Model save
Browse files- README.md +26 -28
- adapter_model.safetensors +1 -1
- all_results.json +8 -8
- eval_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +842 -842
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -2,13 +2,11 @@
|
|
| 2 |
license: other
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
-
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
- generated_from_trainer
|
| 10 |
datasets:
|
| 11 |
-
-
|
| 12 |
base_model: 01-ai/Yi-6B
|
| 13 |
model-index:
|
| 14 |
- name: Yi-6B-zhihu5
|
|
@@ -20,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
# Yi-6B-zhihu5
|
| 22 |
|
| 23 |
-
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
-
- Loss: 2.
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -41,9 +39,9 @@ More information needed
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
-
- learning_rate:
|
| 45 |
-
- train_batch_size:
|
| 46 |
-
- eval_batch_size:
|
| 47 |
- seed: 42
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: cosine
|
|
@@ -54,26 +52,26 @@ The following hyperparameters were used during training:
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
-
| 2.
|
| 58 |
-
| 2.
|
| 59 |
-
| 2.
|
| 60 |
-
| 2.
|
| 61 |
-
| 2.
|
| 62 |
-
| 2.
|
| 63 |
-
| 2.
|
| 64 |
-
| 2.
|
| 65 |
-
| 2.
|
| 66 |
-
| 2.
|
| 67 |
-
| 2.
|
| 68 |
-
| 2.
|
| 69 |
-
| 2.
|
| 70 |
-
| 2.
|
| 71 |
-
| 2.
|
| 72 |
-
| 2.
|
| 73 |
-
| 2.
|
| 74 |
-
| 2.
|
| 75 |
-
| 2.
|
| 76 |
-
| 2.
|
| 77 |
|
| 78 |
|
| 79 |
### Framework versions
|
|
|
|
| 2 |
license: other
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
+
- generator
|
| 10 |
base_model: 01-ai/Yi-6B
|
| 11 |
model-index:
|
| 12 |
- name: Yi-6B-zhihu5
|
|
|
|
| 18 |
|
| 19 |
# Yi-6B-zhihu5
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the generator dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.5677
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 5e-06
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: cosine
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 2.6816 | 1.0 | 96 | 2.6328 |
|
| 56 |
+
| 2.6582 | 2.0 | 192 | 2.6169 |
|
| 57 |
+
| 2.6676 | 3.0 | 288 | 2.5983 |
|
| 58 |
+
| 2.6413 | 4.0 | 384 | 2.5891 |
|
| 59 |
+
| 2.581 | 5.0 | 480 | 2.5825 |
|
| 60 |
+
| 2.5884 | 6.0 | 576 | 2.5776 |
|
| 61 |
+
| 2.704 | 7.0 | 672 | 2.5741 |
|
| 62 |
+
| 2.608 | 8.0 | 768 | 2.5715 |
|
| 63 |
+
| 2.5454 | 9.0 | 864 | 2.5698 |
|
| 64 |
+
| 2.5938 | 10.0 | 960 | 2.5688 |
|
| 65 |
+
| 2.6129 | 11.0 | 1056 | 2.5682 |
|
| 66 |
+
| 2.6334 | 12.0 | 1152 | 2.5679 |
|
| 67 |
+
| 2.5013 | 13.0 | 1248 | 2.5678 |
|
| 68 |
+
| 2.519 | 14.0 | 1344 | 2.5677 |
|
| 69 |
+
| 2.5076 | 15.0 | 1440 | 2.5677 |
|
| 70 |
+
| 2.5443 | 16.0 | 1536 | 2.5677 |
|
| 71 |
+
| 2.5972 | 17.0 | 1632 | 2.5677 |
|
| 72 |
+
| 2.5361 | 18.0 | 1728 | 2.5677 |
|
| 73 |
+
| 2.5317 | 19.0 | 1824 | 2.5677 |
|
| 74 |
+
| 2.632 | 20.0 | 1920 | 2.5677 |
|
| 75 |
|
| 76 |
|
| 77 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 72673912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09603b655b91df777bd2d1500f9b1e168d1a951b2095fccbcc81e5fe59331c61
|
| 3 |
size 72673912
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_loss": 2.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 2561,
|
| 6 |
-
"eval_samples_per_second": 4.
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"train_loss":
|
| 9 |
-
"train_runtime":
|
| 10 |
"train_samples": 2561,
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 2.5677051544189453,
|
| 4 |
+
"eval_runtime": 164.7624,
|
| 5 |
"eval_samples": 2561,
|
| 6 |
+
"eval_samples_per_second": 4.649,
|
| 7 |
+
"eval_steps_per_second": 0.583,
|
| 8 |
+
"train_loss": 0.428011018037796,
|
| 9 |
+
"train_runtime": 2530.9924,
|
| 10 |
"train_samples": 2561,
|
| 11 |
+
"train_samples_per_second": 6.053,
|
| 12 |
+
"train_steps_per_second": 0.759
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_loss": 2.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 2561,
|
| 6 |
-
"eval_samples_per_second": 4.
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 2.5677051544189453,
|
| 4 |
+
"eval_runtime": 164.7624,
|
| 5 |
"eval_samples": 2561,
|
| 6 |
+
"eval_samples_per_second": 4.649,
|
| 7 |
+
"eval_steps_per_second": 0.583
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 2561,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.428011018037796,
|
| 4 |
+
"train_runtime": 2530.9924,
|
| 5 |
"train_samples": 2561,
|
| 6 |
+
"train_samples_per_second": 6.053,
|
| 7 |
+
"train_steps_per_second": 0.759
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -10,2482 +10,2482 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01,
|
| 13 |
-
"learning_rate": 5.208333333333333e-
|
| 14 |
"loss": 2.3378,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.05,
|
| 19 |
-
"learning_rate": 2.
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.1,
|
| 25 |
-
"learning_rate": 5.
|
| 26 |
-
"loss": 2.
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.16,
|
| 31 |
-
"learning_rate": 7.
|
| 32 |
"loss": 2.6688,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.21,
|
| 37 |
-
"learning_rate": 1.0416666666666667e-
|
| 38 |
"loss": 2.7272,
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.26,
|
| 43 |
-
"learning_rate": 1.
|
| 44 |
"loss": 2.6971,
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.31,
|
| 49 |
-
"learning_rate": 1.
|
| 50 |
-
"loss": 2.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.36,
|
| 55 |
-
"learning_rate": 1.8229166666666666e-
|
| 56 |
-
"loss": 2.
|
| 57 |
"step": 35
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.42,
|
| 61 |
-
"learning_rate": 2.
|
| 62 |
-
"loss": 2.
|
| 63 |
"step": 40
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.47,
|
| 67 |
-
"learning_rate": 2.
|
| 68 |
-
"loss": 2.
|
| 69 |
"step": 45
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.52,
|
| 73 |
-
"learning_rate": 2.604166666666667e-
|
| 74 |
-
"loss": 2.
|
| 75 |
"step": 50
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.57,
|
| 79 |
-
"learning_rate": 2.
|
| 80 |
-
"loss": 2.
|
| 81 |
"step": 55
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.62,
|
| 85 |
-
"learning_rate": 3.
|
| 86 |
-
"loss": 2.
|
| 87 |
"step": 60
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.68,
|
| 91 |
-
"learning_rate": 3.
|
| 92 |
-
"loss": 2.
|
| 93 |
"step": 65
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.73,
|
| 97 |
-
"learning_rate": 3.
|
| 98 |
-
"loss": 2.
|
| 99 |
"step": 70
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.78,
|
| 103 |
-
"learning_rate": 3.
|
| 104 |
-
"loss": 2.
|
| 105 |
"step": 75
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.83,
|
| 109 |
-
"learning_rate": 4.
|
| 110 |
-
"loss": 2.
|
| 111 |
"step": 80
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.89,
|
| 115 |
-
"learning_rate": 4.
|
| 116 |
-
"loss": 2.
|
| 117 |
"step": 85
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.94,
|
| 121 |
-
"learning_rate": 4.
|
| 122 |
-
"loss": 2.
|
| 123 |
"step": 90
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.99,
|
| 127 |
-
"learning_rate": 4.947916666666667e-
|
| 128 |
-
"loss": 2.
|
| 129 |
"step": 95
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 1.0,
|
| 133 |
-
"eval_loss": 2.
|
| 134 |
-
"eval_runtime": 173.
|
| 135 |
-
"eval_samples_per_second": 4.
|
| 136 |
"eval_steps_per_second": 1.106,
|
| 137 |
"step": 96
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.04,
|
| 141 |
-
"learning_rate": 5.208333333333334e-
|
| 142 |
-
"loss": 2.
|
| 143 |
"step": 100
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 1.09,
|
| 147 |
-
"learning_rate": 5.
|
| 148 |
-
"loss": 2.
|
| 149 |
"step": 105
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 1.15,
|
| 153 |
-
"learning_rate": 5.729166666666667e-
|
| 154 |
-
"loss": 2.
|
| 155 |
"step": 110
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 1.2,
|
| 159 |
-
"learning_rate": 5.989583333333334e-
|
| 160 |
-
"loss": 2.
|
| 161 |
"step": 115
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 1.25,
|
| 165 |
-
"learning_rate": 6.
|
| 166 |
-
"loss": 2.
|
| 167 |
"step": 120
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 1.3,
|
| 171 |
-
"learning_rate": 6.
|
| 172 |
-
"loss": 2.
|
| 173 |
"step": 125
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 1.35,
|
| 177 |
-
"learning_rate": 6.
|
| 178 |
-
"loss": 2.
|
| 179 |
"step": 130
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 1.41,
|
| 183 |
-
"learning_rate": 7.
|
| 184 |
-
"loss": 2.
|
| 185 |
"step": 135
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 1.46,
|
| 189 |
-
"learning_rate": 7.
|
| 190 |
-
"loss": 2.
|
| 191 |
"step": 140
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 1.51,
|
| 195 |
-
"learning_rate": 7.
|
| 196 |
-
"loss": 2.
|
| 197 |
"step": 145
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 1.56,
|
| 201 |
-
"learning_rate": 7.
|
| 202 |
-
"loss": 2.
|
| 203 |
"step": 150
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 1.61,
|
| 207 |
-
"learning_rate": 8.
|
| 208 |
-
"loss": 2.
|
| 209 |
"step": 155
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 1.67,
|
| 213 |
-
"learning_rate": 8.
|
| 214 |
-
"loss": 2.
|
| 215 |
"step": 160
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 1.72,
|
| 219 |
-
"learning_rate": 8.
|
| 220 |
-
"loss": 2.
|
| 221 |
"step": 165
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 1.77,
|
| 225 |
-
"learning_rate": 8.
|
| 226 |
-
"loss": 2.
|
| 227 |
"step": 170
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 1.82,
|
| 231 |
-
"learning_rate": 9.
|
| 232 |
-
"loss": 2.
|
| 233 |
"step": 175
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 1.88,
|
| 237 |
-
"learning_rate": 9.
|
| 238 |
-
"loss": 2.
|
| 239 |
"step": 180
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 1.93,
|
| 243 |
-
"learning_rate": 9.
|
| 244 |
-
"loss": 2.
|
| 245 |
"step": 185
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 1.98,
|
| 249 |
-
"learning_rate": 9.
|
| 250 |
-
"loss": 2.
|
| 251 |
"step": 190
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 2.0,
|
| 255 |
-
"eval_loss": 2.
|
| 256 |
-
"eval_runtime": 173.
|
| 257 |
-
"eval_samples_per_second": 4.
|
| 258 |
-
"eval_steps_per_second": 1.
|
| 259 |
"step": 192
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 2.03,
|
| 263 |
-
"learning_rate": 9.
|
| 264 |
-
"loss": 2.
|
| 265 |
"step": 195
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"epoch": 2.08,
|
| 269 |
-
"learning_rate": 9.999471159635538e-
|
| 270 |
-
"loss": 2.
|
| 271 |
"step": 200
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 2.14,
|
| 275 |
-
"learning_rate": 9.
|
| 276 |
-
"loss": 2.
|
| 277 |
"step": 205
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 2.19,
|
| 281 |
-
"learning_rate": 9.
|
| 282 |
-
"loss": 2.
|
| 283 |
"step": 210
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 2.24,
|
| 287 |
-
"learning_rate": 9.995629363702008e-
|
| 288 |
-
"loss": 2.
|
| 289 |
"step": 215
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 2.29,
|
| 293 |
-
"learning_rate": 9.
|
| 294 |
-
"loss": 2.
|
| 295 |
"step": 220
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 2.34,
|
| 299 |
-
"learning_rate": 9.
|
| 300 |
-
"loss": 2.
|
| 301 |
"step": 225
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 2.4,
|
| 305 |
-
"learning_rate": 9.988072574069363e-
|
| 306 |
-
"loss": 2.
|
| 307 |
"step": 230
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 2.45,
|
| 311 |
-
"learning_rate": 9.
|
| 312 |
-
"loss": 2.
|
| 313 |
"step": 235
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 2.5,
|
| 317 |
-
"learning_rate": 9.980973490458728e-
|
| 318 |
-
"loss": 2.
|
| 319 |
"step": 240
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 2.55,
|
| 323 |
-
"learning_rate": 9.
|
| 324 |
-
"loss": 2.
|
| 325 |
"step": 245
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 2.6,
|
| 329 |
-
"learning_rate": 9.
|
| 330 |
-
"loss": 2.
|
| 331 |
"step": 250
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 2.66,
|
| 335 |
-
"learning_rate": 9.
|
| 336 |
-
"loss": 2.
|
| 337 |
"step": 255
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 2.71,
|
| 341 |
-
"learning_rate": 9.
|
| 342 |
-
"loss": 2.
|
| 343 |
"step": 260
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 2.76,
|
| 347 |
-
"learning_rate": 9.
|
| 348 |
-
"loss": 2.
|
| 349 |
"step": 265
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 2.81,
|
| 353 |
-
"learning_rate": 9.
|
| 354 |
-
"loss": 2.
|
| 355 |
"step": 270
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 2.86,
|
| 359 |
-
"learning_rate": 9.
|
| 360 |
-
"loss": 2.
|
| 361 |
"step": 275
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 2.92,
|
| 365 |
-
"learning_rate": 9.
|
| 366 |
-
"loss": 2.
|
| 367 |
"step": 280
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 2.97,
|
| 371 |
-
"learning_rate": 9.928701021554545e-
|
| 372 |
-
"loss": 2.
|
| 373 |
"step": 285
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"epoch": 3.0,
|
| 377 |
-
"eval_loss": 2.
|
| 378 |
-
"eval_runtime": 173.
|
| 379 |
"eval_samples_per_second": 4.409,
|
| 380 |
"eval_steps_per_second": 1.105,
|
| 381 |
"step": 288
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 3.02,
|
| 385 |
-
"learning_rate": 9.
|
| 386 |
-
"loss": 2.
|
| 387 |
"step": 290
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 3.07,
|
| 391 |
-
"learning_rate": 9.
|
| 392 |
-
"loss": 2.
|
| 393 |
"step": 295
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 3.12,
|
| 397 |
-
"learning_rate": 9.
|
| 398 |
-
"loss": 2.
|
| 399 |
"step": 300
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 3.18,
|
| 403 |
-
"learning_rate": 9.
|
| 404 |
-
"loss": 2.
|
| 405 |
"step": 305
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 3.23,
|
| 409 |
-
"learning_rate": 9.885382740573385e-
|
| 410 |
-
"loss": 2.
|
| 411 |
"step": 310
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 3.28,
|
| 415 |
-
"learning_rate": 9.
|
| 416 |
-
"loss": 2.
|
| 417 |
"step": 315
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 3.33,
|
| 421 |
-
"learning_rate": 9.
|
| 422 |
-
"loss": 2.
|
| 423 |
"step": 320
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 3.39,
|
| 427 |
-
"learning_rate": 9.
|
| 428 |
-
"loss": 2.
|
| 429 |
"step": 325
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 3.44,
|
| 433 |
-
"learning_rate": 9.
|
| 434 |
-
"loss": 2.
|
| 435 |
"step": 330
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 3.49,
|
| 439 |
-
"learning_rate": 9.83197387995186e-
|
| 440 |
-
"loss": 2.
|
| 441 |
"step": 335
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 3.54,
|
| 445 |
-
"learning_rate": 9.
|
| 446 |
-
"loss": 2.
|
| 447 |
"step": 340
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 3.59,
|
| 451 |
-
"learning_rate": 9.
|
| 452 |
-
"loss": 2.
|
| 453 |
"step": 345
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 3.65,
|
| 457 |
-
"learning_rate": 9.
|
| 458 |
-
"loss": 2.
|
| 459 |
"step": 350
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 3.7,
|
| 463 |
-
"learning_rate": 9.78205501047412e-
|
| 464 |
-
"loss": 2.
|
| 465 |
"step": 355
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 3.75,
|
| 469 |
-
"learning_rate": 9.768584753741134e-
|
| 470 |
-
"loss": 2.
|
| 471 |
"step": 360
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 3.8,
|
| 475 |
-
"learning_rate": 9.
|
| 476 |
-
"loss": 2.
|
| 477 |
"step": 365
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 3.85,
|
| 481 |
-
"learning_rate": 9.
|
| 482 |
-
"loss": 2.
|
| 483 |
"step": 370
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 3.91,
|
| 487 |
-
"learning_rate": 9.72581436681634e-
|
| 488 |
-
"loss": 2.
|
| 489 |
"step": 375
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 3.96,
|
| 493 |
-
"learning_rate": 9.
|
| 494 |
-
"loss": 2.
|
| 495 |
"step": 380
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 4.0,
|
| 499 |
-
"eval_loss": 2.
|
| 500 |
-
"eval_runtime": 173.
|
| 501 |
-
"eval_samples_per_second": 4.
|
| 502 |
-
"eval_steps_per_second": 1.
|
| 503 |
"step": 384
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 4.01,
|
| 507 |
-
"learning_rate": 9.
|
| 508 |
-
"loss": 2.
|
| 509 |
"step": 385
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 4.06,
|
| 513 |
-
"learning_rate": 9.67952963378663e-
|
| 514 |
-
"loss": 2.
|
| 515 |
"step": 390
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 4.11,
|
| 519 |
-
"learning_rate": 9.
|
| 520 |
-
"loss": 2.
|
| 521 |
"step": 395
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 4.17,
|
| 525 |
-
"learning_rate": 9.
|
| 526 |
-
"loss": 2.
|
| 527 |
"step": 400
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 4.22,
|
| 531 |
-
"learning_rate": 9.
|
| 532 |
-
"loss": 2.
|
| 533 |
"step": 405
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 4.27,
|
| 537 |
-
"learning_rate": 9.
|
| 538 |
-
"loss": 2.
|
| 539 |
"step": 410
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 4.32,
|
| 543 |
-
"learning_rate": 9.
|
| 544 |
-
"loss": 2.
|
| 545 |
"step": 415
|
| 546 |
},
|
| 547 |
{
|
| 548 |
"epoch": 4.38,
|
| 549 |
-
"learning_rate": 9.
|
| 550 |
-
"loss": 2.
|
| 551 |
"step": 420
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 4.43,
|
| 555 |
-
"learning_rate": 9.
|
| 556 |
-
"loss": 2.
|
| 557 |
"step": 425
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 4.48,
|
| 561 |
-
"learning_rate": 9.
|
| 562 |
-
"loss": 2.
|
| 563 |
"step": 430
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 4.53,
|
| 567 |
-
"learning_rate": 9.519946465617217e-
|
| 568 |
-
"loss": 2.
|
| 569 |
"step": 435
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 4.58,
|
| 573 |
-
"learning_rate": 9.
|
| 574 |
-
"loss": 2.
|
| 575 |
"step": 440
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 4.64,
|
| 579 |
-
"learning_rate": 9.
|
| 580 |
-
"loss": 2.
|
| 581 |
"step": 445
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 4.69,
|
| 585 |
-
"learning_rate": 9.
|
| 586 |
-
"loss": 2.
|
| 587 |
"step": 450
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 4.74,
|
| 591 |
-
"learning_rate": 9.
|
| 592 |
-
"loss": 2.
|
| 593 |
"step": 455
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 4.79,
|
| 597 |
-
"learning_rate": 9.
|
| 598 |
-
"loss": 2.
|
| 599 |
"step": 460
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 4.84,
|
| 603 |
-
"learning_rate": 9.
|
| 604 |
-
"loss": 2.
|
| 605 |
"step": 465
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 4.9,
|
| 609 |
-
"learning_rate": 9.
|
| 610 |
-
"loss": 2.
