End of training
Browse files- README.md +12 -12
- all_results.json +5 -5
- confusion_matrix_test_fold_3.png +0 -0
- confusion_matrix_valid_fold_3.png +0 -0
- model.safetensors +1 -1
- test_results.json +5 -5
- trainer_state.json +200 -200
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.0002 | 5.1001 | 5424 | 0.
|
| 60 |
-
| 0.0001 | 6.1001 | 6328 | 0.
|
| 61 |
-
| 0.0001 | 7.1001 | 7232 | 0.
|
| 62 |
-
| 0.0001 | 8.1001 | 8136 | 0.
|
| 63 |
-
| 0.0001 | 9.0990 | 9030 | 0.
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.8547
|
| 22 |
+
- Accuracy: 0.7665
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 0.2384 | 0.1001 | 904 | 0.2019 | 0.9639 |
|
| 55 |
+
| 0.0207 | 1.1001 | 1808 | 0.0325 | 0.9900 |
|
| 56 |
+
| 0.0116 | 2.1001 | 2712 | 0.0229 | 0.9963 |
|
| 57 |
+
| 0.0017 | 3.1001 | 3616 | 0.0222 | 0.9950 |
|
| 58 |
+
| 0.0156 | 4.1001 | 4520 | 0.0402 | 0.9900 |
|
| 59 |
+
| 0.0002 | 5.1001 | 5424 | 0.0083 | 0.9975 |
|
| 60 |
+
| 0.0001 | 6.1001 | 6328 | 0.0088 | 0.9975 |
|
| 61 |
+
| 0.0001 | 7.1001 | 7232 | 0.0094 | 0.9975 |
|
| 62 |
+
| 0.0001 | 8.1001 | 8136 | 0.0097 | 0.9975 |
|
| 63 |
+
| 0.0001 | 9.0990 | 9030 | 0.0098 | 0.9975 |
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.099003322259136,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.099003322259136,
|
| 3 |
+
"eval_accuracy": 0.7664576802507836,
|
| 4 |
+
"eval_loss": 0.8547028303146362,
|
| 5 |
+
"eval_runtime": 304.3291,
|
| 6 |
+
"eval_samples_per_second": 4.193,
|
| 7 |
+
"eval_steps_per_second": 0.526
|
| 8 |
}
|
confusion_matrix_test_fold_3.png
ADDED
|
confusion_matrix_valid_fold_3.png
ADDED
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 485250680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a92405eb1a2048bc73411fe4a8f83de063bcb7ea17e092cef106be338573e70d
|
| 3 |
size 485250680
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.099003322259136,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.099003322259136,
|
| 3 |
+
"eval_accuracy": 0.7664576802507836,
|
| 4 |
+
"eval_loss": 0.8547028303146362,
|
| 5 |
+
"eval_runtime": 304.3291,
|
| 6 |
+
"eval_samples_per_second": 4.193,
|
| 7 |
+
"eval_steps_per_second": 0.526
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/Timesformer_default_fold_10_10_epoch_noAug_batch8/checkpoint-
|
| 4 |
"epoch": 9.099003322259136,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 9030,
|
|
@@ -10,740 +10,740 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01107419712070875,
|
| 13 |
-
"grad_norm": 12.
|
| 14 |
"learning_rate": 5.537098560354375e-06,
|
| 15 |
-
"loss": 4.
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.0221483942414175,
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 1.107419712070875e-05,
|
| 22 |
-
"loss": 3.
|
| 23 |
"step": 200
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.03322259136212625,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 1.6611295681063124e-05,
|
| 29 |
-
"loss": 2.
|
| 30 |
"step": 300
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.044296788482835,
|
| 34 |
-
"grad_norm": 12.
|
| 35 |
"learning_rate": 2.21483942414175e-05,
|
| 36 |
-
"loss": 2.
|
| 37 |
"step": 400
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.05537098560354374,
|
| 41 |
-
"grad_norm":
|
| 42 |
"learning_rate": 2.7685492801771873e-05,
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.0664451827242525,
|
| 48 |
-
"grad_norm":
|
| 49 |
"learning_rate": 3.322259136212625e-05,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 600
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.07751937984496124,
|
| 55 |
-
"grad_norm": 9.
|
| 56 |
"learning_rate": 3.875968992248062e-05,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 700
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.08859357696567,
|
| 62 |
-
"grad_norm":
|
| 63 |
"learning_rate": 4.4296788482835e-05,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 800
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.09966777408637874,
|
| 69 |
-
"grad_norm": 9.
|
| 70 |
"learning_rate": 4.983388704318937e-05,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 900
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.10011074197120709,
|
| 76 |
-
"eval_accuracy": 0.
|
| 77 |
-
"eval_loss": 0.
|
| 78 |
-
"eval_runtime":
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second": 0.
|
| 81 |
"step": 904
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 1.0106312292358803,
|
| 85 |
-
"grad_norm":
|
| 86 |
"learning_rate": 4.940322382182848e-05,
|
| 87 |
-
"loss": 0.
|
| 88 |
"step": 1000
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.0217054263565892,
|
| 92 |
-
"grad_norm": 0.
|
| 93 |
"learning_rate": 4.878799064845577e-05,
|
| 94 |
-
"loss": 0.
|
| 95 |
"step": 1100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.032779623477298,
|
| 99 |
-
"grad_norm":
|
| 100 |
"learning_rate": 4.8172757475083056e-05,
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 1200
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.0438538205980066,
|
| 106 |
-
"grad_norm":
|
| 107 |
"learning_rate": 4.755752430171035e-05,
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 1300
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.0549280177187155,
|
| 113 |
-
"grad_norm":
|
| 114 |
"learning_rate": 4.694229112833764e-05,
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 1400
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.0660022148394241,
|
| 120 |
-
"grad_norm": 0.
|
| 121 |
"learning_rate": 4.6327057954964936e-05,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 1500
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 1.0770764119601328,
|
| 127 |
-
"grad_norm": 0.
|
| 128 |
"learning_rate": 4.571182478159223e-05,
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 1600
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.0881506090808417,
|
| 134 |
-
"grad_norm": 0.
|
| 135 |
"learning_rate": 4.5096591608219516e-05,
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 1700
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.0992248062015504,
|
| 141 |
-
"grad_norm": 0.
|
| 142 |
"learning_rate": 4.448135843484681e-05,
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 1800
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.100110741971207,
|
| 148 |
-
"eval_accuracy": 0.
|
| 149 |
-
"eval_loss": 0.
|
| 150 |
-
"eval_runtime":
|
| 151 |
-
"eval_samples_per_second": 2.
|
| 152 |
-
"eval_steps_per_second": 0.
|
| 153 |
"step": 1808
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 2.010188261351052,
|
| 157 |
-
"grad_norm": 0.
