learning_rate": 1.5555555555555555e-05,
|
| 515 |
-
"loss": 0.0018,
|
| 516 |
-
"step": 830
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 9.33,
|
| 520 |
-
"learning_rate": 1.3333333333333333e-05,
|
| 521 |
-
"loss": 0.0032,
|
| 522 |
-
"step": 840
|
| 523 |
-
},
|
| 524 |
-
{
|
| 525 |
-
"epoch": 9.44,
|
| 526 |
-
"learning_rate": 1.1111111111111112e-05,
|
| 527 |
-
"loss": 0.0032,
|
| 528 |
-
"step": 850
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 9.56,
|
| 532 |
-
"learning_rate": 8.88888888888889e-06,
|
| 533 |
-
"loss": 0.0003,
|
| 534 |
-
"step": 860
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 9.67,
|
| 538 |
-
"learning_rate": 6.666666666666667e-06,
|
| 539 |
-
"loss": 0.0021,
|
| 540 |
-
"step": 870
|
| 541 |
-
},
|
| 542 |
-
{
|
| 543 |
-
"epoch": 9.78,
|
| 544 |
-
"learning_rate": 4.444444444444445e-06,
|
| 545 |
-
"loss": 0.0003,
|
| 546 |
-
"step": 880
|
| 547 |
-
},
|
| 548 |
-
{
|
| 549 |
-
"epoch": 9.89,
|
| 550 |
-
"learning_rate": 2.2222222222222225e-06,
|
| 551 |
-
"loss": 0.0003,
|
| 552 |
-
"step": 890
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 10.0,
|
| 556 |
"learning_rate": 0.0,
|
| 557 |
-
"loss": 0.
|
| 558 |
-
"step":
|
| 559 |
},
|
| 560 |
{
|
| 561 |
-
"epoch":
|
| 562 |
-
"step":
|
| 563 |
-
"total_flos":
|
| 564 |
-
"train_loss": 0.
|
| 565 |
-
"train_runtime":
|
| 566 |
-
"train_samples_per_second":
|
| 567 |
-
"train_steps_per_second": 1.
|
| 568 |
}
|
| 569 |
],
|
| 570 |
"logging_steps": 10,
|
| 571 |
-
"max_steps":
|
| 572 |
-
"num_train_epochs":
|
| 573 |
"save_steps": 1000,
|
| 574 |
-
"total_flos":
|
| 575 |
"trial_name": null,
|
| 576 |
"trial_params": null
|
| 577 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 450,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.11,
|
| 13 |
+
"learning_rate": 0.00019555555555555556,
|
| 14 |
+
"loss": 0.0015,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.22,
|
| 19 |
+
"learning_rate": 0.00019111111111111114,
|
| 20 |
+
"loss": 0.0402,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.33,
|
| 25 |
+
"learning_rate": 0.0001866666666666667,
|
| 26 |
+
"loss": 0.0814,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.44,
|
| 31 |
+
"learning_rate": 0.00018222222222222224,
|
| 32 |
+
"loss": 0.0893,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.56,
|
| 37 |
+
"learning_rate": 0.00017777777777777779,
|
| 38 |
+
"loss": 0.1203,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.67,
|
| 43 |
+
"learning_rate": 0.00017333333333333334,
|
| 44 |
+
"loss": 0.0505,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.78,
|
| 49 |
+
"learning_rate": 0.00016888888888888889,
|
| 50 |
+
"loss": 0.0448,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.89,
|
| 55 |
+
"learning_rate": 0.00016444444444444444,
|
| 56 |
+
"loss": 0.073,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 1.0,
|
| 61 |
+
"learning_rate": 0.00016,
|
| 62 |
+
"loss": 0.0954,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 1.11,
|
| 67 |
+
"learning_rate": 0.00015555555555555556,
|
| 68 |
+
"loss": 0.0273,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.11,
|
| 73 |
+
"eval_accuracy": 0.8740740740740741,
|
| 74 |
+
"eval_loss": 0.7636905312538147,
|
| 75 |
+
"eval_runtime": 12.8677,
|
| 76 |
+
"eval_samples_per_second": 83.931,
|
| 77 |
+
"eval_steps_per_second": 10.491,
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 1.22,
|
| 82 |
+