|
| 611 |
"step": 470
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 4.95,
|
| 615 |
-
"learning_rate": 9.352673443295834e-
|
| 616 |
-
"loss": 2.
|
| 617 |
"step": 475
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 5.0,
|
| 621 |
-
"learning_rate": 9.
|
| 622 |
-
"loss": 2.
|
| 623 |
"step": 480
|
| 624 |
},
|
| 625 |
{
|
| 626 |
"epoch": 5.0,
|
| 627 |
-
"eval_loss": 2.
|
| 628 |
-
"eval_runtime": 173.
|
| 629 |
-
"eval_samples_per_second": 4.
|
| 630 |
-
"eval_steps_per_second": 1.
|
| 631 |
"step": 480
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 5.05,
|
| 635 |
-
"learning_rate": 9.
|
| 636 |
-
"loss": 2.
|
| 637 |
"step": 485
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 5.1,
|
| 641 |
-
"learning_rate": 9.283962639106464e-
|
| 642 |
-
"loss": 2.
|
| 643 |
"step": 490
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"epoch": 5.16,
|
| 647 |
-
"learning_rate": 9.260348498328393e-
|
| 648 |
-
"loss": 2.
|
| 649 |
"step": 495
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 5.21,
|
| 653 |
-
"learning_rate": 9.
|
| 654 |
-
"loss": 2.
|
| 655 |
"step": 500
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 5.26,
|
| 659 |
-
"learning_rate": 9.
|
| 660 |
-
"loss": 2.
|
| 661 |
"step": 505
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 5.31,
|
| 665 |
-
"learning_rate": 9.
|
| 666 |
-
"loss": 2.
|
| 667 |
"step": 510
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 5.36,
|
| 671 |
-
"learning_rate": 9.
|
| 672 |
-
"loss": 2.
|
| 673 |
"step": 515
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 5.42,
|
| 677 |
-
"learning_rate": 9.
|
| 678 |
-
"loss": 2.
|
| 679 |
"step": 520
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 5.47,
|
| 683 |
-
"learning_rate": 9.
|
| 684 |
-
"loss": 2.
|
| 685 |
"step": 525
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 5.52,
|
| 689 |
-
"learning_rate": 9.
|
| 690 |
-
"loss": 2.
|
| 691 |
"step": 530
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 5.57,
|
| 695 |
-
"learning_rate": 9.
|
| 696 |
-
"loss": 2.
|
| 697 |
"step": 535
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 5.62,
|
| 701 |
-
"learning_rate": 9.
|
| 702 |
-
"loss": 2.
|
| 703 |
"step": 540
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 5.68,
|
| 707 |
-
"learning_rate": 9.00518101381963e-
|
| 708 |
-
"loss": 2.
|
| 709 |
"step": 545
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 5.73,
|
| 713 |
-
"learning_rate": 8.
|
| 714 |
-
"loss": 2.
|
| 715 |
"step": 550
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 5.78,
|
| 719 |
-
"learning_rate": 8.
|
| 720 |
-
"loss": 2.
|
| 721 |
"step": 555
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 5.83,
|
| 725 |
-
"learning_rate": 8.
|
| 726 |
-
"loss": 2.
|
| 727 |
"step": 560
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 5.89,
|
| 731 |
-
"learning_rate": 8.
|
| 732 |
-
"loss": 2.
|
| 733 |
"step": 565
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 5.94,
|
| 737 |
-
"learning_rate": 8.
|
| 738 |
-
"loss": 2.
|
| 739 |
"step": 570
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 5.99,
|
| 743 |
-
"learning_rate": 8.
|
| 744 |
-
"loss": 2.
|
| 745 |
"step": 575
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 6.0,
|
| 749 |
-
"eval_loss": 2.
|
| 750 |
-
"eval_runtime": 173.
|
| 751 |
-
"eval_samples_per_second": 4.
|
| 752 |
-
"eval_steps_per_second": 1.
|
| 753 |
"step": 576
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 6.04,
|
| 757 |
-
"learning_rate": 8.806748724416156e-
|
| 758 |
-
"loss": 2.
|
| 759 |
"step": 580
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 6.09,
|
| 763 |
-
"learning_rate": 8.
|
| 764 |
-
"loss": 2.
|
| 765 |
"step": 585
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 6.15,
|
| 769 |
-
"learning_rate": 8.
|
| 770 |
-
"loss": 2.
|
| 771 |
"step": 590
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 6.2,
|
| 775 |
-
"learning_rate": 8.71694039549927e-
|
| 776 |
-
"loss": 2.
|
| 777 |
"step": 595
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 6.25,
|
| 781 |
-
"learning_rate": 8.68638668405062e-
|
| 782 |
-
"loss": 2.
|
| 783 |
"step": 600
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 6.3,
|
| 787 |
-
"learning_rate": 8.
|
| 788 |
-
"loss": 2.
|
| 789 |
"step": 605
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 6.35,
|
| 793 |
-
"learning_rate": 8.
|
| 794 |
-
"loss": 2.
|
| 795 |
"step": 610
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 6.41,
|
| 799 |
-
"learning_rate": 8.59290808889849e-
|
| 800 |
-
"loss": 2.
|
| 801 |
"step": 615
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 6.46,
|
| 805 |
-
"learning_rate": 8.
|
| 806 |
-
"loss": 2.
|
| 807 |
"step": 620
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 6.51,
|
| 811 |
-
"learning_rate": 8.
|
| 812 |
-
"loss": 2.
|
| 813 |
"step": 625
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 6.56,
|
| 817 |
-
"learning_rate": 8.496757632016836e-
|
| 818 |
-
"loss": 2.
|
| 819 |
"step": 630
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 6.61,
|
| 823 |
-
"learning_rate": 8.
|
| 824 |
-
"loss": 2.
|
| 825 |
"step": 635
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 6.67,
|
| 829 |
-
"learning_rate": 8.
|
| 830 |
-
"loss": 2.
|
| 831 |
"step": 640
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 6.72,
|
| 835 |
-
"learning_rate": 8.
|
| 836 |
-
"loss": 2.
|
| 837 |
"step": 645
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 6.77,
|
| 841 |
-
"learning_rate": 8.
|
| 842 |
-
"loss": 2.
|
| 843 |
"step": 650
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 6.82,
|
| 847 |
-
"learning_rate": 8.
|
| 848 |
-
"loss": 2.
|
| 849 |
"step": 655
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 6.88,
|
| 853 |
-
"learning_rate": 8.
|
| 854 |
-
"loss": 2.
|
| 855 |
"step": 660
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 6.93,
|
| 859 |
-
"learning_rate": 8.
|
| 860 |
-
"loss": 2.
|
| 861 |
"step": 665
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 6.98,
|
| 865 |
-
"learning_rate": 8.227843852629174e-
|
| 866 |
-
"loss": 2.
|
| 867 |
"step": 670
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 7.0,
|
| 871 |
-
"eval_loss": 2.
|
| 872 |
-
"eval_runtime": 173.
|
| 873 |
-
"eval_samples_per_second": 4.
|
| 874 |
-
"eval_steps_per_second": 1.
|
| 875 |
"step": 672
|
| 876 |
},
|
| 877 |
{
|
| 878 |
"epoch": 7.03,
|
| 879 |
-
"learning_rate": 8.
|
| 880 |
-
"loss": 2.
|
| 881 |
"step": 675
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 7.08,
|
| 885 |
-
"learning_rate": 8.
|
| 886 |
-
"loss": 2.
|
| 887 |
"step": 680
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 7.14,
|
| 891 |
-
"learning_rate": 8.
|
| 892 |
-
"loss": 2.
|
| 893 |
"step": 685
|
| 894 |
},
|
| 895 |
{
|
| 896 |
"epoch": 7.19,
|
| 897 |
-
"learning_rate": 8.
|
| 898 |
-
"loss": 2.
|
| 899 |
"step": 690
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 7.24,
|
| 903 |
-
"learning_rate": 8.
|
| 904 |
-
"loss": 2.
|
| 905 |
"step": 695
|
| 906 |
},
|
| 907 |
{
|
| 908 |
"epoch": 7.29,
|
| 909 |
-
"learning_rate": 8.
|
| 910 |
-
"loss": 2.
|
| 911 |
"step": 700
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 7.34,
|
| 915 |
-
"learning_rate": 7.978496522462167e-
|
| 916 |
-
"loss": 2.
|
| 917 |
"step": 705
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 7.4,
|
| 921 |
-
"learning_rate": 7.
|
| 922 |
-
"loss": 2.
|
| 923 |
"step": 710
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 7.45,
|
| 927 |
-
"learning_rate": 7.
|
| 928 |
-
"loss": 2.
|
| 929 |
"step": 715
|
| 930 |
},
|
| 931 |
{
|
| 932 |
"epoch": 7.5,
|
| 933 |
-
"learning_rate": 7.86788218175523e-
|
| 934 |
-
"loss": 2.
|
| 935 |
"step": 720
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 7.55,
|
| 939 |
-
"learning_rate": 7.
|
| 940 |
-
"loss": 2.
|
| 941 |
"step": 725
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 7.6,
|
| 945 |
-
"learning_rate": 7.
|
| 946 |
-
"loss": 2.
|
| 947 |
"step": 730
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 7.66,
|
| 951 |
-
"learning_rate": 7.
|
| 952 |
-
"loss": 2.
|
| 953 |
"step": 735
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 7.71,
|
| 957 |
-
"learning_rate": 7.
|
| 958 |
-
"loss": 2.
|
| 959 |
"step": 740
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 7.76,
|
| 963 |
-
"learning_rate": 7.
|
| 964 |
-
"loss": 2.
|
| 965 |
"step": 745
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 7.81,
|
| 969 |
-
"learning_rate": 7.
|
| 970 |
-
"loss": 2.
|
| 971 |
"step": 750
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 7.86,
|
| 975 |
-
"learning_rate": 7.
|
| 976 |
-
"loss": 2.
|
| 977 |
"step": 755
|
| 978 |
},
|
| 979 |
{
|
| 980 |
"epoch": 7.92,
|
| 981 |
-
"learning_rate": 7.
|
| 982 |
-
"loss": 2.
|
| 983 |
"step": 760
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 7.97,
|
| 987 |
-
"learning_rate": 7.
|
| 988 |
-
"loss": 2.
|
| 989 |
"step": 765
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 8.0,
|
| 993 |
-
"eval_loss": 2.
|
| 994 |
-
"eval_runtime":
|
| 995 |
-
"eval_samples_per_second": 4.
|
| 996 |
-
"eval_steps_per_second": 1.
|
| 997 |
"step": 768
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
"epoch": 8.02,
|
| 1001 |
-
"learning_rate": 7.
|
| 1002 |
-
"loss": 2.
|
| 1003 |
"step": 770
|
| 1004 |
},
|
| 1005 |
{
|
| 1006 |
"epoch": 8.07,
|
| 1007 |
-
"learning_rate": 7.
|
| 1008 |
-
"loss": 2.
|
| 1009 |
"step": 775
|
| 1010 |
},
|
| 1011 |
{
|
| 1012 |
"epoch": 8.12,
|
| 1013 |
-
"learning_rate": 7.
|
| 1014 |
-
"loss": 2.
|
| 1015 |
"step": 780
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 8.18,
|
| 1019 |
-
"learning_rate": 7.364996674957243e-
|
| 1020 |
-
"loss": 2.
|
| 1021 |
"step": 785
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 8.23,
|
| 1025 |
-
"learning_rate": 7.
|
| 1026 |
-
"loss": 2.
|
| 1027 |
"step": 790
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 8.28,
|
| 1031 |
-
"learning_rate": 7.
|
| 1032 |
-
"loss": 2.
|
| 1033 |
"step": 795
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 8.33,
|
| 1037 |
-
"learning_rate": 7.
|
| 1038 |
-
"loss": 2.
|
| 1039 |
"step": 800
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
"epoch": 8.39,
|
| 1043 |
-
"learning_rate": 7.203286997546543e-
|
| 1044 |
-
"loss": 2.
|
| 1045 |
"step": 805
|
| 1046 |
},
|
| 1047 |
{
|
| 1048 |
"epoch": 8.44,
|
| 1049 |
-
"learning_rate": 7.
|
| 1050 |
-
"loss": 2.
|
| 1051 |
"step": 810
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
"epoch": 8.49,
|
| 1055 |
-
"learning_rate": 7.
|
| 1056 |
-
"loss": 2.
|
| 1057 |
"step": 815
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 8.54,
|
| 1061 |
-
"learning_rate": 7.
|
| 1062 |
-
"loss": 2.
|
| 1063 |
"step": 820
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 8.59,
|
| 1067 |
-
"learning_rate": 7.
|
| 1068 |
-
"loss": 2.
|
| 1069 |
"step": 825
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 8.65,
|
| 1073 |
-
"learning_rate": 6.
|
| 1074 |
-
"loss": 2.
|
| 1075 |
"step": 830
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
"epoch": 8.7,
|
| 1079 |
-
"learning_rate": 6.
|
| 1080 |
-
"loss": 2.
|
| 1081 |
"step": 835
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
"epoch": 8.75,
|
| 1085 |
-
"learning_rate": 6.913417161825449e-
|
| 1086 |
-
"loss": 2.
|
| 1087 |
"step": 840
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
"epoch": 8.8,
|
| 1091 |
-
"learning_rate": 6.
|
| 1092 |
-
"loss": 2.
|
| 1093 |
"step": 845
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 8.85,
|
| 1097 |
-
"learning_rate": 6.
|
| 1098 |
-
"loss": 2.
|
| 1099 |
"step": 850
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 8.91,
|
| 1103 |
-
"learning_rate": 6.
|
| 1104 |
-
"loss": 2.
|
| 1105 |
"step": 855
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
"epoch": 8.96,
|
| 1109 |
-
"learning_rate": 6.
|
| 1110 |
-
"loss": 2.
|
| 1111 |
"step": 860
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
"epoch": 9.0,
|
| 1115 |
-
"eval_loss": 2.
|
| 1116 |
-
"eval_runtime": 173.
|
| 1117 |
-
"eval_samples_per_second": 4.
|
| 1118 |
-
"eval_steps_per_second": 1.
|
| 1119 |
"step": 864
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 9.01,
|
| 1123 |
-
"learning_rate": 6.
|
| 1124 |
-
"loss": 2.
|
| 1125 |
"step": 865
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 9.06,
|
| 1129 |
-
"learning_rate": 6.
|
| 1130 |
-
"loss": 2.
|
| 1131 |
"step": 870
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 9.11,
|
| 1135 |
-
"learning_rate": 6.
|
| 1136 |
-
"loss": 2.
|
| 1137 |
"step": 875
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 9.17,
|
| 1141 |
-
"learning_rate": 6.
|
| 1142 |
-
"loss": 2.
|
| 1143 |
"step": 880
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 9.22,
|
| 1147 |
-
"learning_rate": 6.529515100482768e-
|
| 1148 |
-
"loss": 2.
|
| 1149 |
"step": 885
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 9.27,
|
| 1153 |
-
"learning_rate": 6.486180033018039e-
|
| 1154 |
-
"loss": 2.
|
| 1155 |
"step": 890
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 9.32,
|
| 1159 |
-
"learning_rate": 6.
|
| 1160 |
-
"loss": 2.
|
| 1161 |
"step": 895
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 9.38,
|
| 1165 |
-
"learning_rate": 6.
|
| 1166 |
-
"loss": 2.
|
| 1167 |
"step": 900
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 9.43,
|
| 1171 |
-
"learning_rate": 6.
|
| 1172 |
-
"loss": 2.
|
| 1173 |
"step": 905
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 9.48,
|
| 1177 |
-
"learning_rate": 6.
|
| 1178 |
-
"loss": 2.
|
| 1179 |
"step": 910
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 9.53,
|
| 1183 |
-
"learning_rate": 6.
|
| 1184 |
-
"loss": 2.
|
| 1185 |
"step": 915
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 9.58,
|
| 1189 |
-
"learning_rate": 6.
|
| 1190 |
-
"loss": 2.
|
| 1191 |
"step": 920
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 9.64,
|
| 1195 |
-
"learning_rate": 6.
|
| 1196 |
-
"loss": 2.
|
| 1197 |
"step": 925
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 9.69,
|
| 1201 |
-
"learning_rate": 6.
|
| 1202 |
-
"loss": 2.
|
| 1203 |
"step": 930
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 9.74,
|
| 1207 |
-
"learning_rate": 6.
|
| 1208 |
-
"loss": 2.
|
| 1209 |
"step": 935
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 9.79,
|
| 1213 |
-
"learning_rate": 6.
|
| 1214 |
-
"loss": 2.
|
| 1215 |
"step": 940
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 9.84,
|
| 1219 |
-
"learning_rate": 6.
|
| 1220 |
-
"loss": 2.
|
| 1221 |
"step": 945
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"epoch": 9.9,
|
| 1225 |
-
"learning_rate": 5.957614021457072e-
|
| 1226 |
-
"loss": 2.
|
| 1227 |
"step": 950
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 9.95,
|
| 1231 |
-
"learning_rate": 5.
|
| 1232 |
-
"loss": 2.
|
| 1233 |
"step": 955
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 10.0,
|
| 1237 |
-
"learning_rate": 5.
|
| 1238 |
-
"loss": 2.
|
| 1239 |
"step": 960
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 10.0,
|
| 1243 |
-
"eval_loss": 2.
|
| 1244 |
-
"eval_runtime":
|
| 1245 |
-
"eval_samples_per_second": 4.
|
| 1246 |
-
"eval_steps_per_second": 1.
|
| 1247 |
"step": 960
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
"epoch": 10.05,
|
| 1251 |
-
"learning_rate": 5.823444856965393e-
|
| 1252 |
-
"loss": 2.
|
| 1253 |
"step": 965
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 10.1,
|
| 1257 |
-
"learning_rate": 5.
|
| 1258 |
-
"loss": 2.
|
| 1259 |
"step": 970
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 10.16,
|
| 1263 |
-
"learning_rate": 5.733652372276809e-
|
| 1264 |
-
"loss": 2.
|
| 1265 |
"step": 975
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
"epoch": 10.21,
|
| 1269 |
-
"learning_rate": 5.
|
| 1270 |
-
"loss": 2.
|
| 1271 |
"step": 980
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 10.26,
|
| 1275 |
-
"learning_rate": 5.
|
| 1276 |
-
"loss": 2.
|
| 1277 |
"step": 985
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 10.31,
|
| 1281 |
-
"learning_rate": 5.
|
| 1282 |
-
"loss": 2.
|
| 1283 |
"step": 990
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
"epoch": 10.36,
|
| 1287 |
-
"learning_rate": 5.
|
| 1288 |
-
"loss": 2.
|
| 1289 |
"step": 995
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 10.42,
|
| 1293 |
-
"learning_rate": 5.50817539091401e-
|
| 1294 |
-
"loss": 2.
|
| 1295 |
"step": 1000
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 10.47,
|
| 1299 |
-
"learning_rate": 5.
|
| 1300 |
-
"loss": 2.
|
| 1301 |
"step": 1005
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
"epoch": 10.52,
|
| 1305 |
-
"learning_rate": 5.
|
| 1306 |
-
"loss": 2.
|
| 1307 |
"step": 1010
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
"epoch": 10.57,
|
| 1311 |
-
"learning_rate": 5.372355478441483e-
|
| 1312 |
-
"loss": 2.
|
| 1313 |
"step": 1015
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 10.62,
|
| 1317 |
-
"learning_rate": 5.327015646150716e-
|
| 1318 |
-
"loss": 2.
|
| 1319 |
"step": 1020
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
"epoch": 10.68,
|
| 1323 |
-
"learning_rate": 5.
|
| 1324 |
-
"loss": 2.
|
| 1325 |
"step": 1025
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 10.73,
|
| 1329 |
-
"learning_rate": 5.
|
| 1330 |
-
"loss": 2.
|
| 1331 |
"step": 1030
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 10.78,
|
| 1335 |
-
"learning_rate": 5.
|
| 1336 |
-
"loss": 2.
|
| 1337 |
"step": 1035
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 10.83,
|
| 1341 |
-
"learning_rate": 5.
|
| 1342 |
-
"loss": 2.
|
| 1343 |
"step": 1040
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
"epoch": 10.89,
|
| 1347 |
-
"learning_rate": 5.09998615663101e-
|
| 1348 |
-
"loss": 2.
|
| 1349 |
"step": 1045
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 10.94,
|
| 1353 |
-
"learning_rate": 5.
|
| 1354 |
-
"loss": 2.