|
| 158 |
"learning_rate": 4.38661252614741e-05,
|
| 159 |
-
"loss": 0.
|
| 160 |
"step": 1900
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 2.0212624584717607,
|
| 164 |
-
"grad_norm": 0.
|
| 165 |
"learning_rate": 4.325089208810139e-05,
|
| 166 |
-
"loss": 0.
|
| 167 |
"step": 2000
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 2.0323366555924696,
|
| 171 |
-
"grad_norm": 0.
|
| 172 |
"learning_rate": 4.263565891472868e-05,
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 2100
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.0434108527131785,
|
| 178 |
-
"grad_norm": 0.
|
| 179 |
"learning_rate": 4.2020425741355975e-05,
|
| 180 |
-
"loss": 0.
|
| 181 |
"step": 2200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 2.054485049833887,
|
| 185 |
-
"grad_norm": 0.
|
| 186 |
"learning_rate": 4.140519256798327e-05,
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 2300
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 2.065559246954596,
|
| 192 |
-
"grad_norm": 0.
|
| 193 |
"learning_rate": 4.078995939461056e-05,
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 2400
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 2.0766334440753047,
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
"learning_rate": 4.0174726221237855e-05,
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 2500
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 2.087707641196013,
|
| 206 |
-
"grad_norm": 0.
|
| 207 |
"learning_rate": 3.955949304786514e-05,
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 2600
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 2.098781838316722,
|
| 213 |
-
"grad_norm": 0.
|
| 214 |
"learning_rate": 3.8944259874492434e-05,
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 2700
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 2.100110741971207,
|
| 220 |
"eval_accuracy": 0.9962640099626401,
|
| 221 |
-
"eval_loss": 0.
|
| 222 |
-
"eval_runtime":
|
| 223 |
-
"eval_samples_per_second": 2.
|
| 224 |
-
"eval_steps_per_second": 0.
|
| 225 |
"step": 2712
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 3.009745293466224,
|
| 229 |
-
"grad_norm": 0.
|
| 230 |
"learning_rate": 3.832902670111973e-05,
|
| 231 |
-
"loss": 0.
|
| 232 |
"step": 2800
|
| 233 |
},
|
| 234 |
{
|
| 235 |
"epoch": 3.0208194905869323,
|
| 236 |
-
"grad_norm": 0.
|
| 237 |
"learning_rate": 3.7713793527747014e-05,
|
| 238 |
-
"loss": 0.
|
| 239 |
"step": 2900
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 3.0318936877076412,
|
| 243 |
-
"grad_norm": 0.
|
| 244 |
"learning_rate": 3.7098560354374314e-05,
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 3000
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 3.04296788482835,
|
| 250 |
-
"grad_norm": 0.
|
| 251 |
"learning_rate": 3.64833271810016e-05,
|
| 252 |
-
"loss": 0.
|
| 253 |
"step": 3100
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 3.0540420819490586,
|
| 257 |
-
"grad_norm": 0.
|
| 258 |
"learning_rate": 3.5868094007628894e-05,
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 3200
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 3.0651162790697675,
|
| 264 |
-
"grad_norm": 0.
|
| 265 |
"learning_rate": 3.525286083425619e-05,
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 3300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 3.0761904761904764,
|
| 271 |
-
"grad_norm": 0.
|
| 272 |
"learning_rate": 3.463762766088347e-05,
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 3400
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 3.087264673311185,
|
| 278 |
-
"grad_norm": 0.
|
| 279 |
"learning_rate": 3.4022394487510767e-05,
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 3500
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 3.0983388704318937,
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
"learning_rate": 3.340716131413806e-05,
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 3600
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 3.100110741971207,
|
| 292 |
-
"eval_accuracy": 0.
|
| 293 |
-
"eval_loss": 0.
|
| 294 |
-
"eval_runtime":
|
| 295 |
-
"eval_samples_per_second":
|
| 296 |
-
"eval_steps_per_second": 0.
|
| 297 |
"step": 3616
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 4.0093023255813955,
|
| 301 |
-
"grad_norm": 0.
|
| 302 |
"learning_rate": 3.2791928140765346e-05,
|
| 303 |
"loss": 0.0005,
|
| 304 |
"step": 3700
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 4.020376522702104,
|
| 308 |
-
"grad_norm": 0.
|
| 309 |
"learning_rate": 3.2176694967392646e-05,
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 3800
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 4.0314507198228124,
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
"learning_rate": 3.156146179401994e-05,
|
| 317 |
"loss": 0.0003,
|
| 318 |
"step": 3900
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 4.042524916943521,
|
| 322 |
-
"grad_norm": 0.
|
| 323 |
"learning_rate": 3.0946228620647226e-05,
|
| 324 |
-
"loss": 0.
|
| 325 |
"step": 4000
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 4.05359911406423,
|
| 329 |
-
"grad_norm": 0.
|
| 330 |
"learning_rate": 3.033099544727452e-05,
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 4100
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 4.064673311184939,
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
"learning_rate": 2.971576227390181e-05,
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 4200
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 4.075747508305648,
|
| 343 |
-
"grad_norm": 0.
|
| 344 |
"learning_rate": 2.91005291005291e-05,
|
| 345 |
-
"loss": 0.
|
| 346 |
"step": 4300
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 4.086821705426357,
|
| 350 |
-
"grad_norm": 0.
|
| 351 |
"learning_rate": 2.8485295927156392e-05,
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 4400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 4.097895902547065,
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
"learning_rate": 2.787006275378369e-05,
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 4500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 4.100110741971207,
|
| 364 |
-
"eval_accuracy": 0.
|
| 365 |
-
"eval_loss": 0.
|
| 366 |
-
"eval_runtime":
|
| 367 |
-
"eval_samples_per_second":
|
| 368 |
-
"eval_steps_per_second": 0.
|
| 369 |
"step": 4520
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 5.008859357696567,
|
| 373 |
-
"grad_norm": 0.
|
| 374 |
"learning_rate": 2.725482958041098e-05,
|
| 375 |
-
"loss": 0.
|
| 376 |
"step": 4600
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 5.019933554817276,
|
| 380 |
-
"grad_norm": 0.
|
| 381 |
"learning_rate": 2.6639596407038268e-05,
|
| 382 |
-
"loss": 0.
|
| 383 |
"step": 4700
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 5.0310077519379846,
|
| 387 |
-
"grad_norm": 0.
|
| 388 |
"learning_rate": 2.602436323366556e-05,
|
| 389 |
-
"loss": 0.
|
| 390 |
"step": 4800
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 5.0420819490586934,
|
| 394 |
-
"grad_norm": 0.
|
| 395 |
"learning_rate": 2.540913006029285e-05,
|
| 396 |
-
"loss": 0.
|
| 397 |
"step": 4900
|
| 398 |
},
|
| 399 |
{
|
| 400 |
"epoch": 5.053156146179402,
|
| 401 |
-
"grad_norm": 0.