"learning_rate": 0.0001511111111111111,
|
| 83 |
+
"loss": 0.0246,
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 1.33,
|
| 88 |
+
"learning_rate": 0.00014666666666666666,
|
| 89 |
+
"loss": 0.0223,
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 1.44,
|
| 94 |
+
"learning_rate": 0.00014222222222222224,
|
| 95 |
+
"loss": 0.0129,
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 1.56,
|
| 100 |
+
"learning_rate": 0.0001377777777777778,
|
| 101 |
+
"loss": 0.0401,
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.67,
|
| 106 |
+
"learning_rate": 0.00013333333333333334,
|
| 107 |
+
"loss": 0.0285,
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 1.78,
|
| 112 |
+
"learning_rate": 0.00012888888888888892,
|
| 113 |
+
"loss": 0.0261,
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 1.89,
|
| 118 |
+
"learning_rate": 0.00012444444444444444,
|
| 119 |
+
"loss": 0.0456,
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 2.0,
|
| 124 |
+
"learning_rate": 0.00012,
|
| 125 |
+
"loss": 0.0198,
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 2.11,
|
| 130 |
+
"learning_rate": 0.00011555555555555555,
|
| 131 |
+
"loss": 0.0051,
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 2.22,
|
| 136 |
+
"learning_rate": 0.00011111111111111112,
|
| 137 |
+
"loss": 0.0314,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.22,
|
| 142 |
+
"eval_accuracy": 0.8824074074074074,
|
| 143 |
+
"eval_loss": 0.6027200818061829,
|
| 144 |
+
"eval_runtime": 13.4571,
|
| 145 |
+
"eval_samples_per_second": 80.255,
|
| 146 |
+
"eval_steps_per_second": 10.032,
|
| 147 |
"step": 200
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 2.33,
|
| 151 |
+
"learning_rate": 0.00010666666666666667,
|
| 152 |
+
"loss": 0.0061,
|
| 153 |
"step": 210
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 2.44,
|
| 157 |
+
"learning_rate": 0.00010222222222222222,
|
| 158 |
+
"loss": 0.0103,
|
| 159 |
"step": 220
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 2.56,
|
| 163 |
+
"learning_rate": 9.777777777777778e-05,
|
| 164 |
+
"loss": 0.0119,
|
| 165 |
"step": 230
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 2.67,
|
| 169 |
+
"learning_rate": 9.333333333333334e-05,
|
| 170 |
+
"loss": 0.0121,
|
| 171 |
"step": 240
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 2.78,
|
| 175 |
+
"learning_rate": 8.888888888888889e-05,
|
| 176 |
+
"loss": 0.0109,
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 2.89,
|
| 181 |
+
"learning_rate": 8.444444444444444e-05,
|
| 182 |
+
"loss": 0.0017,
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 3.0,
|
| 187 |
+
"learning_rate": 8e-05,
|
| 188 |
+
"loss": 0.0043,
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 3.11,
|
| 193 |
+
"learning_rate": 7.555555555555556e-05,
|
| 194 |
+
"loss": 0.0005,
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 3.22,
|
| 199 |
+
"learning_rate": 7.111111111111112e-05,
|
| 200 |
+
"loss": 0.0004,
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 3.33,
|
| 205 |
+
"learning_rate": 6.666666666666667e-05,
|
| 206 |
+
"loss": 0.0019,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.33,
|
| 211 |
+
"eval_accuracy": 0.9037037037037037,
|
| 212 |
+
"eval_loss": 0.5983412861824036,
|
| 213 |
+
"eval_runtime": 12.7475,
|
| 214 |
+
"eval_samples_per_second": 84.723,
|
| 215 |
+
"eval_steps_per_second": 10.59,
|
| 216 |
"step": 300
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 3.44,