|
| 1355 |
"step": 1050
|
| 1356 |
},
|
| 1357 |
{
|
| 1358 |
"epoch": 10.99,
|
| 1359 |
-
"learning_rate": 5.
|
| 1360 |
-
"loss": 2.
|
| 1361 |
"step": 1055
|
| 1362 |
},
|
| 1363 |
{
|
| 1364 |
"epoch": 11.0,
|
| 1365 |
-
"eval_loss": 2.
|
| 1366 |
-
"eval_runtime": 173.
|
| 1367 |
"eval_samples_per_second": 4.423,
|
| 1368 |
"eval_steps_per_second": 1.109,
|
| 1369 |
"step": 1056
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
"epoch": 11.04,
|
| 1373 |
-
"learning_rate": 4.
|
| 1374 |
-
"loss": 2.
|
| 1375 |
"step": 1060
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
"epoch": 11.09,
|
| 1379 |
-
"learning_rate": 4.918191341867566e-
|
| 1380 |
-
"loss": 2.
|
| 1381 |
"step": 1065
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
"epoch": 11.15,
|
| 1385 |
-
"learning_rate": 4.
|
| 1386 |
-
"loss": 2.
|
| 1387 |
"step": 1070
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 11.2,
|
| 1391 |
-
"learning_rate": 4.
|
| 1392 |
-
"loss": 2.
|
| 1393 |
"step": 1075
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
"epoch": 11.25,
|
| 1397 |
-
"learning_rate": 4.
|
| 1398 |
-
"loss": 2.
|
| 1399 |
"step": 1080
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 11.3,
|
| 1403 |
-
"learning_rate": 4.
|
| 1404 |
-
"loss": 2.
|
| 1405 |
"step": 1085
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 11.35,
|
| 1409 |
-
"learning_rate": 4.
|
| 1410 |
-
"loss": 2.
|
| 1411 |
"step": 1090
|
| 1412 |
},
|
| 1413 |
{
|
| 1414 |
"epoch": 11.41,
|
| 1415 |
-
"learning_rate": 4.
|
| 1416 |
-
"loss": 2.
|
| 1417 |
"step": 1095
|
| 1418 |
},
|
| 1419 |
{
|
| 1420 |
"epoch": 11.46,
|
| 1421 |
-
"learning_rate": 4.
|
| 1422 |
-
"loss": 2.
|
| 1423 |
"step": 1100
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 11.51,
|
| 1427 |
-
"learning_rate": 4.
|
| 1428 |
-
"loss": 2.
|
| 1429 |
"step": 1105
|
| 1430 |
},
|
| 1431 |
{
|
| 1432 |
"epoch": 11.56,
|
| 1433 |
-
"learning_rate": 4.
|
| 1434 |
-
"loss": 2.
|
| 1435 |
"step": 1110
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
"epoch": 11.61,
|
| 1439 |
-
"learning_rate": 4.
|
| 1440 |
-
"loss": 2.
|
| 1441 |
"step": 1115
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
"epoch": 11.67,
|
| 1445 |
-
"learning_rate": 4.
|
| 1446 |
-
"loss": 2.
|
| 1447 |
"step": 1120
|
| 1448 |
},
|
| 1449 |
{
|
| 1450 |
"epoch": 11.72,
|
| 1451 |
-
"learning_rate": 4.
|
| 1452 |
-
"loss": 2.
|
| 1453 |
"step": 1125
|
| 1454 |
},
|
| 1455 |
{
|
| 1456 |
"epoch": 11.77,
|
| 1457 |
-
"learning_rate": 4.
|
| 1458 |
-
"loss": 2.
|
| 1459 |
"step": 1130
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
"epoch": 11.82,
|
| 1463 |
-
"learning_rate": 4.
|
| 1464 |
-
"loss": 2.
|
| 1465 |
"step": 1135
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 11.88,
|
| 1469 |
-
"learning_rate": 4.
|
| 1470 |
-
"loss": 2.
|
| 1471 |
"step": 1140
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 11.93,
|
| 1475 |
-
"learning_rate": 4.
|
| 1476 |
-
"loss": 2.
|
| 1477 |
"step": 1145
|
| 1478 |
},
|
| 1479 |
{
|
| 1480 |
"epoch": 11.98,
|
| 1481 |
-
"learning_rate": 4.
|
| 1482 |
-
"loss": 2.
|
| 1483 |
"step": 1150
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 12.0,
|
| 1487 |
-
"eval_loss": 2.
|
| 1488 |
-
"eval_runtime": 173.
|
| 1489 |
-
"eval_samples_per_second": 4.
|
| 1490 |
-
"eval_steps_per_second": 1.
|
| 1491 |
"step": 1152
|
| 1492 |
},
|
| 1493 |
{
|
| 1494 |
"epoch": 12.03,
|
| 1495 |
-
"learning_rate": 4.
|
| 1496 |
-
"loss": 2.
|
| 1497 |
"step": 1155
|
| 1498 |
},
|
| 1499 |
{
|
| 1500 |
"epoch": 12.08,
|
| 1501 |
-
"learning_rate": 4.
|
| 1502 |
-
"loss": 2.
|
| 1503 |
"step": 1160
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
"epoch": 12.14,
|
| 1507 |
-
"learning_rate": 4.015634417124932e-
|
| 1508 |
-
"loss": 2.
|
| 1509 |
"step": 1165
|
| 1510 |
},
|
| 1511 |
{
|
| 1512 |
"epoch": 12.19,
|
| 1513 |
-
"learning_rate": 3.
|
| 1514 |
-
"loss": 2.
|
| 1515 |
"step": 1170
|
| 1516 |
},
|
| 1517 |
{
|
| 1518 |
"epoch": 12.24,
|
| 1519 |
-
"learning_rate": 3.
|
| 1520 |
-
"loss": 2.
|
| 1521 |
"step": 1175
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 12.29,
|
| 1525 |
-
"learning_rate": 3.
|
| 1526 |
-
"loss": 2.
|
| 1527 |
"step": 1180
|
| 1528 |
},
|
| 1529 |
{
|
| 1530 |
"epoch": 12.34,
|
| 1531 |
-
"learning_rate": 3.
|
| 1532 |
-
"loss": 2.
|
| 1533 |
"step": 1185
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 12.4,
|
| 1537 |
-
"learning_rate": 3.
|
| 1538 |
-
"loss": 2.
|
| 1539 |
"step": 1190
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
"epoch": 12.45,
|
| 1543 |
-
"learning_rate": 3.
|
| 1544 |
-
"loss": 2.
|
| 1545 |
"step": 1195
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 12.5,
|
| 1549 |
-
"learning_rate": 3.
|
| 1550 |
-
"loss": 2.
|
| 1551 |
"step": 1200
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 12.55,
|
| 1555 |
-
"learning_rate": 3.
|
| 1556 |
-
"loss": 2.
|
| 1557 |
"step": 1205
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 12.6,
|
| 1561 |
-
"learning_rate": 3.618318339490009e-
|
| 1562 |
-
"loss": 2.
|
| 1563 |
"step": 1210
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 12.66,
|
| 1567 |
-
"learning_rate": 3.
|
| 1568 |
-
"loss": 2.
|
| 1569 |
"step": 1215
|
| 1570 |
},
|
| 1571 |
{
|
| 1572 |
"epoch": 12.71,
|
| 1573 |
-
"learning_rate": 3.
|
| 1574 |
-
"loss": 2.
|
| 1575 |
"step": 1220
|
| 1576 |
},
|
| 1577 |
{
|
| 1578 |
"epoch": 12.76,
|
| 1579 |
-
"learning_rate": 3.
|
| 1580 |
-
"loss": 2.
|
| 1581 |
"step": 1225
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 12.81,
|
| 1585 |
-
"learning_rate": 3.444544296144546e-
|
| 1586 |
-
"loss": 2.
|
| 1587 |
"step": 1230
|
| 1588 |
},
|
| 1589 |
{
|
| 1590 |
"epoch": 12.86,
|
| 1591 |
-
"learning_rate": 3.401413162669057e-
|
| 1592 |
-
"loss": 2.
|
| 1593 |
"step": 1235
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 12.92,
|
| 1597 |
-
"learning_rate": 3.
|
| 1598 |
-
"loss": 2.
|
| 1599 |
"step": 1240
|
| 1600 |
},
|
| 1601 |
{
|
| 1602 |
"epoch": 12.97,
|
| 1603 |
-
"learning_rate": 3.
|
| 1604 |
-
"loss": 2.
|
| 1605 |
"step": 1245
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
"epoch": 13.0,
|
| 1609 |
-
"eval_loss": 2.
|
| 1610 |
-
"eval_runtime":
|
| 1611 |
-
"eval_samples_per_second": 4.
|
| 1612 |
-
"eval_steps_per_second": 1.
|
| 1613 |
"step": 1248
|
| 1614 |
},
|
| 1615 |
{
|
| 1616 |
"epoch": 13.02,
|
| 1617 |
-
"learning_rate": 3.272826531885229e-
|
| 1618 |
-
"loss": 2.
|
| 1619 |
"step": 1250
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 13.07,
|
| 1623 |
-
"learning_rate": 3.
|
| 1624 |
-
"loss": 2.
|
| 1625 |
"step": 1255
|
| 1626 |
},
|
| 1627 |
{
|
| 1628 |
"epoch": 13.12,
|
| 1629 |
-
"learning_rate": 3.
|
| 1630 |
-
"loss": 2.
|
| 1631 |
"step": 1260
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
"epoch": 13.18,
|
| 1635 |
-
"learning_rate": 3.
|
| 1636 |
-
"loss": 2.
|
| 1637 |
"step": 1265
|
| 1638 |
},
|
| 1639 |
{
|
| 1640 |
"epoch": 13.23,
|
| 1641 |
-
"learning_rate": 3.
|
| 1642 |
-
"loss": 2.
|
| 1643 |
"step": 1270
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 13.28,
|
| 1647 |
-
"learning_rate": 3.
|
| 1648 |
-
"loss": 2.
|
| 1649 |
"step": 1275
|
| 1650 |
},
|
| 1651 |
{
|
| 1652 |
"epoch": 13.33,
|
| 1653 |
-
"learning_rate": 3.
|
| 1654 |
-
"loss": 2.
|
| 1655 |
"step": 1280
|
| 1656 |
},
|
| 1657 |
{
|
| 1658 |
"epoch": 13.39,
|
| 1659 |
-
"learning_rate": 2.97794946715456e-
|
| 1660 |
-
"loss": 2.
|
| 1661 |
"step": 1285
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 13.44,
|
| 1665 |
-
"learning_rate": 2.
|
| 1666 |
-
"loss": 2.
|
| 1667 |
"step": 1290
|
| 1668 |
},
|
| 1669 |
{
|
| 1670 |
"epoch": 13.49,
|
| 1671 |
-
"learning_rate": 2.
|
| 1672 |
-
"loss": 2.
|
| 1673 |
"step": 1295
|
| 1674 |
},
|
| 1675 |
{
|
| 1676 |
"epoch": 13.54,
|
| 1677 |
-
"learning_rate": 2.
|
| 1678 |
-
"loss": 2.
|
| 1679 |
"step": 1300
|
| 1680 |
},
|
| 1681 |
{
|
| 1682 |
"epoch": 13.59,
|
| 1683 |
-
"learning_rate": 2.
|
| 1684 |
-
"loss": 2.
|
| 1685 |
"step": 1305
|
| 1686 |
},
|
| 1687 |
{
|
| 1688 |
"epoch": 13.65,
|
| 1689 |
-
"learning_rate": 2.
|
| 1690 |
-
"loss": 2.
|
| 1691 |
"step": 1310
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
"epoch": 13.7,
|
| 1695 |
-
"learning_rate": 2.
|
| 1696 |
-
"loss": 2.
|
| 1697 |
"step": 1315
|
| 1698 |
},
|
| 1699 |
{
|
| 1700 |
"epoch": 13.75,
|
| 1701 |
-
"learning_rate": 2.
|
| 1702 |
-
"loss": 2.
|
| 1703 |
"step": 1320
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 13.8,
|
| 1707 |
-
"learning_rate": 2.
|
| 1708 |
-
"loss": 2.
|
| 1709 |
"step": 1325
|
| 1710 |
},
|
| 1711 |
{
|
| 1712 |
"epoch": 13.85,
|
| 1713 |
-
"learning_rate": 2.61101136065115e-
|
| 1714 |
-
"loss": 2.
|
| 1715 |
"step": 1330
|
| 1716 |
},
|
| 1717 |
{
|
| 1718 |
"epoch": 13.91,
|
| 1719 |
-
"learning_rate": 2.
|
| 1720 |
-
"loss": 2.
|
| 1721 |
"step": 1335
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
"epoch": 13.96,
|
| 1725 |
-
"learning_rate": 2.
|
| 1726 |
-
"loss": 2.
|
| 1727 |
"step": 1340
|
| 1728 |
},
|
| 1729 |
{
|
| 1730 |
"epoch": 14.0,
|
| 1731 |
-
"eval_loss": 2.
|
| 1732 |
-
"eval_runtime": 174.
|
| 1733 |
-
"eval_samples_per_second": 4.
|
| 1734 |
-
"eval_steps_per_second": 1.
|
| 1735 |
"step": 1344
|
| 1736 |
},
|
| 1737 |
{
|
| 1738 |
"epoch": 14.01,
|
| 1739 |
-
"learning_rate": 2.
|
| 1740 |
-
"loss": 2.
|
| 1741 |
"step": 1345
|
| 1742 |
},
|
| 1743 |
{
|
| 1744 |
"epoch": 14.06,
|
| 1745 |
-
"learning_rate": 2.
|
| 1746 |
-
"loss": 2.
|
| 1747 |
"step": 1350
|
| 1748 |
},
|
| 1749 |
{
|
| 1750 |
"epoch": 14.11,
|
| 1751 |
-
"learning_rate": 2.
|
| 1752 |
-
"loss": 2.
|
| 1753 |
"step": 1355
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 14.17,
|
| 1757 |
-
"learning_rate": 2.
|
| 1758 |
-
"loss": 2.
|
| 1759 |
"step": 1360
|
| 1760 |
},
|
| 1761 |
{
|
| 1762 |
"epoch": 14.22,
|
| 1763 |
-
"learning_rate": 2.
|
| 1764 |
-
"loss": 2.
|
| 1765 |
"step": 1365
|
| 1766 |
},
|
| 1767 |
{
|
| 1768 |
"epoch": 14.27,
|
| 1769 |
-
"learning_rate": 2.
|
| 1770 |
-
"loss": 2.
|
| 1771 |
"step": 1370
|
| 1772 |
},
|
| 1773 |
{
|
| 1774 |
"epoch": 14.32,
|
| 1775 |
-
"learning_rate": 2.
|
| 1776 |
-
"loss": 2.
|
| 1777 |
"step": 1375
|
| 1778 |
},
|
| 1779 |
{
|
| 1780 |
"epoch": 14.38,
|
| 1781 |
-
"learning_rate": 2.
|
| 1782 |
-
"loss": 2.
|
| 1783 |
"step": 1380
|
| 1784 |
},
|
| 1785 |
{
|
| 1786 |
"epoch": 14.43,
|
| 1787 |
-
"learning_rate": 2.
|
| 1788 |
-
"loss": 2.
|
| 1789 |
"step": 1385
|
| 1790 |
},
|
| 1791 |
{
|
| 1792 |
"epoch": 14.48,
|
| 1793 |
-
"learning_rate": 2.
|
| 1794 |
-
"loss": 2.
|
| 1795 |
"step": 1390
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 14.53,
|
| 1799 |
-
"learning_rate": 2.
|
| 1800 |
-
"loss": 2.
|
| 1801 |
"step": 1395
|
| 1802 |
},
|
| 1803 |
{
|
| 1804 |
"epoch": 14.58,
|
| 1805 |
-
"learning_rate": 2.
|
| 1806 |
-
"loss": 2.
|
| 1807 |
"step": 1400
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 14.64,
|
| 1811 |
-
"learning_rate": 2.036125860051594e-
|
| 1812 |
-
"loss": 2.
|
| 1813 |
"step": 1405
|
| 1814 |
},
|
| 1815 |
{
|
| 1816 |
"epoch": 14.69,
|
| 1817 |
-
"learning_rate": 1.
|
| 1818 |
-
"loss": 2.
|
| 1819 |
"step": 1410
|
| 1820 |
},
|
| 1821 |
{
|
| 1822 |
"epoch": 14.74,
|
| 1823 |
-
"learning_rate": 1.
|
| 1824 |
-
"loss": 2.
|
| 1825 |
"step": 1415
|
| 1826 |
},
|
| 1827 |
{
|
| 1828 |
"epoch": 14.79,
|
| 1829 |
-
"learning_rate": 1.
|
| 1830 |
-
"loss": 2.
|
| 1831 |
"step": 1420
|
| 1832 |
},
|
| 1833 |
{
|
| 1834 |
"epoch": 14.84,
|
| 1835 |
-
"learning_rate": 1.
|
| 1836 |
-
"loss": 2.
|
| 1837 |
"step": 1425
|
| 1838 |
},
|
| 1839 |
{
|
| 1840 |
"epoch": 14.9,
|
| 1841 |
-
"learning_rate": 1.
|
| 1842 |
-
"loss": 2.
|
| 1843 |
"step": 1430
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
"epoch": 14.95,
|
| 1847 |
-
"learning_rate": 1.
|
| 1848 |
-
"loss": 2.
|
| 1849 |
"step": 1435
|
| 1850 |
},
|
| 1851 |
{
|
| 1852 |
"epoch": 15.0,
|
| 1853 |
-
"learning_rate": 1.
|
| 1854 |
-
"loss": 2.
|
| 1855 |
"step": 1440
|
| 1856 |
},
|
| 1857 |
{
|
| 1858 |
"epoch": 15.0,
|
| 1859 |
-
"eval_loss": 2.
|
| 1860 |
-
"eval_runtime": 174.
|
| 1861 |
"eval_samples_per_second": 4.387,
|
| 1862 |
"eval_steps_per_second": 1.1,
|
| 1863 |
"step": 1440
|
| 1864 |
},
|
| 1865 |
{
|
| 1866 |
"epoch": 15.05,
|
| 1867 |
-
"learning_rate": 1.
|
| 1868 |
-
"loss": 2.
|
| 1869 |
"step": 1445
|
| 1870 |
},
|
| 1871 |
{
|
| 1872 |
"epoch": 15.1,
|
| 1873 |
-
"learning_rate": 1.
|
| 1874 |
-
"loss": 2.
|
| 1875 |
"step": 1450
|
| 1876 |
},
|
| 1877 |
{
|
| 1878 |
"epoch": 15.16,
|
| 1879 |
-
"learning_rate": 1.
|
| 1880 |
-
"loss": 2.
|
| 1881 |
"step": 1455
|
| 1882 |
},
|
| 1883 |
{
|
| 1884 |
"epoch": 15.21,
|
| 1885 |
-
"learning_rate": 1.
|
| 1886 |
-
"loss": 2.
|
| 1887 |
"step": 1460
|
| 1888 |
},
|
| 1889 |
{
|
| 1890 |
"epoch": 15.26,
|
| 1891 |
-
"learning_rate": 1.
|
| 1892 |
-
"loss": 2.
|
| 1893 |
"step": 1465
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 15.31,
|
| 1897 |
-
"learning_rate": 1.5820384898856433e-
|
| 1898 |
-
"loss": 2.
|
| 1899 |
"step": 1470
|
| 1900 |
},
|
| 1901 |
{
|
| 1902 |
"epoch": 15.36,
|
| 1903 |
-
"learning_rate": 1.
|
| 1904 |
-
"loss": 2.
|
| 1905 |
"step": 1475
|
| 1906 |
},
|
| 1907 |
{
|
| 1908 |
"epoch": 15.42,
|
| 1909 |
-
"learning_rate": 1.5162604839467265e-
|
| 1910 |
-
"loss": 2.
|
| 1911 |
"step": 1480
|
| 1912 |
},
|
| 1913 |
{
|
| 1914 |
"epoch": 15.47,
|
| 1915 |
-
"learning_rate": 1.4838019315853796e-
|
| 1916 |
-
"loss": 2.
|
| 1917 |
"step": 1485
|
| 1918 |
},
|
| 1919 |
{
|
| 1920 |
"epoch": 15.52,
|
| 1921 |
-
"learning_rate": 1.
|
| 1922 |
-
"loss": 2.
|
| 1923 |
"step": 1490
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 15.57,
|
| 1927 |
-
"learning_rate": 1.