|
| 402 |
"learning_rate": 2.479389688692014e-05,
|
| 403 |
-
"loss": 0.
|
| 404 |
"step": 5000
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 5.06423034330011,
|
| 408 |
-
"grad_norm": 0.
|
| 409 |
"learning_rate": 2.4178663713547438e-05,
|
| 410 |
-
"loss": 0.
|
| 411 |
"step": 5100
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 5.075304540420819,
|
| 415 |
-
"grad_norm": 0.
|
| 416 |
"learning_rate": 2.3563430540174727e-05,
|
| 417 |
-
"loss": 0.
|
| 418 |
"step": 5200
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 5.086378737541528,
|
| 422 |
-
"grad_norm": 0.
|
| 423 |
"learning_rate": 2.2948197366802017e-05,
|
| 424 |
"loss": 0.0002,
|
| 425 |
"step": 5300
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 5.097452934662237,
|
| 429 |
-
"grad_norm": 0.
|
| 430 |
"learning_rate": 2.233296419342931e-05,
|
| 431 |
"loss": 0.0002,
|
| 432 |
"step": 5400
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 5.100110741971207,
|
| 436 |
-
"eval_accuracy": 0.
|
| 437 |
-
"eval_loss": 0.
|
| 438 |
-
"eval_runtime":
|
| 439 |
-
"eval_samples_per_second":
|
| 440 |
-
"eval_steps_per_second": 0.
|
| 441 |
"step": 5424
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.008416389811739,
|
| 445 |
-
"grad_norm": 0.
|
| 446 |
"learning_rate": 2.1717731020056604e-05,
|
| 447 |
"loss": 0.0002,
|
| 448 |
"step": 5500
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 6.019490586932448,
|
| 452 |
-
"grad_norm": 0.
|
| 453 |
"learning_rate": 2.1102497846683894e-05,
|
| 454 |
"loss": 0.0001,
|
| 455 |
"step": 5600
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 6.030564784053156,
|
| 459 |
-
"grad_norm": 0.
|
| 460 |
"learning_rate": 2.0487264673311183e-05,
|
| 461 |
"loss": 0.0001,
|
| 462 |
"step": 5700
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 6.041638981173865,
|
| 466 |
-
"grad_norm": 0.
|
| 467 |
"learning_rate": 1.987203149993848e-05,
|
| 468 |
"loss": 0.0001,
|
| 469 |
"step": 5800
|
| 470 |
},
|
| 471 |
{
|
| 472 |
"epoch": 6.052713178294574,
|
| 473 |
-
"grad_norm": 0.
|
| 474 |
"learning_rate": 1.925679832656577e-05,
|
| 475 |
"loss": 0.0001,
|
| 476 |
"step": 5900
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 6.0637873754152825,
|
| 480 |
-
"grad_norm": 0.
|
| 481 |
"learning_rate": 1.864156515319306e-05,
|
| 482 |
"loss": 0.0001,
|
| 483 |
"step": 6000
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.074861572535991,
|
| 487 |
-
"grad_norm": 0.
|
| 488 |
"learning_rate": 1.8026331979820353e-05,
|
| 489 |
"loss": 0.0001,
|
| 490 |
"step": 6100
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 6.0859357696567,
|
| 494 |
-
"grad_norm": 0.
|
| 495 |
"learning_rate": 1.7411098806447646e-05,
|
| 496 |
"loss": 0.0001,
|
| 497 |
"step": 6200
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 6.097009966777408,
|
| 501 |
-
"grad_norm": 0.
|
| 502 |
"learning_rate": 1.6795865633074936e-05,
|
| 503 |
"loss": 0.0001,
|
| 504 |
"step": 6300
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 6.100110741971207,
|
| 508 |
-
"eval_accuracy": 0.
|
| 509 |
-
"eval_loss": 0.
|
| 510 |
-
"eval_runtime":
|
| 511 |
-
"eval_samples_per_second":
|
| 512 |
-
"eval_steps_per_second": 0.
|
| 513 |
"step": 6328
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 7.00797342192691,
|
| 517 |
-
"grad_norm": 0.
|
| 518 |
"learning_rate": 1.6180632459702226e-05,
|
| 519 |
"loss": 0.0001,
|
| 520 |
"step": 6400
|
| 521 |
},
|
| 522 |
{
|
| 523 |
"epoch": 7.019047619047619,
|
| 524 |
-
"grad_norm": 0.
|
| 525 |
"learning_rate": 1.556539928632952e-05,
|
| 526 |
"loss": 0.0001,
|
| 527 |
"step": 6500
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 7.030121816168328,
|
| 531 |
-
"grad_norm": 0.
|
| 532 |
"learning_rate": 1.4950166112956812e-05,
|
| 533 |
"loss": 0.0001,
|
| 534 |
"step": 6600
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 7.041196013289037,
|
| 538 |
-
"grad_norm": 0.
|
| 539 |
"learning_rate": 1.4334932939584104e-05,
|
| 540 |
"loss": 0.0001,
|
| 541 |
"step": 6700
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 7.052270210409746,
|
| 545 |
-
"grad_norm": 0.
|
| 546 |
"learning_rate": 1.3719699766211393e-05,
|
| 547 |
"loss": 0.0001,
|
| 548 |
"step": 6800
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 7.063344407530454,
|
| 552 |
-
"grad_norm": 0.
|
| 553 |
"learning_rate": 1.3104466592838688e-05,
|
| 554 |
"loss": 0.0001,
|
| 555 |
"step": 6900
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 7.074418604651163,
|
| 559 |
-
"grad_norm": 0.
|
| 560 |
"learning_rate": 1.2489233419465978e-05,
|
| 561 |
"loss": 0.0001,
|
| 562 |
"step": 7000
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 7.0854928017718715,
|
| 566 |
-
"grad_norm": 0.
|
| 567 |
"learning_rate": 1.187400024609327e-05,
|
| 568 |
"loss": 0.0001,
|
| 569 |
"step": 7100
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 7.09656699889258,
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
"learning_rate": 1.1258767072720563e-05,
|
| 575 |
"loss": 0.0001,
|
| 576 |
"step": 7200
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 7.100110741971207,
|
| 580 |
-
"eval_accuracy": 0.
|
| 581 |
-
"eval_loss": 0.
|
| 582 |
-
"eval_runtime":
|
| 583 |
-
"eval_samples_per_second":
|
| 584 |
-
"eval_steps_per_second": 0.
|
| 585 |
"step": 7232
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 8.007530454042081,
|
| 589 |
-
"grad_norm": 0.
|
| 590 |
"learning_rate": 1.0643533899347853e-05,
|
| 591 |
"loss": 0.0001,
|
| 592 |
"step": 7300
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 8.018604651162791,
|
| 596 |
-
"grad_norm": 0.