|
| 220 |
+
"learning_rate": 6.222222222222222e-05,
|
| 221 |
+
"loss": 0.0037,
|
| 222 |
"step": 310
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 3.56,
|
| 226 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 227 |
+
"loss": 0.0025,
|
| 228 |
"step": 320
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 3.67,
|
| 232 |
+
"learning_rate": 5.333333333333333e-05,
|
| 233 |
+
"loss": 0.0026,
|
| 234 |
"step": 330
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 3.78,
|
| 238 |
+
"learning_rate": 4.888888888888889e-05,
|
| 239 |
+
"loss": 0.0006,
|
| 240 |
"step": 340
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 3.89,
|
| 244 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 245 |
+
"loss": 0.0053,
|
| 246 |
"step": 350
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 4.0,
|
| 250 |
+
"learning_rate": 4e-05,
|
| 251 |
+
"loss": 0.0006,
|
| 252 |
"step": 360
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 4.11,
|
| 256 |
+
"learning_rate": 3.555555555555556e-05,
|
| 257 |
+
"loss": 0.0003,
|
| 258 |
"step": 370
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 4.22,
|
| 262 |
+
"learning_rate": 3.111111111111111e-05,
|
| 263 |
+
"loss": 0.0019,
|
| 264 |
"step": 380
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 4.33,
|
| 268 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 269 |
+
"loss": 0.0004,
|
| 270 |
"step": 390
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 4.44,
|
| 274 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 275 |
+
"loss": 0.0019,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.44,
|
| 280 |
+
"eval_accuracy": 0.9092592592592592,
|
| 281 |
+
"eval_loss": 0.5358805060386658,
|
| 282 |
+
"eval_runtime": 12.6258,
|
| 283 |
+
"eval_samples_per_second": 85.539,
|
| 284 |
+
"eval_steps_per_second": 10.692,
|
| 285 |
"step": 400
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 4.56,
|
| 289 |
+
"learning_rate": 1.777777777777778e-05,
|
| 290 |
+
"loss": 0.0003,
|
| 291 |
"step": 410
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 4.67,
|
| 295 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 296 |
+
"loss": 0.002,
|
| 297 |
"step": 420
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 4.78,
|
| 301 |
+
"learning_rate": 8.88888888888889e-06,
|
| 302 |
+
"loss": 0.0046,
|
| 303 |
"step": 430
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 4.89,
|
| 307 |
+
"learning_rate": 4.444444444444445e-06,
|
| 308 |
+
"loss": 0.0032,
|
| 309 |
"step": 440
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 5.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 313 |
"learning_rate": 0.0,
|
| 314 |
+
"loss": 0.0003,
|
| 315 |
+
"step": 450
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 5.0,
|
| 319 |
+
"step": 450,
|
| 320 |
+
"total_flos": 1.6739319895474176e+18,
|
| 321 |
+
"train_loss": 0.02156418908904824,
|
| 322 |
+
"train_runtime": 434.3833,
|
| 323 |
+
"train_samples_per_second": 49.726,
|
| 324 |
+
"train_steps_per_second": 1.036
|
| 325 |
}
|
| 326 |
],
|
| 327 |
"logging_steps": 10,
|
| 328 |
+
"max_steps": 450,
|
| 329 |
+
"num_train_epochs": 5,
|
| 330 |
"save_steps": 1000,
|
| 331 |
+
"total_flos": 1.6739319895474176e+18,
|
| 332 |
"trial_name": null,
|
| 333 |
"trial_params": null
|
| 334 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff0144e19c345d1cafd5108586fa9401bae1c146468e7f549fa127ec77535ac0
|
| 3 |
size 4536
|