|
| 1928 |
-
"loss": 2.
|
| 1929 |
"step": 1495
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 15.62,
|
| 1933 |
-
"learning_rate": 1.
|
| 1934 |
-
"loss": 2.
|
| 1935 |
"step": 1500
|
| 1936 |
},
|
| 1937 |
{
|
| 1938 |
"epoch": 15.68,
|
| 1939 |
-
"learning_rate": 1.3568996935355194e-
|
| 1940 |
-
"loss": 2.
|
| 1941 |
"step": 1505
|
| 1942 |
},
|
| 1943 |
{
|
| 1944 |
"epoch": 15.73,
|
| 1945 |
-
"learning_rate": 1.
|
| 1946 |
-
"loss": 2.
|
| 1947 |
"step": 1510
|
| 1948 |
},
|
| 1949 |
{
|
| 1950 |
"epoch": 15.78,
|
| 1951 |
-
"learning_rate": 1.
|
| 1952 |
-
"loss": 2.
|
| 1953 |
"step": 1515
|
| 1954 |
},
|
| 1955 |
{
|
| 1956 |
"epoch": 15.83,
|
| 1957 |
-
"learning_rate": 1.
|
| 1958 |
-
"loss": 2.
|
| 1959 |
"step": 1520
|
| 1960 |
},
|
| 1961 |
{
|
| 1962 |
"epoch": 15.89,
|
| 1963 |
-
"learning_rate": 1.234813555970129e-
|
| 1964 |
-
"loss": 2.
|
| 1965 |
"step": 1525
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 15.94,
|
| 1969 |
-
"learning_rate": 1.
|
| 1970 |
-
"loss": 2.
|
| 1971 |
"step": 1530
|
| 1972 |
},
|
| 1973 |
{
|
| 1974 |
"epoch": 15.99,
|
| 1975 |
-
"learning_rate": 1.
|
| 1976 |
-
"loss": 2.
|
| 1977 |
"step": 1535
|
| 1978 |
},
|
| 1979 |
{
|
| 1980 |
"epoch": 16.0,
|
| 1981 |
-
"eval_loss": 2.
|
| 1982 |
-
"eval_runtime": 174.
|
| 1983 |
-
"eval_samples_per_second": 4.
|
| 1984 |
-
"eval_steps_per_second": 1.
|
| 1985 |
"step": 1536
|
| 1986 |
},
|
| 1987 |
{
|
| 1988 |
"epoch": 16.04,
|
| 1989 |
-
"learning_rate": 1.
|
| 1990 |
-
"loss": 2.
|
| 1991 |
"step": 1540
|
| 1992 |
},
|
| 1993 |
{
|
| 1994 |
"epoch": 16.09,
|
| 1995 |
-
"learning_rate": 1.1177049141451223e-
|
| 1996 |
-
"loss": 2.
|
| 1997 |
"step": 1545
|
| 1998 |
},
|
| 1999 |
{
|
| 2000 |
"epoch": 16.15,
|
| 2001 |
-
"learning_rate": 1.
|
| 2002 |
-
"loss": 2.
|
| 2003 |
"step": 1550
|
| 2004 |
},
|
| 2005 |
{
|
| 2006 |
"epoch": 16.2,
|
| 2007 |
-
"learning_rate": 1.
|
| 2008 |
-
"loss": 2.
|
| 2009 |
"step": 1555
|
| 2010 |
},
|
| 2011 |
{
|
| 2012 |
"epoch": 16.25,
|
| 2013 |
-
"learning_rate": 1.
|
| 2014 |
-
"loss": 2.
|
| 2015 |
"step": 1560
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 16.3,
|
| 2019 |
-
"learning_rate": 1.
|
| 2020 |
-
"loss": 2.
|
| 2021 |
"step": 1565
|
| 2022 |
},
|
| 2023 |
{
|
| 2024 |
"epoch": 16.35,
|
| 2025 |
-
"learning_rate": 9.
|
| 2026 |
-
"loss": 2.
|
| 2027 |
"step": 1570
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 16.41,
|
| 2031 |
-
"learning_rate": 9.
|
| 2032 |
-
"loss": 2.
|
| 2033 |
"step": 1575
|
| 2034 |
},
|
| 2035 |
{
|
| 2036 |
"epoch": 16.46,
|
| 2037 |
-
"learning_rate": 9.
|
| 2038 |
-
"loss": 2.
|
| 2039 |
"step": 1580
|
| 2040 |
},
|
| 2041 |
{
|
| 2042 |
"epoch": 16.51,
|
| 2043 |
-
"learning_rate": 8.
|
| 2044 |
-
"loss": 2.
|
| 2045 |
"step": 1585
|
| 2046 |
},
|
| 2047 |
{
|
| 2048 |
"epoch": 16.56,
|
| 2049 |
-
"learning_rate": 8.732003345756812e-
|
| 2050 |
-
"loss": 2.
|
| 2051 |
"step": 1590
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 16.61,
|
| 2055 |
-
"learning_rate": 8.
|
| 2056 |
-
"loss": 2.
|
| 2057 |
"step": 1595
|
| 2058 |
},
|
| 2059 |
{
|
| 2060 |
"epoch": 16.67,
|
| 2061 |
-
"learning_rate": 8.
|
| 2062 |
-
"loss": 2.
|
| 2063 |
"step": 1600
|
| 2064 |
},
|
| 2065 |
{
|
| 2066 |
"epoch": 16.72,
|
| 2067 |
-
"learning_rate": 7.
|
| 2068 |
-
"loss": 2.
|
| 2069 |
"step": 1605
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 16.77,
|
| 2073 |
-
"learning_rate": 7.733022865994599e-
|
| 2074 |
-
"loss": 2.
|
| 2075 |
"step": 1610
|
| 2076 |
},
|
| 2077 |
{
|
| 2078 |
"epoch": 16.82,
|
| 2079 |
-
"learning_rate": 7.
|
| 2080 |
-
"loss": 2.
|
| 2081 |
"step": 1615
|
| 2082 |
},
|
| 2083 |
{
|
| 2084 |
"epoch": 16.88,
|
| 2085 |
-
"learning_rate": 7.
|
| 2086 |
-
"loss": 2.
|
| 2087 |
"step": 1620
|
| 2088 |
},
|
| 2089 |
{
|
| 2090 |
"epoch": 16.93,
|
| 2091 |
-
"learning_rate": 7.
|
| 2092 |
-
"loss": 2.
|
| 2093 |
"step": 1625
|
| 2094 |
},
|
| 2095 |
{
|
| 2096 |
"epoch": 16.98,
|
| 2097 |
-
"learning_rate": 6.789918423653285e-
|
| 2098 |
-
"loss": 2.
|
| 2099 |
"step": 1630
|
| 2100 |
},
|
| 2101 |
{
|
| 2102 |
"epoch": 17.0,
|
| 2103 |
-
"eval_loss": 2.
|
| 2104 |
-
"eval_runtime":
|
| 2105 |
-
"eval_samples_per_second": 4.
|
| 2106 |
-
"eval_steps_per_second":
|
| 2107 |
"step": 1632
|
| 2108 |
},
|
| 2109 |
{
|
| 2110 |
"epoch": 17.03,
|
| 2111 |
-
"learning_rate": 6.
|
| 2112 |
-
"loss": 2.
|
| 2113 |
"step": 1635
|
| 2114 |
},
|
| 2115 |
{
|
| 2116 |
"epoch": 17.08,
|
| 2117 |
-
"learning_rate": 6.
|
| 2118 |
-
"loss": 2.
|
| 2119 |
"step": 1640
|
| 2120 |
},
|
| 2121 |
{
|
| 2122 |
"epoch": 17.14,
|
| 2123 |
-
"learning_rate": 6.
|
| 2124 |
-
"loss": 2.
|
| 2125 |
"step": 1645
|
| 2126 |
},
|
| 2127 |
{
|
| 2128 |
"epoch": 17.19,
|
| 2129 |
-
"learning_rate": 5.
|
| 2130 |
-
"loss": 2.
|
| 2131 |
"step": 1650
|
| 2132 |
},
|
| 2133 |
{
|
| 2134 |
"epoch": 17.24,
|
| 2135 |
-
"learning_rate": 5.
|
| 2136 |
-
"loss": 2.
|
| 2137 |
"step": 1655
|
| 2138 |
},
|
| 2139 |
{
|
| 2140 |
"epoch": 17.29,
|
| 2141 |
-
"learning_rate": 5.
|
| 2142 |
-
"loss": 2.
|
| 2143 |
"step": 1660
|
| 2144 |
},
|
| 2145 |
{
|
| 2146 |
"epoch": 17.34,
|
| 2147 |
-
"learning_rate": 5.
|
| 2148 |
-
"loss": 2.
|
| 2149 |
"step": 1665
|
| 2150 |
},
|
| 2151 |
{
|
| 2152 |
"epoch": 17.4,
|
| 2153 |
-
"learning_rate": 5.
|
| 2154 |
-
"loss": 2.
|
| 2155 |
"step": 1670
|
| 2156 |
},
|
| 2157 |
{
|
| 2158 |
"epoch": 17.45,
|
| 2159 |
-
"learning_rate": 4.
|
| 2160 |
-
"loss": 2.
|
| 2161 |
"step": 1675
|
| 2162 |
},
|
| 2163 |
{
|
| 2164 |
"epoch": 17.5,
|
| 2165 |
-
"learning_rate": 4.
|
| 2166 |
-
"loss": 2.
|
| 2167 |
"step": 1680
|
| 2168 |
},
|
| 2169 |
{
|
| 2170 |
"epoch": 17.55,
|
| 2171 |
-
"learning_rate": 4.
|
| 2172 |
-
"loss": 2.
|
| 2173 |
"step": 1685
|
| 2174 |
},
|
| 2175 |
{
|
| 2176 |
"epoch": 17.6,
|
| 2177 |
-
"learning_rate": 4.
|
| 2178 |
-
"loss": 2.
|
| 2179 |
"step": 1690
|
| 2180 |
},
|
| 2181 |
{
|
| 2182 |
"epoch": 17.66,
|
| 2183 |
-
"learning_rate": 4.
|
| 2184 |
-
"loss": 2.
|
| 2185 |
"step": 1695
|
| 2186 |
},
|
| 2187 |
{
|
| 2188 |
"epoch": 17.71,
|
| 2189 |
-
"learning_rate": 3.946391248748821e-
|
| 2190 |
-
"loss": 2.
|
| 2191 |
"step": 1700
|
| 2192 |
},
|
| 2193 |
{
|
| 2194 |
"epoch": 17.76,
|
| 2195 |
-
"learning_rate": 3.
|
| 2196 |
-
"loss": 2.
|
| 2197 |
"step": 1705
|
| 2198 |
},
|
| 2199 |
{
|
| 2200 |
"epoch": 17.81,
|
| 2201 |
-
"learning_rate": 3.600054390390778e-
|
| 2202 |
-
"loss": 2.
|
| 2203 |
"step": 1710
|
| 2204 |
},
|
| 2205 |
{
|
| 2206 |
"epoch": 17.86,
|
| 2207 |
-
"learning_rate": 3.
|
| 2208 |
-
"loss": 2.
|
| 2209 |
"step": 1715
|
| 2210 |
},
|
| 2211 |
{
|
| 2212 |
"epoch": 17.92,
|
| 2213 |
-
"learning_rate": 3.269053732550581e-
|
| 2214 |
-
"loss": 2.
|
| 2215 |
"step": 1720
|
| 2216 |
},
|
| 2217 |
{
|
| 2218 |
"epoch": 17.97,
|
| 2219 |
-
"learning_rate": 3.
|
| 2220 |
-
"loss": 2.
|
| 2221 |
"step": 1725
|
| 2222 |
},
|
| 2223 |
{
|
| 2224 |
"epoch": 18.0,
|
| 2225 |
-
"eval_loss": 2.
|
| 2226 |
-
"eval_runtime":
|
| 2227 |
-
"eval_samples_per_second": 4.
|
| 2228 |
-
"eval_steps_per_second":
|
| 2229 |
"step": 1728
|
| 2230 |
},
|
| 2231 |
{
|
| 2232 |
"epoch": 18.02,
|
| 2233 |
-
"learning_rate": 2.
|
| 2234 |
-
"loss": 2.
|
| 2235 |
"step": 1730
|
| 2236 |
},
|
| 2237 |
{
|
| 2238 |
"epoch": 18.07,
|
| 2239 |
-
"learning_rate": 2.80154604581197e-
|
| 2240 |
-
"loss": 2.
|
| 2241 |
"step": 1735
|
| 2242 |
},
|
| 2243 |
{
|
| 2244 |
"epoch": 18.12,
|
| 2245 |
-
"learning_rate": 2.653493525244721e-
|
| 2246 |
-
"loss": 2.
|
| 2247 |
"step": 1740
|
| 2248 |
},
|
| 2249 |
{
|
| 2250 |
"epoch": 18.18,
|
| 2251 |
-
"learning_rate": 2.
|
| 2252 |
-
"loss": 2.
|
| 2253 |
"step": 1745
|
| 2254 |
},
|
| 2255 |
{
|
| 2256 |
"epoch": 18.23,
|
| 2257 |
-
"learning_rate": 2.
|
| 2258 |
-
"loss": 2.
|
| 2259 |
"step": 1750
|
| 2260 |
},
|
| 2261 |
{
|
| 2262 |
"epoch": 18.28,
|
| 2263 |
-
"learning_rate": 2.232857356169199e-
|
| 2264 |
-
"loss": 2.
|
| 2265 |
"step": 1755
|
| 2266 |
},
|
| 2267 |
{
|
| 2268 |
"epoch": 18.33,
|
| 2269 |
-
"learning_rate": 2.
|
| 2270 |
-
"loss": 2.
|
| 2271 |
"step": 1760
|
| 2272 |
},
|
| 2273 |
{
|
| 2274 |
"epoch": 18.39,
|
| 2275 |
-
"learning_rate": 1.972149451072297e-
|
| 2276 |
-
"loss": 2.
|
| 2277 |
"step": 1765
|
| 2278 |
},
|
| 2279 |
{
|
| 2280 |
"epoch": 18.44,
|
| 2281 |
-
"learning_rate": 1.
|
| 2282 |
-
"loss": 2.
|
| 2283 |
"step": 1770
|
| 2284 |
},
|
| 2285 |
{
|
| 2286 |
"epoch": 18.49,
|
| 2287 |
-
"learning_rate": 1.
|
| 2288 |
-
"loss": 2.
|
| 2289 |
"step": 1775
|
| 2290 |
},
|
| 2291 |
{
|
| 2292 |
"epoch": 18.54,
|
| 2293 |
-
"learning_rate": 1.
|
| 2294 |
-
"loss": 2.
|
| 2295 |
"step": 1780
|
| 2296 |
},
|
| 2297 |
{
|
| 2298 |
"epoch": 18.59,
|
| 2299 |
-
"learning_rate": 1.
|
| 2300 |
-
"loss": 2.
|
| 2301 |
"step": 1785
|
| 2302 |
},
|
| 2303 |
{
|
| 2304 |
"epoch": 18.65,
|
| 2305 |
-
"learning_rate": 1.
|
| 2306 |
-
"loss": 2.
|
| 2307 |
"step": 1790
|
| 2308 |
},
|
| 2309 |
{
|
| 2310 |
"epoch": 18.7,
|
| 2311 |
-
"learning_rate": 1.
|
| 2312 |
-
"loss": 2.
|
| 2313 |
"step": 1795
|
| 2314 |
},
|
| 2315 |
{
|
| 2316 |
"epoch": 18.75,
|
| 2317 |
-
"learning_rate": 1.
|
| 2318 |
-
"loss": 2.
|
| 2319 |
"step": 1800
|
| 2320 |
},
|
| 2321 |
{
|
| 2322 |
"epoch": 18.8,
|
| 2323 |
-
"learning_rate": 1.
|
| 2324 |
-
"loss": 2.
|
| 2325 |
"step": 1805
|
| 2326 |
},
|
| 2327 |
{
|
| 2328 |
"epoch": 18.85,
|
| 2329 |
-
"learning_rate": 9.
|
| 2330 |
-
"loss": 2.
|
| 2331 |
"step": 1810
|
| 2332 |
},
|
| 2333 |
{
|
| 2334 |
"epoch": 18.91,
|
| 2335 |
-
"learning_rate": 9.
|
| 2336 |
-
"loss": 2.
|
| 2337 |
"step": 1815
|
| 2338 |
},
|
| 2339 |
{
|
| 2340 |
"epoch": 18.96,
|
| 2341 |
-
"learning_rate": 8.
|
| 2342 |
-
"loss": 2.
|
| 2343 |
"step": 1820
|
| 2344 |
},
|
| 2345 |
{
|
| 2346 |
"epoch": 19.0,
|
| 2347 |
-
"eval_loss": 2.
|
| 2348 |
-
"eval_runtime":
|
| 2349 |
-
"eval_samples_per_second": 4.
|
| 2350 |
-
"eval_steps_per_second":
|
| 2351 |
"step": 1824
|
| 2352 |
},
|
| 2353 |
{
|
| 2354 |
"epoch": 19.01,
|
| 2355 |
-
"learning_rate": 7.
|
| 2356 |
-
"loss": 2.
|
| 2357 |
"step": 1825
|
| 2358 |
},
|
| 2359 |
{
|
| 2360 |
"epoch": 19.06,
|
| 2361 |
-
"learning_rate": 6.
|
| 2362 |
-
"loss": 2.
|
| 2363 |
"step": 1830
|
| 2364 |
},
|
| 2365 |
{
|
| 2366 |
"epoch": 19.11,
|
| 2367 |
-
"learning_rate": 5.
|
| 2368 |
-
"loss": 2.
|
| 2369 |
"step": 1835
|
| 2370 |
},
|
| 2371 |
{
|
| 2372 |
"epoch": 19.17,
|
| 2373 |
-
"learning_rate": 5.
|
| 2374 |
-
"loss": 2.
|
| 2375 |
"step": 1840
|
| 2376 |
},
|
| 2377 |
{
|
| 2378 |
"epoch": 19.22,
|
| 2379 |
-
"learning_rate": 4.640895825593683e-
|
| 2380 |
-
"loss": 2.
|
| 2381 |
"step": 1845
|
| 2382 |
},
|
| 2383 |
{
|
| 2384 |
"epoch": 19.27,
|
| 2385 |
-
"learning_rate": 4.
|
| 2386 |
-
"loss": 2.
|
| 2387 |
"step": 1850
|
| 2388 |
},
|
| 2389 |
{
|
| 2390 |
"epoch": 19.32,
|
| 2391 |
-
"learning_rate": 3.
|
| 2392 |
-
"loss": 2.
|
| 2393 |
"step": 1855
|
| 2394 |
},
|
| 2395 |
{
|
| 2396 |
"epoch": 19.38,
|
| 2397 |
-
"learning_rate": 2.
|
| 2398 |
-
"loss": 2.
|
| 2399 |
"step": 1860
|
| 2400 |
},
|
| 2401 |
{
|
| 2402 |
"epoch": 19.43,
|
| 2403 |
-
"learning_rate": 2.
|
| 2404 |
-
"loss": 2.
|
| 2405 |
"step": 1865
|
| 2406 |
},
|
| 2407 |
{
|
| 2408 |
"epoch": 19.48,
|
| 2409 |
-
"learning_rate": 2.
|
| 2410 |
-
"loss": 2.
|
| 2411 |
"step": 1870
|
| 2412 |
},
|
| 2413 |
{
|
| 2414 |
"epoch": 19.53,
|
| 2415 |
-
"learning_rate": 1.
|
| 2416 |
-
"loss": 2.
|
| 2417 |
"step": 1875
|
| 2418 |
},
|
| 2419 |
{
|
| 2420 |
"epoch": 19.58,
|
| 2421 |
-
"learning_rate": 1.
|
| 2422 |
-
"loss": 2.
|
| 2423 |
"step": 1880
|
| 2424 |
},
|
| 2425 |
{
|
| 2426 |
"epoch": 19.64,
|
| 2427 |
-
"learning_rate": 1.
|
| 2428 |
-
"loss": 2.
|
| 2429 |
"step": 1885
|
| 2430 |
},
|
| 2431 |
{
|
| 2432 |
"epoch": 19.69,
|
| 2433 |
-
"learning_rate": 7.
|
| 2434 |
-
"loss": 2.
|
| 2435 |
"step": 1890
|
| 2436 |
},
|
| 2437 |
{
|
| 2438 |
"epoch": 19.74,
|
| 2439 |
-
"learning_rate": 5.