|
| 597 |
"learning_rate": 1.0028300725975146e-05,
|
| 598 |
"loss": 0.0001,
|
| 599 |
"step": 7400
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.029678848283499,
|
| 603 |
-
"grad_norm": 0.
|
| 604 |
"learning_rate": 9.413067552602436e-06,
|
| 605 |
"loss": 0.0001,
|
| 606 |
"step": 7500
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 8.040753045404209,
|
| 610 |
-
"grad_norm": 0.
|
| 611 |
"learning_rate": 8.797834379229729e-06,
|
| 612 |
"loss": 0.0001,
|
| 613 |
"step": 7600
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 8.051827242524917,
|
| 617 |
-
"grad_norm": 0.
|
| 618 |
"learning_rate": 8.18260120585702e-06,
|
| 619 |
"loss": 0.0001,
|
| 620 |
"step": 7700
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 8.062901439645625,
|
| 624 |
-
"grad_norm": 0.
|
| 625 |
"learning_rate": 7.567368032484312e-06,
|
| 626 |
"loss": 0.0001,
|
| 627 |
"step": 7800
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 8.073975636766335,
|
| 631 |
-
"grad_norm": 0.
|
| 632 |
"learning_rate": 6.952134859111603e-06,
|
| 633 |
"loss": 0.0001,
|
| 634 |
"step": 7900
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 8.085049833887043,
|
| 638 |
-
"grad_norm": 0.
|
| 639 |
"learning_rate": 6.336901685738895e-06,
|
| 640 |
"loss": 0.0001,
|
| 641 |
"step": 8000
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 8.096124031007752,
|
| 645 |
-
"grad_norm": 0.
|
| 646 |
"learning_rate": 5.7216685123661875e-06,
|
| 647 |
"loss": 0.0001,
|
| 648 |
"step": 8100
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 8.100110741971207,
|
| 652 |
-
"eval_accuracy": 0.
|
| 653 |
-
"eval_loss": 0.
|
| 654 |
-
"eval_runtime":
|
| 655 |
-
"eval_samples_per_second": 3.
|
| 656 |
-
"eval_steps_per_second": 0.
|
| 657 |
"step": 8136
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 9.007087486157253,
|
| 661 |
-
"grad_norm": 0.
|
| 662 |
"learning_rate": 5.106435338993479e-06,
|
| 663 |
"loss": 0.0001,
|
| 664 |
"step": 8200
|
| 665 |
},
|
| 666 |
{
|
| 667 |
"epoch": 9.018161683277963,
|
| 668 |
-
"grad_norm": 0.
|
| 669 |
"learning_rate": 4.4912021656207705e-06,
|
| 670 |
"loss": 0.0001,
|
| 671 |
"step": 8300
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 9.029235880398671,
|
| 675 |
-
"grad_norm": 0.
|
| 676 |
"learning_rate": 3.875968992248062e-06,
|
| 677 |
"loss": 0.0001,
|
| 678 |
"step": 8400
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 9.04031007751938,
|
| 682 |
-
"grad_norm": 0.
|
| 683 |
"learning_rate": 3.260735818875354e-06,
|
| 684 |
"loss": 0.0001,
|
| 685 |
"step": 8500
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 9.051384274640089,
|
| 689 |
-
"grad_norm": 0.
|
| 690 |
"learning_rate": 2.6455026455026455e-06,
|
| 691 |
"loss": 0.0001,
|
| 692 |
"step": 8600
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 9.062458471760797,
|
| 696 |
-
"grad_norm": 0.
|
| 697 |
"learning_rate": 2.0302694721299375e-06,
|
| 698 |
"loss": 0.0001,
|
| 699 |
"step": 8700
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 9.073532668881507,
|
| 703 |
-
"grad_norm": 0.
|
| 704 |
"learning_rate": 1.415036298757229e-06,
|
| 705 |
"loss": 0.0001,
|
| 706 |
"step": 8800
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"epoch": 9.084606866002215,
|
| 710 |
-
"grad_norm": 0.
|
| 711 |
"learning_rate": 7.998031253845208e-07,
|
| 712 |
"loss": 0.0001,
|
| 713 |
"step": 8900
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 9.095681063122923,
|
| 717 |
-
"grad_norm": 0.
|
| 718 |
"learning_rate": 1.8456995201181249e-07,
|
| 719 |
"loss": 0.0001,
|
| 720 |
"step": 9000
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 9.099003322259136,
|
| 724 |
-
"eval_accuracy": 0.
|
| 725 |
-
"eval_loss": 0.
|
| 726 |
-
"eval_runtime":
|
| 727 |
-
"eval_samples_per_second":
|
| 728 |
-
"eval_steps_per_second": 0.
|
| 729 |
"step": 9030
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 9.099003322259136,
|
| 733 |
"step": 9030,
|
| 734 |
"total_flos": 6.328460909097596e+19,
|
| 735 |
-
"train_loss": 0.
|
| 736 |
-
"train_runtime":
|
| 737 |
-
"train_samples_per_second": 2.
|
| 738 |
-
"train_steps_per_second": 0.
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 9.099003322259136,
|
| 742 |
-
"eval_accuracy": 0.
|
| 743 |
-
"eval_loss": 0.
|
| 744 |
-
"eval_runtime":
|
| 745 |
-
"eval_samples_per_second":
|
| 746 |
-
"eval_steps_per_second": 0.