|
| 2440 |
-
"loss": 2.
|
| 2441 |
"step": 1895
|
| 2442 |
},
|
| 2443 |
{
|
| 2444 |
"epoch": 19.79,
|
| 2445 |
-
"learning_rate": 3.
|
| 2446 |
-
"loss": 2.
|
| 2447 |
"step": 1900
|
| 2448 |
},
|
| 2449 |
{
|
| 2450 |
"epoch": 19.84,
|
| 2451 |
-
"learning_rate": 1.
|
| 2452 |
-
"loss": 2.
|
| 2453 |
"step": 1905
|
| 2454 |
},
|
| 2455 |
{
|
| 2456 |
"epoch": 19.9,
|
| 2457 |
-
"learning_rate": 8.26304875812256e-
|
| 2458 |
-
"loss": 2.
|
| 2459 |
"step": 1910
|
| 2460 |
},
|
| 2461 |
{
|
| 2462 |
"epoch": 19.95,
|
| 2463 |
-
"learning_rate": 2.
|
| 2464 |
-
"loss": 2.
|
| 2465 |
"step": 1915
|
| 2466 |
},
|
| 2467 |
{
|
| 2468 |
"epoch": 20.0,
|
| 2469 |
"learning_rate": 0.0,
|
| 2470 |
-
"loss": 2.
|
| 2471 |
"step": 1920
|
| 2472 |
},
|
| 2473 |
{
|
| 2474 |
"epoch": 20.0,
|
| 2475 |
-
"eval_loss": 2.
|
| 2476 |
-
"eval_runtime":
|
| 2477 |
-
"eval_samples_per_second": 4.
|
| 2478 |
-
"eval_steps_per_second":
|
| 2479 |
"step": 1920
|
| 2480 |
},
|
| 2481 |
{
|
| 2482 |
"epoch": 20.0,
|
| 2483 |
"step": 1920,
|
| 2484 |
"total_flos": 1.0984887148766822e+18,
|
| 2485 |
-
"train_loss":
|
| 2486 |
-
"train_runtime":
|
| 2487 |
-
"train_samples_per_second":
|
| 2488 |
-
"train_steps_per_second": 0.
|
| 2489 |
}
|
| 2490 |
],
|
| 2491 |
"logging_steps": 5,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 5.208333333333333e-08,
|
| 14 |
"loss": 2.3378,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 2.604166666666667e-07,
|
| 20 |
+
"loss": 2.6783,
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 5.208333333333334e-07,
|
| 26 |
+
"loss": 2.6965,
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.16,
|
| 31 |
+
"learning_rate": 7.8125e-07,
|
| 32 |
"loss": 2.6688,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.21,
|
| 37 |
+
"learning_rate": 1.0416666666666667e-06,
|
| 38 |
"loss": 2.7272,
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.26,
|
| 43 |
+
"learning_rate": 1.3020833333333335e-06,
|
| 44 |
"loss": 2.6971,
|
| 45 |
"step": 25
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.31,
|
| 49 |
+
"learning_rate": 1.5625e-06,
|
| 50 |
+
"loss": 2.638,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.36,
|
| 55 |
+
"learning_rate": 1.8229166666666666e-06,
|
| 56 |
+
"loss": 2.6253,
|
| 57 |
"step": 35
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.42,
|
| 61 |
+
"learning_rate": 2.0833333333333334e-06,
|
| 62 |
+
"loss": 2.6373,
|
| 63 |
"step": 40
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.47,
|
| 67 |
+
"learning_rate": 2.3437500000000002e-06,
|
| 68 |
+
"loss": 2.6102,
|
| 69 |
"step": 45
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.52,
|
| 73 |
+
"learning_rate": 2.604166666666667e-06,
|
| 74 |
+
"loss": 2.592,
|
| 75 |
"step": 50
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.57,
|
| 79 |
+
"learning_rate": 2.8645833333333334e-06,
|
| 80 |
+
"loss": 2.5777,
|
| 81 |
"step": 55
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.62,
|
| 85 |
+
"learning_rate": 3.125e-06,
|
| 86 |
+
"loss": 2.6194,
|
| 87 |
"step": 60
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.68,
|
| 91 |
+
"learning_rate": 3.385416666666667e-06,
|
| 92 |
+
"loss": 2.608,
|
| 93 |
"step": 65
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.73,
|
| 97 |
+
"learning_rate": 3.6458333333333333e-06,
|
| 98 |
+
"loss": 2.6459,
|
| 99 |
"step": 70
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.78,
|
| 103 |
+
"learning_rate": 3.90625e-06,
|
| 104 |
+
"loss": 2.6886,
|
| 105 |
"step": 75
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.83,
|
| 109 |
+
"learning_rate": 4.166666666666667e-06,
|
| 110 |
+
"loss": 2.4494,
|
| 111 |
"step": 80
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.89,
|
| 115 |
+
"learning_rate": 4.427083333333334e-06,
|
| 116 |
+
"loss": 2.6428,
|
| 117 |
"step": 85
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.94,
|
| 121 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 122 |
+
"loss": 2.6275,
|
| 123 |
"step": 90
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.99,
|
| 127 |
+
"learning_rate": 4.947916666666667e-06,
|
| 128 |
+
"loss": 2.6816,
|
| 129 |
"step": 95
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 1.0,
|
| 133 |
+
"eval_loss": 2.6328012943267822,
|
| 134 |
+
"eval_runtime": 173.5828,
|
| 135 |
+
"eval_samples_per_second": 4.413,
|
| 136 |
"eval_steps_per_second": 1.106,
|
| 137 |
"step": 96
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.04,
|
| 141 |
+
"learning_rate": 5.208333333333334e-06,
|
| 142 |
+
"loss": 2.716,
|
| 143 |
"step": 100
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 1.09,
|
| 147 |
+
"learning_rate": 5.468750000000001e-06,
|
| 148 |
+
"loss": 2.6176,
|
| 149 |
"step": 105
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 1.15,
|
| 153 |
+
"learning_rate": 5.729166666666667e-06,
|
| 154 |
+
"loss": 2.6579,
|
| 155 |
"step": 110
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 1.2,
|
| 159 |
+
"learning_rate": 5.989583333333334e-06,
|
| 160 |
+
"loss": 2.7026,
|
| 161 |
"step": 115
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 1.25,
|
| 165 |
+
"learning_rate": 6.25e-06,
|
| 166 |
+
"loss": 2.6952,
|
| 167 |
"step": 120
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 1.3,
|
| 171 |
+
"learning_rate": 6.510416666666667e-06,
|
| 172 |
+
"loss": 2.5857,
|
| 173 |
"step": 125
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 1.35,
|
| 177 |
+
"learning_rate": 6.770833333333334e-06,
|
| 178 |
+
"loss": 2.718,
|
| 179 |
"step": 130
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 1.41,
|
| 183 |
+
"learning_rate": 7.031250000000001e-06,
|
| 184 |
+
"loss": 2.6229,
|
| 185 |
"step": 135
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 1.46,
|
| 189 |
+
"learning_rate": 7.291666666666667e-06,
|
| 190 |
+
"loss": 2.6168,
|
| 191 |
"step": 140
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 1.51,
|
| 195 |
+
"learning_rate": 7.552083333333334e-06,
|
| 196 |
+
"loss": 2.5181,
|
| 197 |
"step": 145
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 1.56,
|
| 201 |
+
"learning_rate": 7.8125e-06,
|
| 202 |
+
"loss": 2.6514,
|
| 203 |
"step": 150
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 1.61,
|
| 207 |
+
"learning_rate": 8.072916666666667e-06,
|
| 208 |
+
"loss": 2.6047,
|
| 209 |
"step": 155
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 1.67,
|
| 213 |
+
"learning_rate": 8.333333333333334e-06,
|
| 214 |
+
"loss": 2.5415,
|
| 215 |
"step": 160
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 1.72,
|
| 219 |
+
"learning_rate": 8.59375e-06,
|
| 220 |
+
"loss": 2.6892,
|
| 221 |
"step": 165
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 1.77,
|
| 225 |
+
"learning_rate": 8.854166666666667e-06,
|
| 226 |
+
"loss": 2.7038,
|
| 227 |
"step": 170
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 1.82,
|
| 231 |
+
"learning_rate": 9.114583333333334e-06,
|
| 232 |
+
"loss": 2.6528,
|
| 233 |
"step": 175
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 1.88,
|
| 237 |
+
"learning_rate": 9.375000000000001e-06,
|
| 238 |
+
"loss": 2.5846,
|
| 239 |
"step": 180
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 1.93,
|
| 243 |
+
"learning_rate": 9.635416666666668e-06,
|
| 244 |
+
"loss": 2.4526,
|
| 245 |
"step": 185
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 1.98,
|
| 249 |
+
"learning_rate": 9.895833333333334e-06,
|
| 250 |
+
"loss": 2.6582,
|
| 251 |
"step": 190
|
| 252 |
},
|
| 253 |
{
|
| 254 |
"epoch": 2.0,
|
| 255 |
+
"eval_loss": 2.6169474124908447,
|
| 256 |
+
"eval_runtime": 173.6466,
|
| 257 |
+
"eval_samples_per_second": 4.411,
|
| 258 |
+
"eval_steps_per_second": 1.106,
|
| 259 |
"step": 192
|
| 260 |
},
|
| 261 |
{
|
| 262 |
"epoch": 2.03,
|
| 263 |
+
"learning_rate": 9.99992563069711e-06,
|
| 264 |
+
"loss": 2.5407,
|
| 265 |
"step": 195
|
| 266 |
},
|
| 267 |
{
|
| 268 |
"epoch": 2.08,
|
| 269 |
+
"learning_rate": 9.999471159635538e-06,
|
| 270 |
+
"loss": 2.6746,
|
| 271 |
"step": 200
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 2.14,
|
| 275 |
+
"learning_rate": 9.998603571300204e-06,
|
| 276 |
+
"loss": 2.653,
|
| 277 |
"step": 205
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 2.19,
|
| 281 |
+
"learning_rate": 9.997322937381829e-06,
|
| 282 |
+
"loss": 2.5313,
|
| 283 |
"step": 210
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 2.24,
|
| 287 |
+
"learning_rate": 9.995629363702008e-06,
|
| 288 |
+
"loss": 2.7327,
|
| 289 |
"step": 215
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 2.29,
|
| 293 |
+
"learning_rate": 9.993522990204453e-06,
|
| 294 |
+
"loss": 2.5849,
|
| 295 |
"step": 220
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 2.34,
|
| 299 |
+
"learning_rate": 9.991003990943424e-06,
|
| 300 |
+
"loss": 2.6192,
|
| 301 |
"step": 225
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 2.4,
|
| 305 |
+
"learning_rate": 9.988072574069363e-06,
|
| 306 |
+
"loss": 2.6161,
|
| 307 |
"step": 230
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 2.45,
|
| 311 |
+
"learning_rate": 9.984728981811676e-06,
|
| 312 |
+
"loss": 2.536,
|
| 313 |
"step": 235
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 2.5,
|
| 317 |
+
"learning_rate": 9.980973490458728e-06,
|
| 318 |
+
"loss": 2.5393,
|
| 319 |
"step": 240
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 2.55,
|
| 323 |
+
"learning_rate": 9.976806410335015e-06,
|
| 324 |
+
"loss": 2.6175,
|
| 325 |
"step": 245
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 2.6,
|
| 329 |
+
"learning_rate": 9.972228085775512e-06,
|
| 330 |
+
"loss": 2.5245,
|
| 331 |
"step": 250
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 2.66,
|
| 335 |
+
"learning_rate": 9.967238895097223e-06,
|
| 336 |
+
"loss": 2.6436,
|
| 337 |
"step": 255
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 2.71,
|
| 341 |
+
"learning_rate": 9.961839250567925e-06,
|
| 342 |
+
"loss": 2.6141,
|
| 343 |
"step": 260
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 2.76,
|
| 347 |
+
"learning_rate": 9.956029598372092e-06,
|
| 348 |
+
"loss": 2.6642,
|
| 349 |
"step": 265
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 2.81,
|
| 353 |
+
"learning_rate": 9.94981041857404e-06,
|
| 354 |
+
"loss": 2.6052,
|
| 355 |
"step": 270
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 2.86,
|
| 359 |
+
"learning_rate": 9.943182225078242e-06,
|
| 360 |
+
"loss": 2.6589,
|
| 361 |
"step": 275
|
| 362 |
},
|
| 363 |
{
|
| 364 |
"epoch": 2.92,
|
| 365 |
+
"learning_rate": 9.936145565586871e-06,
|
| 366 |
+
"loss": 2.5745,
|
| 367 |
"step": 280
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 2.97,
|
| 371 |
+
"learning_rate": 9.928701021554545e-06,
|
| 372 |
+
"loss": 2.6676,
|
| 373 |
"step": 285
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"epoch": 3.0,
|
| 377 |
+
"eval_loss": 2.598314046859741,
|
| 378 |
+
"eval_runtime": 173.726,
|
| 379 |
"eval_samples_per_second": 4.409,
|
| 380 |
"eval_steps_per_second": 1.105,
|
| 381 |
"step": 288
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 3.02,
|
| 385 |
+
"learning_rate": 9.920849208140277e-06,
|
| 386 |
+
"loss": 2.5292,
|
| 387 |
"step": 290
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 3.07,
|
| 391 |
+
"learning_rate": 9.912590774156638e-06,
|
| 392 |
+
"loss": 2.6445,
|
| 393 |
"step": 295
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 3.12,
|
| 397 |
+
"learning_rate": 9.903926402016153e-06,
|
| 398 |
+
"loss": 2.6219,
|
| 399 |
"step": 300
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 3.18,
|
| 403 |
+
"learning_rate": 9.894856807674908e-06,
|
| 404 |
+
"loss": 2.4258,
|
| 405 |
"step": 305
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 3.23,
|
| 409 |
+
"learning_rate": 9.885382740573385e-06,
|
| 410 |
+
"loss": 2.6602,
|
| 411 |
"step": 310
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 3.28,
|
| 415 |
+
"learning_rate": 9.875504983574545e-06,
|
| 416 |
+
"loss": 2.539,
|
| 417 |
"step": 315
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 3.33,
|
| 421 |
+
"learning_rate": 9.86522435289912e-06,
|
| 422 |
+
"loss": 2.5752,
|
| 423 |
"step": 320
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 3.39,
|
| 427 |
+
"learning_rate": 9.85454169805819e-06,
|
| 428 |
+
"loss": 2.5685,
|
| 429 |
"step": 325
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 3.44,
|
| 433 |
+
"learning_rate": 9.843457901782967e-06,
|
| 434 |
+
"loss": 2.6553,
|
| 435 |
"step": 330
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 3.49,
|
| 439 |
+
"learning_rate": 9.83197387995186e-06,
|
| 440 |
+
"loss": 2.4846,
|
| 441 |
"step": 335
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 3.54,
|
| 445 |
+
"learning_rate": 9.820090581514799e-06,
|
| 446 |
+
"loss": 2.6538,
|
| 447 |
"step": 340
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 3.59,
|
| 451 |
+
"learning_rate": 9.807808988414811e-06,
|
| 452 |
+
"loss": 2.5469,
|
| 453 |
"step": 345
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 3.65,
|
| 457 |
+
"learning_rate": 9.795130115506887e-06,
|
| 458 |
+
"loss": 2.6193,
|
| 459 |
"step": 350
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 3.7,
|
| 463 |
+
"learning_rate": 9.78205501047412e-06,
|
| 464 |
+
"loss": 2.5287,
|
| 465 |
"step": 355
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 3.75,
|
| 469 |
+
"learning_rate": 9.768584753741134e-06,
|
| 470 |
+
"loss": 2.5179,
|
| 471 |
"step": 360
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 3.8,
|
| 475 |
+
"learning_rate": 9.754720458384808e-06,
|
| 476 |
+
"loss": 2.6582,
|
| 477 |
"step": 365
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 3.85,
|
| 481 |
+
"learning_rate": 9.740463270042289e-06,
|
| 482 |
+
"loss": 2.6538,
|
| 483 |
"step": 370
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 3.91,
|
| 487 |
+
"learning_rate": 9.72581436681634e-06,
|
| 488 |
+
"loss": 2.641,
|
| 489 |
"step": 375
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 3.96,
|
| 493 |
+
"learning_rate": 9.710774959177983e-06,
|
| 494 |
+
"loss": 2.6413,
|
| 495 |
"step": 380
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 4.0,
|
| 499 |
+
"eval_loss": 2.589087724685669,
|
| 500 |
+
"eval_runtime": 173.3132,
|
| 501 |
+
"eval_samples_per_second": 4.42,
|
| 502 |
+
"eval_steps_per_second": 1.108,
|
| 503 |
"step": 384
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 4.01,
|
| 507 |
+
"learning_rate": 9.695346289866478e-06,
|
| 508 |
+
"loss": 2.6235,
|
| 509 |
"step": 385
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 4.06,
|
| 513 |
+
"learning_rate": 9.67952963378663e-06,
|
| 514 |
+
"loss": 2.5417,
|
| 515 |
"step": 390
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 4.11,
|
| 519 |
+
"learning_rate": 9.66332629790344e-06,
|
| 520 |
+
"loss": 2.5655,
|
| 521 |
"step": 395
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 4.17,
|
| 525 |
+
"learning_rate": 9.646737621134112e-06,
|
| 526 |
+
"loss": 2.6339,
|
| 527 |
"step": 400
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 4.22,
|
| 531 |
+
"learning_rate": 9.629764974237416e-06,
|
| 532 |
+
"loss": 2.6498,
|
| 533 |
"step": 405
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 4.27,
|
| 537 |
+
"learning_rate": 9.612409759700412e-06,
|
| 538 |
+
"loss": 2.5508,
|
| 539 |
"step": 410
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 4.32,
|
| 543 |
+
"learning_rate": 9.594673411622563e-06,