|
| 747 |
"step": 9030
|
| 748 |
}
|
| 749 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9975093399750934,
|
| 3 |
+
"best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/Timesformer_default_fold_10_10_epoch_noAug_batch8/checkpoint-5424",
|
| 4 |
"epoch": 9.099003322259136,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 9030,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01107419712070875,
|
| 13 |
+
"grad_norm": 12.339608192443848,
|
| 14 |
"learning_rate": 5.537098560354375e-06,
|
| 15 |
+
"loss": 4.1774,
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.0221483942414175,
|
| 20 |
+
"grad_norm": 14.543400764465332,
|
| 21 |
"learning_rate": 1.107419712070875e-05,
|
| 22 |
+
"loss": 3.8205,
|
| 23 |
"step": 200
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.03322259136212625,
|
| 27 |
+
"grad_norm": 15.178791046142578,
|
| 28 |
"learning_rate": 1.6611295681063124e-05,
|
| 29 |
+
"loss": 2.9812,
|
| 30 |
"step": 300
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.044296788482835,
|
| 34 |
+
"grad_norm": 12.90939712524414,
|
| 35 |
"learning_rate": 2.21483942414175e-05,
|
| 36 |
+
"loss": 2.072,
|
| 37 |
"step": 400
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.05537098560354374,
|
| 41 |
+
"grad_norm": 12.425464630126953,
|
| 42 |
"learning_rate": 2.7685492801771873e-05,
|
| 43 |
+
"loss": 1.265,
|
| 44 |
"step": 500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.0664451827242525,
|
| 48 |
+
"grad_norm": 7.096066474914551,
|
| 49 |
"learning_rate": 3.322259136212625e-05,
|
| 50 |
+
"loss": 0.8079,
|
| 51 |
"step": 600
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.07751937984496124,
|
| 55 |
+
"grad_norm": 9.374312400817871,
|
| 56 |
"learning_rate": 3.875968992248062e-05,
|
| 57 |
+
"loss": 0.4583,
|
| 58 |
"step": 700
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.08859357696567,
|
| 62 |
+
"grad_norm": 2.866607904434204,
|
| 63 |
"learning_rate": 4.4296788482835e-05,
|
| 64 |
+
"loss": 0.2863,
|
| 65 |
"step": 800
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.09966777408637874,
|
| 69 |
+
"grad_norm": 9.150209426879883,
|
| 70 |
"learning_rate": 4.983388704318937e-05,
|
| 71 |
+
"loss": 0.2384,
|
| 72 |
"step": 900
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.10011074197120709,
|
| 76 |
+
"eval_accuracy": 0.9638854296388543,
|
| 77 |
+
"eval_loss": 0.20189498364925385,
|
| 78 |
+
"eval_runtime": 306.3851,
|
| 79 |
+
"eval_samples_per_second": 2.621,
|
| 80 |
+
"eval_steps_per_second": 0.33,
|
| 81 |
"step": 904
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 1.0106312292358803,
|
| 85 |
+
"grad_norm": 0.4338759779930115,
|
| 86 |
"learning_rate": 4.940322382182848e-05,
|
| 87 |
+
"loss": 0.1309,
|
| 88 |
"step": 1000
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.0217054263565892,
|
| 92 |
+
"grad_norm": 0.7621960639953613,
|
| 93 |
"learning_rate": 4.878799064845577e-05,
|
| 94 |
+
"loss": 0.1036,
|
| 95 |
"step": 1100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.032779623477298,
|
| 99 |
+
"grad_norm": 0.665744960308075,
|
| 100 |
"learning_rate": 4.8172757475083056e-05,
|
| 101 |
+
"loss": 0.075,
|
| 102 |
"step": 1200
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.0438538205980066,
|
| 106 |
+
"grad_norm": 11.760805130004883,
|
| 107 |
"learning_rate": 4.755752430171035e-05,
|
| 108 |
+
"loss": 0.0808,
|
| 109 |
"step": 1300
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.0549280177187155,
|
| 113 |
+
"grad_norm": 2.482733726501465,
|
| 114 |
"learning_rate": 4.694229112833764e-05,
|
| 115 |
+
"loss": 0.0308,
|
| 116 |
"step": 1400
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.0660022148394241,
|
| 120 |
+
"grad_norm": 0.05557706952095032,
|
| 121 |
"learning_rate": 4.6327057954964936e-05,
|
| 122 |
+
"loss": 0.0475,
|
| 123 |
"step": 1500
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 1.0770764119601328,
|
| 127 |
+
"grad_norm": 0.05685936659574509,
|
| 128 |
"learning_rate": 4.571182478159223e-05,
|
| 129 |
+
"loss": 0.0211,
|
| 130 |
"step": 1600
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.0881506090808417,
|
| 134 |
+
"grad_norm": 0.07164409011602402,
|
| 135 |
"learning_rate": 4.5096591608219516e-05,
|
| 136 |
+
"loss": 0.0367,
|
| 137 |
"step": 1700
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.0992248062015504,
|
| 141 |
+
"grad_norm": 0.07703804969787598,
|
| 142 |
"learning_rate": 4.448135843484681e-05,
|
| 143 |
+
"loss": 0.0207,
|
| 144 |
"step": 1800
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.100110741971207,
|
| 148 |
+
"eval_accuracy": 0.9900373599003736,
|
| 149 |
+
"eval_loss": 0.03251923993229866,
|
| 150 |
+
"eval_runtime": 319.7386,
|
| 151 |
+
"eval_samples_per_second": 2.511,
|
| 152 |
+
"eval_steps_per_second": 0.316,
|
| 153 |
"step": 1808
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 2.010188261351052,
|
| 157 |
+
"grad_norm": 0.049545079469680786,
|
| 158 |
"learning_rate": 4.38661252614741e-05,
|
| 159 |
+
"loss": 0.0066,
|
| 160 |
"step": 1900
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 2.0212624584717607,
|
| 164 |
+
"grad_norm": 0.023045338690280914,
|
| 165 |
"learning_rate": 4.325089208810139e-05,
|
| 166 |
+
"loss": 0.0035,
|
| 167 |
"step": 2000
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 2.0323366555924696,
|
| 171 |
+
"grad_norm": 0.016869375482201576,
|
| 172 |
"learning_rate": 4.263565891472868e-05,
|
| 173 |
+
"loss": 0.0162,
|
| 174 |
"step": 2100
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 2.0434108527131785,
|
| 178 |
+
"grad_norm": 0.029845820739865303,
|
| 179 |
"learning_rate": 4.2020425741355975e-05,
|
| 180 |
+
"loss": 0.0185,
|
| 181 |
"step": 2200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 2.054485049833887,
|
| 185 |
+
"grad_norm": 0.009218129329383373,
|
| 186 |
"learning_rate": 4.140519256798327e-05,
|
| 187 |
+
"loss": 0.0109,
|
| 188 |
"step": 2300
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 2.065559246954596,