|
| 544 |
+
"loss": 2.6466,
|
| 545 |
"step": 415
|
| 546 |
},
|
| 547 |
{
|
| 548 |
"epoch": 4.38,
|
| 549 |
+
"learning_rate": 9.576557395597237e-06,
|
| 550 |
+
"loss": 2.4891,
|
| 551 |
"step": 420
|
| 552 |
},
|
| 553 |
{
|
| 554 |
"epoch": 4.43,
|
| 555 |
+
"learning_rate": 9.558063208590594e-06,
|
| 556 |
+
"loss": 2.5521,
|
| 557 |
"step": 425
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 4.48,
|
| 561 |
+
"learning_rate": 9.539192378817894e-06,
|
| 562 |
+
"loss": 2.517,
|
| 563 |
"step": 430
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 4.53,
|
| 567 |
+
"learning_rate": 9.519946465617217e-06,
|
| 568 |
+
"loss": 2.562,
|
| 569 |
"step": 435
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 4.58,
|
| 573 |
+
"learning_rate": 9.500327059320606e-06,
|
| 574 |
+
"loss": 2.7011,
|
| 575 |
"step": 440
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 4.64,
|
| 579 |
+
"learning_rate": 9.480335781122661e-06,
|
| 580 |
+
"loss": 2.4814,
|
| 581 |
"step": 445
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 4.69,
|
| 585 |
+
"learning_rate": 9.459974282946572e-06,
|
| 586 |
+
"loss": 2.6825,
|
| 587 |
"step": 450
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 4.74,
|
| 591 |
+
"learning_rate": 9.439244247307618e-06,
|
| 592 |
+
"loss": 2.5627,
|
| 593 |
"step": 455
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 4.79,
|
| 597 |
+
"learning_rate": 9.41814738717414e-06,
|
| 598 |
+
"loss": 2.5377,
|
| 599 |
"step": 460
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 4.84,
|
| 603 |
+
"learning_rate": 9.396685445825987e-06,
|
| 604 |
+
"loss": 2.6597,
|
| 605 |
"step": 465
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 4.9,
|
| 609 |
+
"learning_rate": 9.374860196710474e-06,
|
| 610 |
+
"loss": 2.6323,
|
| 611 |
"step": 470
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 4.95,
|
| 615 |
+
"learning_rate": 9.352673443295834e-06,
|
| 616 |
+
"loss": 2.609,
|
| 617 |
"step": 475
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 5.0,
|
| 621 |
+
"learning_rate": 9.330127018922195e-06,
|
| 622 |
+
"loss": 2.581,
|
| 623 |
"step": 480
|
| 624 |
},
|
| 625 |
{
|
| 626 |
"epoch": 5.0,
|
| 627 |
+
"eval_loss": 2.5825417041778564,
|
| 628 |
+
"eval_runtime": 173.2578,
|
| 629 |
+
"eval_samples_per_second": 4.421,
|
| 630 |
+
"eval_steps_per_second": 1.108,
|
| 631 |
"step": 480
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 5.05,
|
| 635 |
+
"learning_rate": 9.307222786650079e-06,
|
| 636 |
+
"loss": 2.6336,
|
| 637 |
"step": 485
|
| 638 |
},
|
| 639 |
{
|
| 640 |
"epoch": 5.1,
|
| 641 |
+
"learning_rate": 9.283962639106464e-06,
|
| 642 |
+
"loss": 2.6305,
|
| 643 |
"step": 490
|
| 644 |
},
|
| 645 |
{
|
| 646 |
"epoch": 5.16,
|
| 647 |
+
"learning_rate": 9.260348498328393e-06,
|
| 648 |
+
"loss": 2.5438,
|
| 649 |
"step": 495
|
| 650 |
},
|
| 651 |
{
|
| 652 |
"epoch": 5.21,
|
| 653 |
+
"learning_rate": 9.23638231560414e-06,
|
| 654 |
+
"loss": 2.5235,
|
| 655 |
"step": 500
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 5.26,
|
| 659 |
+
"learning_rate": 9.212066071311978e-06,
|
| 660 |
+
"loss": 2.5714,
|
| 661 |
"step": 505
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 5.31,
|
| 665 |
+
"learning_rate": 9.18740177475654e-06,
|
| 666 |
+
"loss": 2.6968,
|
| 667 |
"step": 510
|
| 668 |
},
|
| 669 |
{
|
| 670 |
"epoch": 5.36,
|
| 671 |
+
"learning_rate": 9.162391464002776e-06,
|
| 672 |
+
"loss": 2.5705,
|
| 673 |
"step": 515
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 5.42,
|
| 677 |
+
"learning_rate": 9.137037205707552e-06,
|
| 678 |
+
"loss": 2.5459,
|
| 679 |
"step": 520
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 5.47,
|
| 683 |
+
"learning_rate": 9.111341094948876e-06,
|
| 684 |
+
"loss": 2.5294,
|
| 685 |
"step": 525
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 5.52,
|
| 689 |
+
"learning_rate": 9.08530525505277e-06,
|
| 690 |
+
"loss": 2.5656,
|
| 691 |
"step": 530
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 5.57,
|
| 695 |
+
"learning_rate": 9.058931837417823e-06,
|
| 696 |
+
"loss": 2.6372,
|
| 697 |
"step": 535
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 5.62,
|
| 701 |
+
"learning_rate": 9.032223021337415e-06,
|
| 702 |
+
"loss": 2.539,
|
| 703 |
"step": 540
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 5.68,
|
| 707 |
+
"learning_rate": 9.00518101381963e-06,
|
| 708 |
+
"loss": 2.6005,
|
| 709 |
"step": 545
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 5.73,
|
| 713 |
+
"learning_rate": 8.9778080494049e-06,
|
| 714 |
+
"loss": 2.5895,
|
| 715 |
"step": 550
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 5.78,
|
| 719 |
+
"learning_rate": 8.950106389981346e-06,
|
| 720 |
+
"loss": 2.5937,
|
| 721 |
"step": 555
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 5.83,
|
| 725 |
+
"learning_rate": 8.92207832459788e-06,
|
| 726 |
+
"loss": 2.5635,
|
| 727 |
"step": 560
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 5.89,
|
| 731 |
+
"learning_rate": 8.893726169275054e-06,
|
| 732 |
+
"loss": 2.5176,
|
| 733 |
"step": 565
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 5.94,
|
| 737 |
+
"learning_rate": 8.865052266813686e-06,
|
| 738 |
+
"loss": 2.6101,
|
| 739 |
"step": 570
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 5.99,
|
| 743 |
+
"learning_rate": 8.836058986601263e-06,
|
| 744 |
+
"loss": 2.5884,
|
| 745 |
"step": 575
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 6.0,
|
| 749 |
+
"eval_loss": 2.577636957168579,
|
| 750 |
+
"eval_runtime": 173.3959,
|
| 751 |
+
"eval_samples_per_second": 4.418,
|
| 752 |
+
"eval_steps_per_second": 1.107,
|
| 753 |
"step": 576
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 6.04,
|
| 757 |
+
"learning_rate": 8.806748724416156e-06,
|
| 758 |
+
"loss": 2.5728,
|
| 759 |
"step": 580
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 6.09,
|
| 763 |
+
"learning_rate": 8.777123902229658e-06,
|
| 764 |
+
"loss": 2.652,
|
| 765 |
"step": 585
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 6.15,
|
| 769 |
+
"learning_rate": 8.747186968005837e-06,
|
| 770 |
+
"loss": 2.5489,
|
| 771 |
"step": 590
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 6.2,
|
| 775 |
+
"learning_rate": 8.71694039549927e-06,
|
| 776 |
+
"loss": 2.6273,
|
| 777 |
"step": 595
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 6.25,
|
| 781 |
+
"learning_rate": 8.68638668405062e-06,
|
| 782 |
+
"loss": 2.4337,
|
| 783 |
"step": 600
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 6.3,
|
| 787 |
+
"learning_rate": 8.655528358380121e-06,
|
| 788 |
+
"loss": 2.5657,
|
| 789 |
"step": 605
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 6.35,
|
| 793 |
+
"learning_rate": 8.624367968378941e-06,
|
| 794 |
+
"loss": 2.6715,
|
| 795 |
"step": 610
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 6.41,
|
| 799 |
+
"learning_rate": 8.59290808889849e-06,
|
| 800 |
+
"loss": 2.5736,
|
| 801 |
"step": 615
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 6.46,
|
| 805 |
+
"learning_rate": 8.561151319537656e-06,
|
| 806 |
+
"loss": 2.5889,
|
| 807 |
"step": 620
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 6.51,
|
| 811 |
+
"learning_rate": 8.52910028442798e-06,
|
| 812 |
+
"loss": 2.5689,
|
| 813 |
"step": 625
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 6.56,
|
| 817 |
+
"learning_rate": 8.496757632016836e-06,
|
| 818 |
+
"loss": 2.6729,
|
| 819 |
"step": 630
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 6.61,
|
| 823 |
+
"learning_rate": 8.46412603484857e-06,
|
| 824 |
+
"loss": 2.4771,
|
| 825 |
"step": 635
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 6.67,
|
| 829 |
+
"learning_rate": 8.43120818934367e-06,
|
| 830 |
+
"loss": 2.5163,
|
| 831 |
"step": 640
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 6.72,
|
| 835 |
+
"learning_rate": 8.398006815575949e-06,
|
| 836 |
+
"loss": 2.5749,
|
| 837 |
"step": 645
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 6.77,
|
| 841 |
+
"learning_rate": 8.364524657047789e-06,
|
| 842 |
+
"loss": 2.5716,
|
| 843 |
"step": 650
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 6.82,
|
| 847 |
+
"learning_rate": 8.330764480463427e-06,
|
| 848 |
+
"loss": 2.5333,
|
| 849 |
"step": 655
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 6.88,
|
| 853 |
+
"learning_rate": 8.296729075500345e-06,
|
| 854 |
+
"loss": 2.5299,
|
| 855 |
"step": 660
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 6.93,
|
| 859 |
+
"learning_rate": 8.262421254578749e-06,
|
| 860 |
+
"loss": 2.5526,
|
| 861 |
"step": 665
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 6.98,
|
| 865 |
+
"learning_rate": 8.227843852629174e-06,
|
| 866 |
+
"loss": 2.704,
|
| 867 |
"step": 670
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 7.0,
|
| 871 |
+
"eval_loss": 2.57405686378479,
|
| 872 |
+
"eval_runtime": 173.1315,
|
| 873 |
+
"eval_samples_per_second": 4.424,
|
| 874 |
+
"eval_steps_per_second": 1.109,
|
| 875 |
"step": 672
|
| 876 |
},
|
| 877 |
{
|
| 878 |
"epoch": 7.03,
|
| 879 |
+
"learning_rate": 8.192999726858227e-06,
|
| 880 |
+
"loss": 2.5605,
|
| 881 |
"step": 675
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 7.08,
|
| 885 |
+
"learning_rate": 8.157891756512488e-06,
|
| 886 |
+
"loss": 2.6373,
|
| 887 |
"step": 680
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 7.14,
|
| 891 |
+
"learning_rate": 8.122522842640596e-06,
|
| 892 |
+
"loss": 2.6236,
|
| 893 |
"step": 685
|
| 894 |
},
|
| 895 |
{
|
| 896 |
"epoch": 7.19,
|
| 897 |
+
"learning_rate": 8.086895907853526e-06,
|
| 898 |
+
"loss": 2.5717,
|
| 899 |
"step": 690
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 7.24,
|
| 903 |
+
"learning_rate": 8.051013896083084e-06,
|
| 904 |
+
"loss": 2.5228,
|
| 905 |
"step": 695
|
| 906 |
},
|
| 907 |
{
|
| 908 |
"epoch": 7.29,
|
| 909 |
+
"learning_rate": 8.014879772338649e-06,
|
| 910 |
+
"loss": 2.5166,
|
| 911 |
"step": 700
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 7.34,
|
| 915 |
+
"learning_rate": 7.978496522462167e-06,
|
| 916 |
+
"loss": 2.5228,
|
| 917 |
"step": 705
|
| 918 |
},
|
| 919 |
{
|
| 920 |
"epoch": 7.4,
|
| 921 |
+
"learning_rate": 7.941867152881423e-06,
|
| 922 |
+
"loss": 2.7549,
|
| 923 |
"step": 710
|
| 924 |
},
|
| 925 |
{
|
| 926 |
"epoch": 7.45,
|
| 927 |
+
"learning_rate": 7.904994690361612e-06,
|
| 928 |
+
"loss": 2.5288,
|
| 929 |
"step": 715
|
| 930 |
},
|
| 931 |
{
|
| 932 |
"epoch": 7.5,
|
| 933 |
+
"learning_rate": 7.86788218175523e-06,
|
| 934 |
+
"loss": 2.582,
|
| 935 |
"step": 720
|
| 936 |
},
|
| 937 |
{
|
| 938 |
"epoch": 7.55,
|
| 939 |
+
"learning_rate": 7.830532693750314e-06,
|
| 940 |
+
"loss": 2.5402,
|
| 941 |
"step": 725
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 7.6,
|
| 945 |
+
"learning_rate": 7.792949312617023e-06,
|
| 946 |
+
"loss": 2.5406,
|
| 947 |
"step": 730
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 7.66,
|
| 951 |
+
"learning_rate": 7.755135143952621e-06,
|
| 952 |
+
"loss": 2.4985,
|
| 953 |
"step": 735
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 7.71,
|
| 957 |
+
"learning_rate": 7.71709331242485e-06,
|
| 958 |
+
"loss": 2.6041,
|
| 959 |
"step": 740
|
| 960 |
},
|
| 961 |
{
|
| 962 |
"epoch": 7.76,
|
| 963 |
+
"learning_rate": 7.678826961513739e-06,
|
| 964 |
+
"loss": 2.544,
|
| 965 |
"step": 745
|
| 966 |
},
|
| 967 |
{
|
| 968 |
"epoch": 7.81,
|
| 969 |
+
"learning_rate": 7.64033925325184e-06,
|
| 970 |
+
"loss": 2.5934,
|
| 971 |
"step": 750
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 7.86,
|
| 975 |
+
"learning_rate": 7.601633367962955e-06,
|
| 976 |
+
"loss": 2.5599,
|
| 977 |
"step": 755
|
| 978 |
},
|
| 979 |
{
|
| 980 |
"epoch": 7.92,
|
| 981 |
+
"learning_rate": 7.562712503999327e-06,
|
| 982 |
+
"loss": 2.6012,
|
| 983 |
"step": 760
|
| 984 |
},
|
| 985 |
{
|
| 986 |
"epoch": 7.97,
|
| 987 |
+
"learning_rate": 7.523579877477361e-06,
|
| 988 |
+
"loss": 2.608,
|
| 989 |
"step": 765
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 8.0,
|
| 993 |
+
"eval_loss": 2.571471691131592,
|
| 994 |
+
"eval_runtime": 173.1738,
|
| 995 |
+
"eval_samples_per_second": 4.423,
|
| 996 |
+
"eval_steps_per_second": 1.109,
|
| 997 |
"step": 768
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
"epoch": 8.02,
|
| 1001 |
+
"learning_rate": 7.484238722011869e-06,
|
| 1002 |
+
"loss": 2.6066,
|
| 1003 |
"step": 770
|
| 1004 |
},
|
| 1005 |
{
|
| 1006 |
"epoch": 8.07,
|
| 1007 |
+
"learning_rate": 7.444692288448864e-06,
|
| 1008 |
+
"loss": 2.5357,
|
| 1009 |
"step": 775
|
| 1010 |
},
|
| 1011 |
{
|
| 1012 |
"epoch": 8.12,
|
| 1013 |
+
"learning_rate": 7.404943844596939e-06,
|
| 1014 |
+
"loss": 2.487,
|
| 1015 |
"step": 780
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
"epoch": 8.18,
|
| 1019 |
+
"learning_rate": 7.364996674957243e-06,
|
| 1020 |
+
"loss": 2.5873,
|
| 1021 |
"step": 785
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 8.23,
|
| 1025 |
+
"learning_rate": 7.324854080452071e-06,
|
| 1026 |
+
"loss": 2.6906,
|
| 1027 |
"step": 790
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 8.28,
|
| 1031 |
+
"learning_rate": 7.284519378152104e-06,
|
| 1032 |
+
"loss": 2.575,
|
| 1033 |
"step": 795
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 8.33,
|
| 1037 |
+
"learning_rate": 7.243995901002312e-06,
|
| 1038 |
+
"loss": 2.5426,
|
| 1039 |
"step": 800
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
"epoch": 8.39,
|
| 1043 |
+
"learning_rate": 7.203286997546543e-06,
|
| 1044 |
+
"loss": 2.5829,
|
| 1045 |
"step": 805
|
| 1046 |
},
|
| 1047 |
{
|
| 1048 |
"epoch": 8.44,
|
| 1049 |
+
"learning_rate": 7.162396031650831e-06,
|
| 1050 |
+
"loss": 2.5422,
|
| 1051 |
"step": 810
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
"epoch": 8.49,
|
| 1055 |
+
"learning_rate": 7.121326382225429e-06,
|
| 1056 |
+
"loss": 2.5977,
|
| 1057 |
"step": 815
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 8.54,
|
| 1061 |
+
"learning_rate": 7.080081442945597e-06,
|
| 1062 |
+
"loss": 2.5636,
|
| 1063 |
"step": 820
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 8.59,
|
| 1067 |
+
"learning_rate": 7.038664621971184e-06,
|
| 1068 |
+
"loss": 2.6223,
|
| 1069 |
"step": 825
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
"epoch": 8.65,
|
| 1073 |
+
"learning_rate": 6.997079341665003e-06,
|
| 1074 |
+
"loss": 2.5567,
|
| 1075 |
"step": 830
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
"epoch": 8.7,
|
| 1079 |
+
"learning_rate": 6.955329038310028e-06,
|
| 1080 |
+
"loss": 2.5051,
|
| 1081 |
"step": 835
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
"epoch": 8.75,
|
| 1085 |
+
"learning_rate": 6.913417161825449e-06,
|
| 1086 |
+
"loss": 2.5383,
|
| 1087 |
"step": 840
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
"epoch": 8.8,
|
| 1091 |
+
"learning_rate": 6.871347175481602e-06,
|
| 1092 |
+
"loss": 2.5363,
|
| 1093 |
"step": 845
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 8.85,
|
| 1097 |
+
"learning_rate": 6.829122555613786e-06,
|
| 1098 |
+
"loss": 2.6013,
|
| 1099 |
"step": 850
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 8.91,
|
| 1103 |
+
"learning_rate": 6.786746791335001e-06,
|
| 1104 |
+
"loss": 2.6019,
|
| 1105 |
"step": 855
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
"epoch": 8.96,
|
| 1109 |
+
"learning_rate": 6.7442233842476545e-06,
|
| 1110 |
+
"loss": 2.5454,
|
| 1111 |
"step": 860