|
| 192 |
+
"grad_norm": 0.07040040194988251,
|
| 193 |
"learning_rate": 4.078995939461056e-05,
|
| 194 |
+
"loss": 0.0023,
|
| 195 |
"step": 2400
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 2.0766334440753047,
|
| 199 |
+
"grad_norm": 0.12176311016082764,
|
| 200 |
"learning_rate": 4.0174726221237855e-05,
|
| 201 |
+
"loss": 0.0258,
|
| 202 |
"step": 2500
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 2.087707641196013,
|
| 206 |
+
"grad_norm": 0.01268716063350439,
|
| 207 |
"learning_rate": 3.955949304786514e-05,
|
| 208 |
+
"loss": 0.0098,
|
| 209 |
"step": 2600
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 2.098781838316722,
|
| 213 |
+
"grad_norm": 0.03558783233165741,
|
| 214 |
"learning_rate": 3.8944259874492434e-05,
|
| 215 |
+
"loss": 0.0116,
|
| 216 |
"step": 2700
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 2.100110741971207,
|
| 220 |
"eval_accuracy": 0.9962640099626401,
|
| 221 |
+
"eval_loss": 0.02290569432079792,
|
| 222 |
+
"eval_runtime": 324.5071,
|
| 223 |
+
"eval_samples_per_second": 2.475,
|
| 224 |
+
"eval_steps_per_second": 0.311,
|
| 225 |
"step": 2712
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 3.009745293466224,
|
| 229 |
+
"grad_norm": 0.021466247737407684,
|
| 230 |
"learning_rate": 3.832902670111973e-05,
|
| 231 |
+
"loss": 0.0169,
|
| 232 |
"step": 2800
|
| 233 |
},
|
| 234 |
{
|
| 235 |
"epoch": 3.0208194905869323,
|
| 236 |
+
"grad_norm": 0.014765599742531776,
|
| 237 |
"learning_rate": 3.7713793527747014e-05,
|
| 238 |
+
"loss": 0.0008,
|
| 239 |
"step": 2900
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 3.0318936877076412,
|
| 243 |
+
"grad_norm": 0.012668099254369736,
|
| 244 |
"learning_rate": 3.7098560354374314e-05,
|
| 245 |
+
"loss": 0.0021,
|
| 246 |
"step": 3000
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 3.04296788482835,
|
| 250 |
+
"grad_norm": 0.007325606886297464,
|
| 251 |
"learning_rate": 3.64833271810016e-05,
|
| 252 |
+
"loss": 0.0043,
|
| 253 |
"step": 3100
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 3.0540420819490586,
|
| 257 |
+
"grad_norm": 0.010318818502128124,
|
| 258 |
"learning_rate": 3.5868094007628894e-05,
|
| 259 |
+
"loss": 0.0119,
|
| 260 |
"step": 3200
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 3.0651162790697675,
|
| 264 |
+
"grad_norm": 0.00951201282441616,
|
| 265 |
"learning_rate": 3.525286083425619e-05,
|
| 266 |
+
"loss": 0.0006,
|
| 267 |
"step": 3300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 3.0761904761904764,
|
| 271 |
+
"grad_norm": 0.0036382139660418034,
|
| 272 |
"learning_rate": 3.463762766088347e-05,
|
| 273 |
+
"loss": 0.0006,
|
| 274 |
"step": 3400
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 3.087264673311185,
|
| 278 |
+
"grad_norm": 0.014880606904625893,
|
| 279 |
"learning_rate": 3.4022394487510767e-05,
|
| 280 |
+
"loss": 0.0112,
|
| 281 |
"step": 3500
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 3.0983388704318937,
|
| 285 |
+
"grad_norm": 0.02532036043703556,
|
| 286 |
"learning_rate": 3.340716131413806e-05,
|
| 287 |
+
"loss": 0.0017,
|
| 288 |
"step": 3600
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 3.100110741971207,
|
| 292 |
+
"eval_accuracy": 0.9950186799501868,
|
| 293 |
+
"eval_loss": 0.022232333198189735,
|
| 294 |
+
"eval_runtime": 321.5404,
|
| 295 |
+
"eval_samples_per_second": 2.497,
|
| 296 |
+
"eval_steps_per_second": 0.314,
|
| 297 |
"step": 3616
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 4.0093023255813955,
|
| 301 |
+
"grad_norm": 0.006754144560545683,
|
| 302 |
"learning_rate": 3.2791928140765346e-05,
|
| 303 |
"loss": 0.0005,
|
| 304 |
"step": 3700
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 4.020376522702104,
|
| 308 |
+
"grad_norm": 0.005147715099155903,
|
| 309 |
"learning_rate": 3.2176694967392646e-05,
|
| 310 |
+
"loss": 0.0149,
|
| 311 |
"step": 3800
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 4.0314507198228124,
|
| 315 |
+
"grad_norm": 0.007229967508465052,
|
| 316 |
"learning_rate": 3.156146179401994e-05,
|
| 317 |
"loss": 0.0003,
|
| 318 |
"step": 3900
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 4.042524916943521,
|
| 322 |
+
"grad_norm": 0.014596535824239254,
|
| 323 |
"learning_rate": 3.0946228620647226e-05,
|
| 324 |
+
"loss": 0.0004,
|
| 325 |
"step": 4000
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 4.05359911406423,
|
| 329 |
+
"grad_norm": 0.0032493751496076584,
|
| 330 |
"learning_rate": 3.033099544727452e-05,
|
| 331 |
+
"loss": 0.0003,
|
| 332 |
"step": 4100
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 4.064673311184939,
|
| 336 |
+
"grad_norm": 0.004764176905155182,
|
| 337 |
"learning_rate": 2.971576227390181e-05,
|
| 338 |
+
"loss": 0.0002,
|
| 339 |
"step": 4200
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 4.075747508305648,
|
| 343 |
+
"grad_norm": 0.005187960807234049,
|
| 344 |
"learning_rate": 2.91005291005291e-05,
|
| 345 |
+
"loss": 0.0002,
|
| 346 |
"step": 4300
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 4.086821705426357,
|
| 350 |
+
"grad_norm": 0.008601618930697441,
|
| 351 |
"learning_rate": 2.8485295927156392e-05,
|
| 352 |
+
"loss": 0.0004,
|
| 353 |
"step": 4400
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 4.097895902547065,
|
| 357 |
+
"grad_norm": 0.5019575357437134,
|
| 358 |
"learning_rate": 2.787006275378369e-05,
|
| 359 |
+
"loss": 0.0156,
|
| 360 |
"step": 4500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 4.100110741971207,
|
| 364 |
+
"eval_accuracy": 0.9900373599003736,
|
| 365 |
+
"eval_loss": 0.04016907513141632,
|
| 366 |
+
"eval_runtime": 316.7446,
|
| 367 |
+
"eval_samples_per_second": 2.535,
|
| 368 |
+
"eval_steps_per_second": 0.319,
|
| 369 |
"step": 4520
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 5.008859357696567,
|
| 373 |
+
"grad_norm": 0.09171910583972931,
|
| 374 |
"learning_rate": 2.725482958041098e-05,
|
| 375 |
+
"loss": 0.0379,