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
"epoch": 9.0,
|
| 1115 |
+
"eval_loss": 2.5697662830352783,
|
| 1116 |
+
"eval_runtime": 173.2483,
|
| 1117 |
+
"eval_samples_per_second": 4.421,
|
| 1118 |
+
"eval_steps_per_second": 1.108,
|
| 1119 |
"step": 864
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 9.01,
|
| 1123 |
+
"learning_rate": 6.701555848154193e-06,
|
| 1124 |
+
"loss": 2.6289,
|
| 1125 |
"step": 865
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 9.06,
|
| 1129 |
+
"learning_rate": 6.6587477087667615e-06,
|
| 1130 |
+
"loss": 2.6078,
|
| 1131 |
"step": 870
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 9.11,
|
| 1135 |
+
"learning_rate": 6.615802503415865e-06,
|
| 1136 |
+
"loss": 2.5328,
|
| 1137 |
"step": 875
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 9.17,
|
| 1141 |
+
"learning_rate": 6.572723780758069e-06,
|
| 1142 |
+
"loss": 2.537,
|
| 1143 |
"step": 880
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 9.22,
|
| 1147 |
+
"learning_rate": 6.529515100482768e-06,
|
| 1148 |
+
"loss": 2.5444,
|
| 1149 |
"step": 885
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 9.27,
|
| 1153 |
+
"learning_rate": 6.486180033018039e-06,
|
| 1154 |
+
"loss": 2.4951,
|
| 1155 |
"step": 890
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 9.32,
|
| 1159 |
+
"learning_rate": 6.442722159235608e-06,
|
| 1160 |
+
"loss": 2.5551,
|
| 1161 |
"step": 895
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 9.38,
|
| 1165 |
+
"learning_rate": 6.399145070154962e-06,
|
| 1166 |
+
"loss": 2.6229,
|
| 1167 |
"step": 900
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 9.43,
|
| 1171 |
+
"learning_rate": 6.355452366646602e-06,
|
| 1172 |
+
"loss": 2.4483,
|
| 1173 |
"step": 905
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 9.48,
|
| 1177 |
+
"learning_rate": 6.311647659134509e-06,
|
| 1178 |
+
"loss": 2.659,
|
| 1179 |
"step": 910
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 9.53,
|
| 1183 |
+
"learning_rate": 6.267734567297799e-06,
|
| 1184 |
+
"loss": 2.565,
|
| 1185 |
"step": 915
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 9.58,
|
| 1189 |
+
"learning_rate": 6.2237167197716195e-06,
|
| 1190 |
+
"loss": 2.5539,
|
| 1191 |
"step": 920
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 9.64,
|
| 1195 |
+
"learning_rate": 6.179597753847317e-06,
|
| 1196 |
+
"loss": 2.5881,
|
| 1197 |
"step": 925
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 9.69,
|
| 1201 |
+
"learning_rate": 6.135381315171867e-06,
|
| 1202 |
+
"loss": 2.5665,
|
| 1203 |
"step": 930
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 9.74,
|
| 1207 |
+
"learning_rate": 6.091071057446635e-06,
|
| 1208 |
+
"loss": 2.5365,
|
| 1209 |
"step": 935
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 9.79,
|
| 1213 |
+
"learning_rate": 6.046670642125461e-06,
|
| 1214 |
+
"loss": 2.6475,
|
| 1215 |
"step": 940
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 9.84,
|
| 1219 |
+
"learning_rate": 6.002183738112103e-06,
|
| 1220 |
+
"loss": 2.6788,
|
| 1221 |
"step": 945
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"epoch": 9.9,
|
| 1225 |
+
"learning_rate": 5.957614021457072e-06,
|
| 1226 |
+
"loss": 2.5368,
|
| 1227 |
"step": 950
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 9.95,
|
| 1231 |
+
"learning_rate": 5.912965175053867e-06,
|
| 1232 |
+
"loss": 2.547,
|
| 1233 |
"step": 955
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 10.0,
|
| 1237 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 1238 |
+
"loss": 2.5938,
|
| 1239 |
"step": 960
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 10.0,
|
| 1243 |
+
"eval_loss": 2.5687718391418457,
|
| 1244 |
+
"eval_runtime": 173.1474,
|
| 1245 |
+
"eval_samples_per_second": 4.424,
|
| 1246 |
+
"eval_steps_per_second": 1.109,
|
| 1247 |
"step": 960
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
"epoch": 10.05,
|
| 1251 |
+
"learning_rate": 5.823444856965393e-06,
|
| 1252 |
+
"loss": 2.6,
|
| 1253 |
"step": 965
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 10.1,
|
| 1257 |
+
"learning_rate": 5.77858078254047e-06,
|
| 1258 |
+
"loss": 2.6841,
|
| 1259 |
"step": 970
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 10.16,
|
| 1263 |
+
"learning_rate": 5.733652372276809e-06,
|
| 1264 |
+
"loss": 2.6076,
|
| 1265 |
"step": 975
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
"epoch": 10.21,
|
| 1269 |
+
"learning_rate": 5.688663338707554e-06,
|
| 1270 |
+
"loss": 2.6151,
|
| 1271 |
"step": 980
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 10.26,
|
| 1275 |
+
"learning_rate": 5.643617399375281e-06,
|
| 1276 |
+
"loss": 2.5886,
|
| 1277 |
"step": 985
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 10.31,
|
| 1281 |
+
"learning_rate": 5.598518276524813e-06,
|
| 1282 |
+
"loss": 2.6533,
|
| 1283 |
"step": 990
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
"epoch": 10.36,
|
| 1287 |
+
"learning_rate": 5.553369696795647e-06,
|
| 1288 |
+
"loss": 2.3891,
|
| 1289 |
"step": 995
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 10.42,
|
| 1293 |
+
"learning_rate": 5.50817539091401e-06,
|
| 1294 |
+
"loss": 2.697,
|
| 1295 |
"step": 1000
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 10.47,
|
| 1299 |
+
"learning_rate": 5.462939093384579e-06,
|
| 1300 |
+
"loss": 2.5268,
|
| 1301 |
"step": 1005
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
"epoch": 10.52,
|
| 1305 |
+
"learning_rate": 5.417664542181894e-06,
|
| 1306 |
+
"loss": 2.5242,
|
| 1307 |
"step": 1010
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
"epoch": 10.57,
|
| 1311 |
+
"learning_rate": 5.372355478441483e-06,
|
| 1312 |
+
"loss": 2.5093,
|
| 1313 |
"step": 1015
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 10.62,
|
| 1317 |
+
"learning_rate": 5.327015646150716e-06,
|
| 1318 |
+
"loss": 2.5013,
|
| 1319 |
"step": 1020
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
"epoch": 10.68,
|
| 1323 |
+
"learning_rate": 5.2816487918394385e-06,
|
| 1324 |
+
"loss": 2.4911,
|
| 1325 |
"step": 1025
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 10.73,
|
| 1329 |
+
"learning_rate": 5.236258664270385e-06,
|
| 1330 |
+
"loss": 2.6194,
|
| 1331 |
"step": 1030
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
"epoch": 10.78,
|
| 1335 |
+
"learning_rate": 5.1908490141294085e-06,
|
| 1336 |
+
"loss": 2.4813,
|
| 1337 |
"step": 1035
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
"epoch": 10.83,
|
| 1341 |
+
"learning_rate": 5.145423593715558e-06,
|
| 1342 |
+
"loss": 2.5679,
|
| 1343 |
"step": 1040
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
"epoch": 10.89,
|
| 1347 |
+
"learning_rate": 5.09998615663101e-06,
|
| 1348 |
+
"loss": 2.5244,
|
| 1349 |
"step": 1045
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 10.94,
|
| 1353 |
+
"learning_rate": 5.054540457470912e-06,
|
| 1354 |
+
"loss": 2.6256,
|
| 1355 |
"step": 1050
|
| 1356 |
},
|
| 1357 |
{
|
| 1358 |
"epoch": 10.99,
|
| 1359 |
+
"learning_rate": 5.009090251513119e-06,
|
| 1360 |
+
"loss": 2.6129,
|
| 1361 |
"step": 1055
|
| 1362 |
},
|
| 1363 |
{
|
| 1364 |
"epoch": 11.0,
|
| 1365 |
+
"eval_loss": 2.568225145339966,
|
| 1366 |
+
"eval_runtime": 173.1937,
|
| 1367 |
"eval_samples_per_second": 4.423,
|
| 1368 |
"eval_steps_per_second": 1.109,
|
| 1369 |
"step": 1056
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
"epoch": 11.04,
|
| 1373 |
+
"learning_rate": 4.963639294407893e-06,
|
| 1374 |
+
"loss": 2.4814,
|
| 1375 |
"step": 1060
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
"epoch": 11.09,
|
| 1379 |
+
"learning_rate": 4.918191341867566e-06,
|
| 1380 |
+
"loss": 2.6482,
|
| 1381 |
"step": 1065
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
"epoch": 11.15,
|
| 1385 |
+
"learning_rate": 4.8727501493562e-06,
|
| 1386 |
+
"loss": 2.6263,
|
| 1387 |
"step": 1070
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 11.2,
|
| 1391 |
+
"learning_rate": 4.827319471779255e-06,
|
| 1392 |
+
"loss": 2.6835,
|
| 1393 |
"step": 1075
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
"epoch": 11.25,
|
| 1397 |
+
"learning_rate": 4.781903063173321e-06,
|
| 1398 |
+
"loss": 2.4925,
|
| 1399 |
"step": 1080
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 11.3,
|
| 1403 |
+
"learning_rate": 4.736504676395912e-06,
|
| 1404 |
+
"loss": 2.51,
|
| 1405 |
"step": 1085
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 11.35,
|
| 1409 |
+
"learning_rate": 4.691128062815361e-06,
|
| 1410 |
+
"loss": 2.5933,
|
| 1411 |
"step": 1090
|
| 1412 |
},
|
| 1413 |
{
|
| 1414 |
"epoch": 11.41,
|
| 1415 |
+
"learning_rate": 4.64577697200083e-06,
|
| 1416 |
+
"loss": 2.6073,
|
| 1417 |
"step": 1095
|
| 1418 |
},
|
| 1419 |
{
|
| 1420 |
"epoch": 11.46,
|
| 1421 |
+
"learning_rate": 4.600455151412482e-06,
|
| 1422 |
+
"loss": 2.6271,
|
| 1423 |
"step": 1100
|
| 1424 |
},
|
| 1425 |
{
|
| 1426 |
"epoch": 11.51,
|
| 1427 |
+
"learning_rate": 4.555166346091811e-06,
|
| 1428 |
+
"loss": 2.5913,
|
| 1429 |
"step": 1105
|
| 1430 |
},
|
| 1431 |
{
|
| 1432 |
"epoch": 11.56,
|
| 1433 |
+
"learning_rate": 4.509914298352197e-06,
|
| 1434 |
+
"loss": 2.4734,
|
| 1435 |
"step": 1110
|
| 1436 |
},
|
| 1437 |
{
|
| 1438 |
"epoch": 11.61,
|
| 1439 |
+
"learning_rate": 4.464702747469654e-06,
|
| 1440 |
+
"loss": 2.4006,
|
| 1441 |
"step": 1115
|
| 1442 |
},
|
| 1443 |
{
|
| 1444 |
"epoch": 11.67,
|
| 1445 |
+
"learning_rate": 4.4195354293738484e-06,
|
| 1446 |
+
"loss": 2.5788,
|
| 1447 |
"step": 1120
|
| 1448 |
},
|
| 1449 |
{
|
| 1450 |
"epoch": 11.72,
|
| 1451 |
+
"learning_rate": 4.374416076339405e-06,
|
| 1452 |
+
"loss": 2.6018,
|
| 1453 |
"step": 1125
|
| 1454 |
},
|
| 1455 |
{
|
| 1456 |
"epoch": 11.77,
|
| 1457 |
+
"learning_rate": 4.3293484166774795e-06,
|
| 1458 |
+
"loss": 2.3919,
|
| 1459 |
"step": 1130
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
"epoch": 11.82,
|
| 1463 |
+
"learning_rate": 4.2843361744276965e-06,
|
| 1464 |
+
"loss": 2.5624,
|
| 1465 |
"step": 1135
|
| 1466 |
},
|
| 1467 |
{
|
| 1468 |
"epoch": 11.88,
|
| 1469 |
+
"learning_rate": 4.239383069050417e-06,
|
| 1470 |
+
"loss": 2.6089,
|
| 1471 |
"step": 1140
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 11.93,
|
| 1475 |
+
"learning_rate": 4.194492815119393e-06,
|
| 1476 |
+
"loss": 2.6184,
|
| 1477 |
"step": 1145
|
| 1478 |
},
|
| 1479 |
{
|
| 1480 |
"epoch": 11.98,
|
| 1481 |
+
"learning_rate": 4.149669122014823e-06,
|
| 1482 |
+
"loss": 2.6334,
|
| 1483 |
"step": 1150
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 12.0,
|
| 1487 |
+
"eval_loss": 2.5679450035095215,
|
| 1488 |
+
"eval_runtime": 173.1818,
|
| 1489 |
+
"eval_samples_per_second": 4.423,
|
| 1490 |
+
"eval_steps_per_second": 1.109,
|
| 1491 |
"step": 1152
|
| 1492 |
},
|
| 1493 |
{
|
| 1494 |
"epoch": 12.03,
|
| 1495 |
+
"learning_rate": 4.104915693616838e-06,
|
| 1496 |
+
"loss": 2.6666,
|
| 1497 |
"step": 1155
|
| 1498 |
},
|
| 1499 |
{
|
| 1500 |
"epoch": 12.08,
|
| 1501 |
+
"learning_rate": 4.060236227999441e-06,
|
| 1502 |
+
"loss": 2.5513,
|
| 1503 |
"step": 1160
|
| 1504 |
},
|
| 1505 |
{
|
| 1506 |
"epoch": 12.14,
|
| 1507 |
+
"learning_rate": 4.015634417124932e-06,
|
| 1508 |
+
"loss": 2.4863,
|
| 1509 |
"step": 1165
|
| 1510 |
},
|
| 1511 |
{
|
| 1512 |
"epoch": 12.19,
|
| 1513 |
+
"learning_rate": 3.971113946538826e-06,
|
| 1514 |
+
"loss": 2.5857,
|
| 1515 |
"step": 1170
|
| 1516 |
},
|
| 1517 |
{
|
| 1518 |
"epoch": 12.24,
|
| 1519 |
+
"learning_rate": 3.926678495065313e-06,
|
| 1520 |
+
"loss": 2.6008,
|
| 1521 |
"step": 1175
|
| 1522 |
},
|
| 1523 |
{
|
| 1524 |
"epoch": 12.29,
|
| 1525 |
+
"learning_rate": 3.882331734503263e-06,
|
| 1526 |
+
"loss": 2.5744,
|
| 1527 |
"step": 1180
|
| 1528 |
},
|
| 1529 |
{
|
| 1530 |
"epoch": 12.34,
|
| 1531 |
+
"learning_rate": 3.838077329322828e-06,
|
| 1532 |
+
"loss": 2.6885,
|
| 1533 |
"step": 1185
|
| 1534 |
},
|
| 1535 |
{
|
| 1536 |
"epoch": 12.4,
|
| 1537 |
+
"learning_rate": 3.7939189363626282e-06,
|
| 1538 |
+
"loss": 2.6531,
|
| 1539 |
"step": 1190
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
"epoch": 12.45,
|
| 1543 |
+
"learning_rate": 3.7498602045275846e-06,
|
| 1544 |
+
"loss": 2.6082,
|
| 1545 |
"step": 1195
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 12.5,
|
| 1549 |
+
"learning_rate": 3.705904774487396e-06,
|
| 1550 |
+
"loss": 2.5587,
|
| 1551 |
"step": 1200
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 12.55,
|
| 1555 |
+
"learning_rate": 3.6620562783757163e-06,
|
| 1556 |
+
"loss": 2.4835,
|
| 1557 |
"step": 1205
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
"epoch": 12.6,
|
| 1561 |
+
"learning_rate": 3.618318339490009e-06,
|
| 1562 |
+
"loss": 2.5595,
|
| 1563 |
"step": 1210
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 12.66,
|
| 1567 |
+
"learning_rate": 3.5746945719921476e-06,
|
| 1568 |
+
"loss": 2.5684,
|
| 1569 |
"step": 1215
|
| 1570 |
},
|
| 1571 |
{
|
| 1572 |
"epoch": 12.71,
|
| 1573 |
+
"learning_rate": 3.531188580609778e-06,
|
| 1574 |
+
"loss": 2.4877,
|
| 1575 |
"step": 1220
|
| 1576 |
},
|
| 1577 |
{
|
| 1578 |
"epoch": 12.76,
|
| 1579 |
+
"learning_rate": 3.4878039603384505e-06,
|
| 1580 |
+
"loss": 2.7007,
|
| 1581 |
"step": 1225
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 12.81,
|
| 1585 |
+
"learning_rate": 3.444544296144546e-06,
|
| 1586 |
+
"loss": 2.5391,
|
| 1587 |
"step": 1230
|
| 1588 |
},
|
| 1589 |
{
|
| 1590 |
"epoch": 12.86,
|
| 1591 |
+
"learning_rate": 3.401413162669057e-06,
|
| 1592 |
+
"loss": 2.5575,
|
| 1593 |
"step": 1235
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 12.92,
|
| 1597 |
+
"learning_rate": 3.3584141239321953e-06,
|
| 1598 |
+
"loss": 2.5095,
|
| 1599 |
"step": 1240
|
| 1600 |
},
|
| 1601 |
{
|
| 1602 |
"epoch": 12.97,
|
| 1603 |
+
"learning_rate": 3.3155507330389004e-06,
|
| 1604 |
+
"loss": 2.5013,
|
| 1605 |
"step": 1245
|
| 1606 |
},
|
| 1607 |
{
|
| 1608 |
"epoch": 13.0,
|
| 1609 |
+
"eval_loss": 2.567814350128174,
|
| 1610 |
+
"eval_runtime": 173.1218,
|
| 1611 |
+
"eval_samples_per_second": 4.425,
|
| 1612 |
+
"eval_steps_per_second": 1.109,
|
| 1613 |
"step": 1248
|
| 1614 |
},
|
| 1615 |
{
|
| 1616 |
"epoch": 13.02,
|
| 1617 |
+
"learning_rate": 3.272826531885229e-06,
|
| 1618 |
+
"loss": 2.4931,
|
| 1619 |
"step": 1250
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 13.07,
|
| 1623 |
+
"learning_rate": 3.2302450508656835e-06,
|
| 1624 |
+
"loss": 2.6623,
|
| 1625 |
"step": 1255
|
| 1626 |
},
|
| 1627 |
{
|
| 1628 |
"epoch": 13.12,
|
| 1629 |
+
"learning_rate": 3.1878098085814926e-06,
|
| 1630 |
+
"loss": 2.6147,
|
| 1631 |
"step": 1260
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
"epoch": 13.18,
|
| 1635 |
+
"learning_rate": 3.1455243115498523e-06,
|
| 1636 |
+
"loss": 2.4961,
|
| 1637 |
"step": 1265
|
| 1638 |
},
|
| 1639 |
{
|
| 1640 |
"epoch": 13.23,
|
| 1641 |
+
"learning_rate": 3.1033920539141837e-06,
|
| 1642 |
+
"loss": 2.5426,
|
| 1643 |
"step": 1270
|
| 1644 |
},
|
| 1645 |
{
|
| 1646 |
"epoch": 13.28,
|
| 1647 |
+
"learning_rate": 3.061416517155397e-06,
|
| 1648 |
+
"loss": 2.6229,
|
| 1649 |
"step": 1275
|
| 1650 |
},
|
| 1651 |
{
|
| 1652 |
"epoch": 13.33,
|
| 1653 |
+
"learning_rate": 3.019601169804216e-06,
|
| 1654 |
+
"loss": 2.5512,
|
| 1655 |
"step": 1280
|
| 1656 |
},
|
| 1657 |
{
|
| 1658 |
"epoch": 13.39,
|
| 1659 |
+
"learning_rate": 2.97794946715456e-06,
|
| 1660 |
+
"loss": 2.5486,
|
| 1661 |