|
| 376 |
"step": 4600
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 5.019933554817276,
|
| 380 |
+
"grad_norm": 0.012514377012848854,
|
| 381 |
"learning_rate": 2.6639596407038268e-05,
|
| 382 |
+
"loss": 0.0049,
|
| 383 |
"step": 4700
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 5.0310077519379846,
|
| 387 |
+
"grad_norm": 0.009760179556906223,
|
| 388 |
"learning_rate": 2.602436323366556e-05,
|
| 389 |
+
"loss": 0.0008,
|
| 390 |
"step": 4800
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 5.0420819490586934,
|
| 394 |
+
"grad_norm": 0.00494693499058485,
|
| 395 |
"learning_rate": 2.540913006029285e-05,
|
| 396 |
+
"loss": 0.0094,
|
| 397 |
"step": 4900
|
| 398 |
},
|
| 399 |
{
|
| 400 |
"epoch": 5.053156146179402,
|
| 401 |
+
"grad_norm": 0.003839722601696849,
|
| 402 |
"learning_rate": 2.479389688692014e-05,
|
| 403 |
+
"loss": 0.0003,
|
| 404 |
"step": 5000
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 5.06423034330011,
|
| 408 |
+
"grad_norm": 0.004592357203364372,
|
| 409 |
"learning_rate": 2.4178663713547438e-05,
|
| 410 |
+
"loss": 0.0002,
|
| 411 |
"step": 5100
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 5.075304540420819,
|
| 415 |
+
"grad_norm": 0.00357171637006104,
|
| 416 |
"learning_rate": 2.3563430540174727e-05,
|
| 417 |
+
"loss": 0.0003,
|
| 418 |
"step": 5200
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 5.086378737541528,
|
| 422 |
+
"grad_norm": 0.004462802782654762,
|
| 423 |
"learning_rate": 2.2948197366802017e-05,
|
| 424 |
"loss": 0.0002,
|
| 425 |
"step": 5300
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 5.097452934662237,
|
| 429 |
+
"grad_norm": 0.002604804467409849,
|
| 430 |
"learning_rate": 2.233296419342931e-05,
|
| 431 |
"loss": 0.0002,
|
| 432 |
"step": 5400
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 5.100110741971207,
|
| 436 |
+
"eval_accuracy": 0.9975093399750934,
|
| 437 |
+
"eval_loss": 0.008347271010279655,
|
| 438 |
+
"eval_runtime": 311.1635,
|
| 439 |
+
"eval_samples_per_second": 2.581,
|
| 440 |
+
"eval_steps_per_second": 0.325,
|
| 441 |
"step": 5424
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.008416389811739,
|
| 445 |
+
"grad_norm": 0.0028000217862427235,
|
| 446 |
"learning_rate": 2.1717731020056604e-05,
|
| 447 |
"loss": 0.0002,
|
| 448 |
"step": 5500
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 6.019490586932448,
|
| 452 |
+
"grad_norm": 0.0019141006050631404,
|
| 453 |
"learning_rate": 2.1102497846683894e-05,
|
| 454 |
"loss": 0.0001,
|
| 455 |
"step": 5600
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 6.030564784053156,
|
| 459 |
+
"grad_norm": 0.0038908650167286396,
|
| 460 |
"learning_rate": 2.0487264673311183e-05,
|
| 461 |
"loss": 0.0001,
|
| 462 |
"step": 5700
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 6.041638981173865,
|
| 466 |
+
"grad_norm": 0.0013375241542235017,
|
| 467 |
"learning_rate": 1.987203149993848e-05,
|
| 468 |
"loss": 0.0001,
|
| 469 |
"step": 5800
|
| 470 |
},
|
| 471 |
{
|
| 472 |
"epoch": 6.052713178294574,
|
| 473 |
+
"grad_norm": 0.0016891614068299532,
|
| 474 |
"learning_rate": 1.925679832656577e-05,
|
| 475 |
"loss": 0.0001,
|
| 476 |
"step": 5900
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 6.0637873754152825,
|
| 480 |
+
"grad_norm": 0.0015141346957534552,
|
| 481 |
"learning_rate": 1.864156515319306e-05,
|
| 482 |
"loss": 0.0001,
|
| 483 |
"step": 6000
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.074861572535991,
|
| 487 |
+
"grad_norm": 0.0012503410689532757,
|
| 488 |
"learning_rate": 1.8026331979820353e-05,
|
| 489 |
"loss": 0.0001,
|
| 490 |
"step": 6100
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 6.0859357696567,
|
| 494 |
+
"grad_norm": 0.0019348779460415244,
|
| 495 |
"learning_rate": 1.7411098806447646e-05,
|
| 496 |
"loss": 0.0001,
|
| 497 |
"step": 6200
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 6.097009966777408,
|
| 501 |
+
"grad_norm": 0.001840105396695435,
|
| 502 |
"learning_rate": 1.6795865633074936e-05,
|
| 503 |
"loss": 0.0001,
|
| 504 |
"step": 6300
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 6.100110741971207,
|
| 508 |
+
"eval_accuracy": 0.9975093399750934,
|
| 509 |
+
"eval_loss": 0.008798662573099136,
|
| 510 |
+
"eval_runtime": 315.9616,
|
| 511 |
+
"eval_samples_per_second": 2.541,
|
| 512 |
+
"eval_steps_per_second": 0.32,
|
| 513 |
"step": 6328
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 7.00797342192691,
|
| 517 |
+
"grad_norm": 0.0018666000105440617,
|
| 518 |
"learning_rate": 1.6180632459702226e-05,
|
| 519 |
"loss": 0.0001,
|
| 520 |
"step": 6400
|
| 521 |
},
|
| 522 |
{
|
| 523 |
"epoch": 7.019047619047619,
|
| 524 |
+
"grad_norm": 0.0011329470435157418,
|
| 525 |
"learning_rate": 1.556539928632952e-05,
|
| 526 |
"loss": 0.0001,
|
| 527 |
"step": 6500
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 7.030121816168328,
|
| 531 |
+
"grad_norm": 0.0014819415519014,
|
| 532 |
"learning_rate": 1.4950166112956812e-05,
|
| 533 |
"loss": 0.0001,
|
| 534 |
"step": 6600
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 7.041196013289037,
|
| 538 |
+
"grad_norm": 0.0013377605937421322,
|
| 539 |
"learning_rate": 1.4334932939584104e-05,
|
| 540 |
"loss": 0.0001,
|
| 541 |
"step": 6700
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 7.052270210409746,
|
| 545 |
+
"grad_norm": 0.0014949695905670524,
|
| 546 |
"learning_rate": 1.3719699766211393e-05,
|
| 547 |
"loss": 0.0001,
|
| 548 |
"step": 6800
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 7.063344407530454,
|
| 552 |
+
"grad_norm": 0.0020517068915069103,
|
| 553 |
"learning_rate": 1.3104466592838688e-05,
|
| 554 |
"loss": 0.0001,
|
| 555 |
"step": 6900
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 7.074418604651163,
|
| 559 |
+
"grad_norm": 0.0016913407016545534,
|
| 560 |
"learning_rate": 1.2489233419465978e-05,
|
| 561 |
"loss": 0.0001,
|
| 562 |
"step": 7000
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 7.0854928017718715,
|
| 566 |
+
"grad_norm": 0.0019159069051966071,
|
| 567 |
"learning_rate": 1.187400024609327e-05,
|
| 568 |
"loss": 0.0001,
|
| 569 |
"step": 7100
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 7.09656699889258,
|
| 573 |
+
"grad_norm": 0.0017233892576768994,
|
| 574 |
"learning_rate": 1.1258767072720563e-05,
|
| 575 |
"loss": 0.0001,
|
| 576 |
"step": 7200
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 7.100110741971207,
|
| 580 |
+
"eval_accuracy": 0.9975093399750934,
|
| 581 |
+
"eval_loss": 0.009401123970746994,
|
| 582 |
+
"eval_runtime": 205.4199,
|
| 583 |
+
"eval_samples_per_second": 3.909,
|
| 584 |
+
"eval_steps_per_second": 0.492,
|
| 585 |
"step": 7232
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 8.007530454042081,
|
| 589 |
+
"grad_norm": 0.0016070300480350852,
|
| 590 |
"learning_rate": 1.0643533899347853e-05,
|
| 591 |
"loss": 0.0001,
|
| 592 |
"step": 7300
|
| 593 |
},
|
| 594 |
{
|
| 595 |
"epoch": 8.018604651162791,
|
| 596 |
+
"grad_norm": 0.0009037270210683346,
|
| 597 |
"learning_rate": 1.0028300725975146e-05,
|
| 598 |
"loss": 0.0001,
|
| 599 |
"step": 7400
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.029678848283499,
|
| 603 |
+
"grad_norm": 0.0009796767262741923,
|
| 604 |
"learning_rate": 9.413067552602436e-06,
|
| 605 |
"loss": 0.0001,
|
| 606 |
"step": 7500
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 8.040753045404209,
|
| 610 |
+
"grad_norm": 0.009153931401669979,
|
| 611 |
"learning_rate": 8.797834379229729e-06,
|
| 612 |
"loss": 0.0001,
|
| 613 |
"step": 7600
|
| 614 |
},
|
| 615 |
{
|
| 616 |
"epoch": 8.051827242524917,
|
| 617 |
+
"grad_norm": 0.0009286152780987322,
|
| 618 |
"learning_rate": 8.18260120585702e-06,
|
| 619 |
"loss": 0.0001,
|
| 620 |
"step": 7700
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 8.062901439645625,
|
| 624 |
+
"grad_norm": 0.0012453129747882485,
|
| 625 |
"learning_rate": 7.567368032484312e-06,
|
| 626 |
"loss": 0.0001,
|
| 627 |
"step": 7800
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 8.073975636766335,
|
| 631 |
+
"grad_norm": 0.000763101561460644,
|
| 632 |
"learning_rate": 6.952134859111603e-06,
|
| 633 |
"loss": 0.0001,
|
| 634 |
"step": 7900
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 8.085049833887043,
|
| 638 |
+
"grad_norm": 0.0010468490654602647,
|
| 639 |
"learning_rate": 6.336901685738895e-06,
|
| 640 |
"loss": 0.0001,
|
| 641 |
"step": 8000
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 8.096124031007752,
|
| 645 |
+
"grad_norm": 0.0007441536872647703,
|
| 646 |
"learning_rate": 5.7216685123661875e-06,
|
| 647 |
"loss": 0.0001,
|
| 648 |
"step": 8100
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 8.100110741971207,
|
| 652 |
+
"eval_accuracy": 0.9975093399750934,
|
| 653 |
+
"eval_loss": 0.009709909558296204,
|
| 654 |
+
"eval_runtime": 213.0126,
|
| 655 |
+
"eval_samples_per_second": 3.77,
|
| 656 |
+
"eval_steps_per_second": 0.474,
|
| 657 |
"step": 8136
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 9.007087486157253,
|
| 661 |
+
"grad_norm": 0.0011277415324002504,
|
| 662 |
"learning_rate": 5.106435338993479e-06,
|
| 663 |
"loss": 0.0001,
|
| 664 |
"step": 8200
|
| 665 |
},
|
| 666 |
{
|
| 667 |
"epoch": 9.018161683277963,
|
| 668 |
+
"grad_norm": 0.0012697929050773382,
|
| 669 |
"learning_rate": 4.4912021656207705e-06,
|
| 670 |
"loss": 0.0001,
|
| 671 |
"step": 8300
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 9.029235880398671,
|
| 675 |
+
"grad_norm": 0.0028499774634838104,
|
| 676 |
"learning_rate": 3.875968992248062e-06,
|
| 677 |
"loss": 0.0001,
|
| 678 |
"step": 8400
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 9.04031007751938,
|
| 682 |
+
"grad_norm": 0.0017348791006952524,
|
| 683 |
"learning_rate": 3.260735818875354e-06,
|
| 684 |
"loss": 0.0001,
|
| 685 |
"step": 8500
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 9.051384274640089,
|
| 689 |
+
"grad_norm": 0.0006883046007715166,
|
| 690 |
"learning_rate": 2.6455026455026455e-06,
|
| 691 |
"loss": 0.0001,
|
| 692 |
"step": 8600
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 9.062458471760797,
|
| 696 |
+
"grad_norm": 0.00142951391171664,
|
| 697 |
"learning_rate": 2.0302694721299375e-06,
|
| 698 |
"loss": 0.0001,
|
| 699 |
"step": 8700
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 9.073532668881507,
|
| 703 |
+
"grad_norm": 0.000702825200278312,
|
| 704 |
"learning_rate": 1.415036298757229e-06,
|
| 705 |
"loss": 0.0001,
|
| 706 |
"step": 8800
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"epoch": 9.084606866002215,
|
| 710 |
+
"grad_norm": 0.0009480651351623237,
|
| 711 |
"learning_rate": 7.998031253845208e-07,
|
| 712 |
"loss": 0.0001,
|
| 713 |
"step": 8900
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 9.095681063122923,
|
| 717 |
+
"grad_norm": 0.0010264083975926042,
|
| 718 |
"learning_rate": 1.8456995201181249e-07,
|
| 719 |
"loss": 0.0001,
|
| 720 |
"step": 9000
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 9.099003322259136,
|
| 724 |
+
"eval_accuracy": 0.9975093399750934,
|
| 725 |
+
"eval_loss": 0.009837848134338856,
|
| 726 |
+
"eval_runtime": 215.3394,
|
| 727 |
+
"eval_samples_per_second": 3.729,
|
| 728 |
+
"eval_steps_per_second": 0.469,
|
| 729 |
"step": 9030
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 9.099003322259136,
|
| 733 |
"step": 9030,
|
| 734 |
"total_flos": 6.328460909097596e+19,
|
| 735 |
+
"train_loss": 0.18714786747627524,
|
| 736 |
+
"train_runtime": 33340.824,
|
| 737 |
+
"train_samples_per_second": 2.167,
|
| 738 |
+
"train_steps_per_second": 0.271
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 9.099003322259136,
|
| 742 |
+
"eval_accuracy": 0.7664576802507836,
|
| 743 |
+
"eval_loss": 0.8547028303146362,
|
| 744 |
+
"eval_runtime": 304.3291,
|
| 745 |
+
"eval_samples_per_second": 4.193,
|
| 746 |
+
"eval_steps_per_second": 0.526,
|
| 747 |
"step": 9030
|
| 748 |
}
|
| 749 |
],
|