"step": 1285
|
| 1662 |
},
|
| 1663 |
{
|
| 1664 |
"epoch": 13.44,
|
| 1665 |
+
"learning_rate": 2.936464850978027e-06,
|
| 1666 |
+
"loss": 2.5661,
|
| 1667 |
"step": 1290
|
| 1668 |
},
|
| 1669 |
{
|
| 1670 |
"epoch": 13.49,
|
| 1671 |
+
"learning_rate": 2.8951507492394937e-06,
|
| 1672 |
+
"loss": 2.5613,
|
| 1673 |
"step": 1295
|
| 1674 |
},
|
| 1675 |
{
|
| 1676 |
"epoch": 13.54,
|
| 1677 |
+
"learning_rate": 2.854010575813856e-06,
|
| 1678 |
+
"loss": 2.5139,
|
| 1679 |
"step": 1300
|
| 1680 |
},
|
| 1681 |
{
|
| 1682 |
"epoch": 13.59,
|
| 1683 |
+
"learning_rate": 2.8130477302039292e-06,
|
| 1684 |
+
"loss": 2.5344,
|
| 1685 |
"step": 1305
|
| 1686 |
},
|
| 1687 |
{
|
| 1688 |
"epoch": 13.65,
|
| 1689 |
+
"learning_rate": 2.7722655972595438e-06,
|
| 1690 |
+
"loss": 2.6115,
|
| 1691 |
"step": 1310
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
"epoch": 13.7,
|
| 1695 |
+
"learning_rate": 2.731667546897845e-06,
|
| 1696 |
+
"loss": 2.551,
|
| 1697 |
"step": 1315
|
| 1698 |
},
|
| 1699 |
{
|
| 1700 |
"epoch": 13.75,
|
| 1701 |
+
"learning_rate": 2.6912569338248317e-06,
|
| 1702 |
+
"loss": 2.6828,
|
| 1703 |
"step": 1320
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 13.8,
|
| 1707 |
+
"learning_rate": 2.6510370972581455e-06,
|
| 1708 |
+
"loss": 2.502,
|
| 1709 |
"step": 1325
|
| 1710 |
},
|
| 1711 |
{
|
| 1712 |
"epoch": 13.85,
|
| 1713 |
+
"learning_rate": 2.61101136065115e-06,
|
| 1714 |
+
"loss": 2.6054,
|
| 1715 |
"step": 1330
|
| 1716 |
},
|
| 1717 |
{
|
| 1718 |
"epoch": 13.91,
|
| 1719 |
+
"learning_rate": 2.5711830314182996e-06,
|
| 1720 |
+
"loss": 2.6214,
|
| 1721 |
"step": 1335
|
| 1722 |
},
|
| 1723 |
{
|
| 1724 |
"epoch": 13.96,
|
| 1725 |
+
"learning_rate": 2.5315554006618487e-06,
|
| 1726 |
+
"loss": 2.519,
|
| 1727 |
"step": 1340
|
| 1728 |
},
|
| 1729 |
{
|
| 1730 |
"epoch": 14.0,
|
| 1731 |
+
"eval_loss": 2.567744255065918,
|
| 1732 |
+
"eval_runtime": 174.5513,
|
| 1733 |
+
"eval_samples_per_second": 4.388,
|
| 1734 |
+
"eval_steps_per_second": 1.1,
|
| 1735 |
"step": 1344
|
| 1736 |
},
|
| 1737 |
{
|
| 1738 |
"epoch": 14.01,
|
| 1739 |
+
"learning_rate": 2.4921317428998924e-06,
|
| 1740 |
+
"loss": 2.5582,
|
| 1741 |
"step": 1345
|
| 1742 |
},
|
| 1743 |
{
|
| 1744 |
"epoch": 14.06,
|
| 1745 |
+
"learning_rate": 2.4529153157957913e-06,
|
| 1746 |
+
"loss": 2.4842,
|
| 1747 |
"step": 1350
|
| 1748 |
},
|
| 1749 |
{
|
| 1750 |
"epoch": 14.11,
|
| 1751 |
+
"learning_rate": 2.4139093598889806e-06,
|
| 1752 |
+
"loss": 2.5287,
|
| 1753 |
"step": 1355
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 14.17,
|
| 1757 |
+
"learning_rate": 2.3751170983272e-06,
|
| 1758 |
+
"loss": 2.6123,
|
| 1759 |
"step": 1360
|
| 1760 |
},
|
| 1761 |
{
|
| 1762 |
"epoch": 14.22,
|
| 1763 |
+
"learning_rate": 2.3365417366001552e-06,
|
| 1764 |
+
"loss": 2.6674,
|
| 1765 |
"step": 1365
|
| 1766 |
},
|
| 1767 |
{
|
| 1768 |
"epoch": 14.27,
|
| 1769 |
+
"learning_rate": 2.2981864622746438e-06,
|
| 1770 |
+
"loss": 2.6728,
|
| 1771 |
"step": 1370
|
| 1772 |
},
|
| 1773 |
{
|
| 1774 |
"epoch": 14.32,
|
| 1775 |
+
"learning_rate": 2.260054444731155e-06,
|
| 1776 |
+
"loss": 2.5313,
|
| 1777 |
"step": 1375
|
| 1778 |
},
|
| 1779 |
{
|
| 1780 |
"epoch": 14.38,
|
| 1781 |
+
"learning_rate": 2.2221488349019903e-06,
|
| 1782 |
+
"loss": 2.664,
|
| 1783 |
"step": 1380
|
| 1784 |
},
|
| 1785 |
{
|
| 1786 |
"epoch": 14.43,
|
| 1787 |
+
"learning_rate": 2.184472765010871e-06,
|
| 1788 |
+
"loss": 2.4754,
|
| 1789 |
"step": 1385
|
| 1790 |
},
|
| 1791 |
{
|
| 1792 |
"epoch": 14.48,
|
| 1793 |
+
"learning_rate": 2.147029348314136e-06,
|
| 1794 |
+
"loss": 2.6064,
|
| 1795 |
"step": 1390
|
| 1796 |
},
|
| 1797 |
{
|
| 1798 |
"epoch": 14.53,
|
| 1799 |
+
"learning_rate": 2.109821678843484e-06,
|
| 1800 |
+
"loss": 2.5408,
|
| 1801 |
"step": 1395
|
| 1802 |
},
|
| 1803 |
{
|
| 1804 |
"epoch": 14.58,
|
| 1805 |
+
"learning_rate": 2.0728528311502977e-06,
|
| 1806 |
+
"loss": 2.6351,
|
| 1807 |
"step": 1400
|
| 1808 |
},
|
| 1809 |
{
|
| 1810 |
"epoch": 14.64,
|
| 1811 |
+
"learning_rate": 2.036125860051594e-06,
|
| 1812 |
+
"loss": 2.4797,
|
| 1813 |
"step": 1405
|
| 1814 |
},
|
| 1815 |
{
|
| 1816 |
"epoch": 14.69,
|
| 1817 |
+
"learning_rate": 1.999643800377596e-06,
|
| 1818 |
+
"loss": 2.6001,
|
| 1819 |
"step": 1410
|
| 1820 |
},
|
| 1821 |
{
|
| 1822 |
"epoch": 14.74,
|
| 1823 |
+
"learning_rate": 1.963409666720958e-06,
|
| 1824 |
+
"loss": 2.5746,
|
| 1825 |
"step": 1415
|
| 1826 |
},
|
| 1827 |
{
|
| 1828 |
"epoch": 14.79,
|
| 1829 |
+
"learning_rate": 1.927426453187663e-06,
|
| 1830 |
+
"loss": 2.5829,
|
| 1831 |
"step": 1420
|
| 1832 |
},
|
| 1833 |
{
|
| 1834 |
"epoch": 14.84,
|
| 1835 |
+
"learning_rate": 1.8916971331496143e-06,
|
| 1836 |
+
"loss": 2.5435,
|
| 1837 |
"step": 1425
|
| 1838 |
},
|
| 1839 |
{
|
| 1840 |
"epoch": 14.9,
|
| 1841 |
+
"learning_rate": 1.8562246589989369e-06,
|
| 1842 |
+
"loss": 2.5677,
|
| 1843 |
"step": 1430
|
| 1844 |
},
|
| 1845 |
{
|
| 1846 |
"epoch": 14.95,
|
| 1847 |
+
"learning_rate": 1.8210119619040206e-06,
|
| 1848 |
+
"loss": 2.4879,
|
| 1849 |
"step": 1435
|
| 1850 |
},
|
| 1851 |
{
|
| 1852 |
"epoch": 15.0,
|
| 1853 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 1854 |
+
"loss": 2.5076,
|
| 1855 |
"step": 1440
|
| 1856 |
},
|
| 1857 |
{
|
| 1858 |
"epoch": 15.0,
|
| 1859 |
+
"eval_loss": 2.5677287578582764,
|
| 1860 |
+
"eval_runtime": 174.6013,
|
| 1861 |
"eval_samples_per_second": 4.387,
|
| 1862 |
"eval_steps_per_second": 1.1,
|
| 1863 |
"step": 1440
|
| 1864 |
},
|
| 1865 |
{
|
| 1866 |
"epoch": 15.05,
|
| 1867 |
+
"learning_rate": 1.75137751598484e-06,
|
| 1868 |
+
"loss": 2.522,
|
| 1869 |
"step": 1445
|
| 1870 |
},
|
| 1871 |
{
|
| 1872 |
"epoch": 15.1,
|
| 1873 |
+
"learning_rate": 1.7169615212076612e-06,
|
| 1874 |
+
"loss": 2.5531,
|
| 1875 |
"step": 1450
|
| 1876 |
},
|
| 1877 |
{
|
| 1878 |
"epoch": 15.16,
|
| 1879 |
+
"learning_rate": 1.6828168111049454e-06,
|
| 1880 |
+
"loss": 2.6733,
|
| 1881 |
"step": 1455
|
| 1882 |
},
|
| 1883 |
{
|
| 1884 |
"epoch": 15.21,
|
| 1885 |
+
"learning_rate": 1.6489462071290213e-06,
|
| 1886 |
+
"loss": 2.5552,
|
| 1887 |
"step": 1460
|
| 1888 |
},
|
| 1889 |
{
|
| 1890 |
"epoch": 15.26,
|
| 1891 |
+
"learning_rate": 1.615352508082229e-06,
|
| 1892 |
+
"loss": 2.5467,
|
| 1893 |
"step": 1465
|
| 1894 |
},
|
| 1895 |
{
|
| 1896 |
"epoch": 15.31,
|
| 1897 |
+
"learning_rate": 1.5820384898856433e-06,
|
| 1898 |
+
"loss": 2.4187,
|
| 1899 |
"step": 1470
|
| 1900 |
},
|
| 1901 |
{
|
| 1902 |
"epoch": 15.36,
|
| 1903 |
+
"learning_rate": 1.549006905349702e-06,
|
| 1904 |
+
"loss": 2.5954,
|
| 1905 |
"step": 1475
|
| 1906 |
},
|
| 1907 |
{
|
| 1908 |
"epoch": 15.42,
|
| 1909 |
+
"learning_rate": 1.5162604839467265e-06,
|
| 1910 |
+
"loss": 2.6387,
|
| 1911 |
"step": 1480
|
| 1912 |
},
|
| 1913 |
{
|
| 1914 |
"epoch": 15.47,
|
| 1915 |
+
"learning_rate": 1.4838019315853796e-06,
|
| 1916 |
+
"loss": 2.6038,
|
| 1917 |
"step": 1485
|
| 1918 |
},
|
| 1919 |
{
|
| 1920 |
"epoch": 15.52,
|
| 1921 |
+
"learning_rate": 1.4516339303870763e-06,
|
| 1922 |
+
"loss": 2.5639,
|
| 1923 |
"step": 1490
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 15.57,
|
| 1927 |
+
"learning_rate": 1.419759138464355e-06,
|
| 1928 |
+
"loss": 2.5704,
|
| 1929 |
"step": 1495
|
| 1930 |
},
|
| 1931 |
{
|
| 1932 |
"epoch": 15.62,
|
| 1933 |
+
"learning_rate": 1.3881801897012225e-06,
|
| 1934 |
+
"loss": 2.4915,
|
| 1935 |
"step": 1500
|
| 1936 |
},
|
| 1937 |
{
|
| 1938 |
"epoch": 15.68,
|
| 1939 |
+
"learning_rate": 1.3568996935355194e-06,
|
| 1940 |
+
"loss": 2.5739,
|
| 1941 |
"step": 1505
|
| 1942 |
},
|
| 1943 |
{
|
| 1944 |
"epoch": 15.73,
|
| 1945 |
+
"learning_rate": 1.325920234743291e-06,
|
| 1946 |
+
"loss": 2.6971,
|
| 1947 |
"step": 1510
|
| 1948 |
},
|
| 1949 |
{
|
| 1950 |
"epoch": 15.78,
|
| 1951 |
+
"learning_rate": 1.2952443732252058e-06,
|
| 1952 |
+
"loss": 2.5222,
|
| 1953 |
"step": 1515
|
| 1954 |
},
|
| 1955 |
{
|
| 1956 |
"epoch": 15.83,
|
| 1957 |
+
"learning_rate": 1.264874643795021e-06,
|
| 1958 |
+
"loss": 2.4783,
|
| 1959 |
"step": 1520
|
| 1960 |
},
|
| 1961 |
{
|
| 1962 |
"epoch": 15.89,
|
| 1963 |
+
"learning_rate": 1.234813555970129e-06,
|
| 1964 |
+
"loss": 2.5954,
|
| 1965 |
"step": 1525
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 15.94,
|
| 1969 |
+
"learning_rate": 1.2050635937641909e-06,
|
| 1970 |
+
"loss": 2.6067,
|
| 1971 |
"step": 1530
|
| 1972 |
},
|
| 1973 |
{
|
| 1974 |
"epoch": 15.99,
|
| 1975 |
+
"learning_rate": 1.1756272154818715e-06,
|
| 1976 |
+
"loss": 2.5443,
|
| 1977 |
"step": 1535
|
| 1978 |
},
|
| 1979 |
{
|
| 1980 |
"epoch": 16.0,
|
| 1981 |
+
"eval_loss": 2.567720413208008,
|
| 1982 |
+
"eval_runtime": 174.877,
|
| 1983 |
+
"eval_samples_per_second": 4.38,
|
| 1984 |
+
"eval_steps_per_second": 1.098,
|
| 1985 |
"step": 1536
|
| 1986 |
},
|
| 1987 |
{
|
| 1988 |
"epoch": 16.04,
|
| 1989 |
+
"learning_rate": 1.1465068535157098e-06,
|
| 1990 |
+
"loss": 2.5967,
|
| 1991 |
"step": 1540
|
| 1992 |
},
|
| 1993 |
{
|
| 1994 |
"epoch": 16.09,
|
| 1995 |
+
"learning_rate": 1.1177049141451223e-06,
|
| 1996 |
+
"loss": 2.6367,
|
| 1997 |
"step": 1545
|
| 1998 |
},
|
| 1999 |
{
|
| 2000 |
"epoch": 16.15,
|
| 2001 |
+
"learning_rate": 1.089223777337568e-06,
|
| 2002 |
+
"loss": 2.5624,
|
| 2003 |
"step": 1550
|
| 2004 |
},
|
| 2005 |
{
|
| 2006 |
"epoch": 16.2,
|
| 2007 |
+
"learning_rate": 1.0610657965518861e-06,
|
| 2008 |
+
"loss": 2.5973,
|
| 2009 |
"step": 1555
|
| 2010 |
},
|
| 2011 |
{
|
| 2012 |
"epoch": 16.25,
|
| 2013 |
+
"learning_rate": 1.0332332985438248e-06,
|
| 2014 |
+
"loss": 2.4671,
|
| 2015 |
"step": 1560
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 16.3,
|
| 2019 |
+
"learning_rate": 1.0057285831737739e-06,
|
| 2020 |
+
"loss": 2.5794,
|
| 2021 |
"step": 1565
|
| 2022 |
},
|
| 2023 |
{
|
| 2024 |
"epoch": 16.35,
|
| 2025 |
+
"learning_rate": 9.785539232167296e-07,
|
| 2026 |
+
"loss": 2.6019,
|
| 2027 |
"step": 1570
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 16.41,
|
| 2031 |
+
"learning_rate": 9.517115641744795e-07,
|
| 2032 |
+
"loss": 2.3944,
|
| 2033 |
"step": 1575
|
| 2034 |
},
|
| 2035 |
{
|
| 2036 |
"epoch": 16.46,
|
| 2037 |
+
"learning_rate": 9.252037240900618e-07,
|
| 2038 |
+
"loss": 2.6003,
|
| 2039 |
"step": 1580
|
| 2040 |
},
|
| 2041 |
{
|
| 2042 |
"epoch": 16.51,
|
| 2043 |
+
"learning_rate": 8.990325933644717e-07,
|
| 2044 |
+
"loss": 2.5742,
|
| 2045 |
"step": 1585
|
| 2046 |
},
|
| 2047 |
{
|
| 2048 |
"epoch": 16.56,
|
| 2049 |
+
"learning_rate": 8.732003345756812e-07,
|
| 2050 |
+
"loss": 2.5666,
|
| 2051 |
"step": 1590
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 16.61,
|
| 2055 |
+
"learning_rate": 8.47709082299924e-07,
|
| 2056 |
+
"loss": 2.5089,
|
| 2057 |
"step": 1595
|
| 2058 |
},
|
| 2059 |
{
|
| 2060 |
"epoch": 16.67,
|
| 2061 |
+
"learning_rate": 8.225609429353187e-07,
|
| 2062 |
+
"loss": 2.6752,
|
| 2063 |
"step": 1600
|
| 2064 |
},
|
| 2065 |
{
|
| 2066 |
"epoch": 16.72,
|
| 2067 |
+
"learning_rate": 7.977579945278091e-07,
|
| 2068 |
+
"loss": 2.6726,
|
| 2069 |
"step": 1605
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 16.77,
|
| 2073 |
+
"learning_rate": 7.733022865994599e-07,
|
| 2074 |
+
"loss": 2.5055,
|
| 2075 |
"step": 1610
|
| 2076 |
},
|
| 2077 |
{
|
| 2078 |
"epoch": 16.82,
|
| 2079 |
+
"learning_rate": 7.491958399790827e-07,
|
| 2080 |
+
"loss": 2.564,
|
| 2081 |
"step": 1615
|
| 2082 |
},
|
| 2083 |
{
|
| 2084 |
"epoch": 16.88,
|
| 2085 |
+
"learning_rate": 7.254406466352682e-07,
|
| 2086 |
+
"loss": 2.5455,
|
| 2087 |
"step": 1620
|
| 2088 |
},
|
| 2089 |
{
|
| 2090 |
"epoch": 16.93,
|
| 2091 |
+
"learning_rate": 7.020386695117732e-07,
|
| 2092 |
+
"loss": 2.5649,
|
| 2093 |
"step": 1625
|
| 2094 |
},
|
| 2095 |
{
|
| 2096 |
"epoch": 16.98,
|
| 2097 |
+
"learning_rate": 6.789918423653285e-07,
|
| 2098 |
+
"loss": 2.5972,
|
| 2099 |
"step": 1630
|
| 2100 |
},
|
| 2101 |
{
|
| 2102 |
"epoch": 17.0,
|
| 2103 |
+
"eval_loss": 2.5676934719085693,
|
| 2104 |
+
"eval_runtime": 164.8301,
|
| 2105 |
+
"eval_samples_per_second": 4.647,
|
| 2106 |
+
"eval_steps_per_second": 0.582,
|
| 2107 |
"step": 1632
|
| 2108 |
},
|
| 2109 |
{
|
| 2110 |
"epoch": 17.03,
|
| 2111 |
+
"learning_rate": 6.563020696058387e-07,
|
| 2112 |
+
"loss": 2.5949,
|
| 2113 |
"step": 1635
|
| 2114 |
},
|
| 2115 |
{
|
| 2116 |
"epoch": 17.08,
|
| 2117 |
+
"learning_rate": 6.339712261390213e-07,
|
| 2118 |
+
"loss": 2.5258,
|
| 2119 |
"step": 1640
|
| 2120 |
},
|
| 2121 |
{
|
| 2122 |
"epoch": 17.14,
|
| 2123 |
+
"learning_rate": 6.120011572114803e-07,
|
| 2124 |
+
"loss": 2.6606,
|
| 2125 |
"step": 1645
|
| 2126 |
},
|
| 2127 |
{
|
| 2128 |
"epoch": 17.19,
|
| 2129 |
+
"learning_rate": 5.903936782582253e-07,
|
| 2130 |
+
"loss": 2.5174,
|
| 2131 |
"step": 1650
|
| 2132 |
},
|
| 2133 |
{
|
| 2134 |
"epoch": 17.24,
|
| 2135 |
+
"learning_rate": 5.691505747526633e-07,
|
| 2136 |
+
"loss": 2.6218,
|
| 2137 |
"step": 1655
|
| 2138 |
},
|
| 2139 |
{
|
| 2140 |
"epoch": 17.29,
|
| 2141 |
+
"learning_rate": 5.482736020590551e-07,
|
| 2142 |
+
"loss": 2.5367,
|
| 2143 |
"step": 1660
|
| 2144 |
},
|
| 2145 |
{
|
| 2146 |
"epoch": 17.34,
|
| 2147 |
+
"learning_rate": 5.277644852874742e-07,
|
| 2148 |
+
"loss": 2.6172,
|
| 2149 |
"step": 1665
|
| 2150 |
},
|
| 2151 |
{
|
| 2152 |
"epoch": 17.4,
|
| 2153 |
+
"learning_rate": 5.076249191512461e-07,
|
| 2154 |
+
"loss": 2.5443,
|
| 2155 |
"step": 1670
|
| 2156 |
},
|
| 2157 |
{
|
| 2158 |
"epoch": 17.45,
|
| 2159 |
+
"learning_rate": 4.878565678269204e-07,
|
| 2160 |
+
"loss": 2.406,
|
| 2161 |
"step": 1675
|
| 2162 |
},
|
| 2163 |
{
|
| 2164 |
"epoch": 17.5,
|
| 2165 |
+
"learning_rate": 4.6846106481675035e-07,
|
| 2166 |
+
"loss": 2.6111,
|
| 2167 |
"step": 1680
|
| 2168 |
},
|
| 2169 |
{
|
| 2170 |
"epoch": 17.55,
|
| 2171 |
+
"learning_rate": 4.494400128137144e-07,
|
| 2172 |
+
"loss": 2.5944,
|
| 2173 |
"step": 1685
|
| 2174 |
},
|
| 2175 |
{
|
| 2176 |
"epoch": 17.6,
|
| 2177 |
+
"learning_rate": 4.3079498356908446e-07,
|
| 2178 |
+
"loss": 2.589,
|
| 2179 |
"step": 1690
|
| 2180 |
},
|
| 2181 |
{
|
| 2182 |
"epoch": 17.66,
|
| 2183 |
+
"learning_rate": 4.1252751776254373e-07,
|
| 2184 |
+
"loss": 2.6432,
|
| 2185 |
"step": 1695
|
| 2186 |
},
|
| 2187 |
{
|
| 2188 |
"epoch": 17.71,
|
| 2189 |
+
"learning_rate": 3.946391248748821e-07,
|
| 2190 |
+
"loss": 2.6341,
|
| 2191 |
"step": 1700
|
| 2192 |
},
|
| 2193 |
{
|
| 2194 |
"epoch": 17.76,
|
| 2195 |
+
"learning_rate": 3.7713128306326286e-07,
|
| 2196 |
+
"loss": 2.4919,
|
| 2197 |
"step": 1705
|
| 2198 |
},
|
| 2199 |
{
|
| 2200 |
"epoch": 17.81,
|
| 2201 |
+
"learning_rate": 3.600054390390778e-07,
|
| 2202 |
+
"loss": 2.4727,
|
| 2203 |
"step": 1710
|
| 2204 |
},
|
| 2205 |
{
|
| 2206 |
"epoch": 17.86,
|
| 2207 |
+
"learning_rate": 3.4326300794840174e-07,
|
| 2208 |
+
"loss": 2.5534,
|
| 2209 |
"step": 1715
|
| 2210 |
},
|
| 2211 |
{
|
| 2212 |
"epoch": 17.92,
|
| 2213 |
+
"learning_rate": 3.269053732550581e-07,
|
| 2214 |
+
"loss": 2.6066,
|
| 2215 |
"step": 1720
|
| 2216 |
},
|
| 2217 |
{
|
| 2218 |
"epoch": 17.97,
|
| 2219 |
+
"learning_rate": 3.1093388662630173e-07,
|
| 2220 |
+
"loss": 2.5361,
|
| 2221 |
"step": 1725
|
| 2222 |
},
|
| 2223 |
{
|
| 2224 |
"epoch": 18.0,
|
| 2225 |
+
"eval_loss": 2.567695140838623,
|
| 2226 |
+
"eval_runtime": 164.9524,
|
| 2227 |
+
"eval_samples_per_second": 4.644,
|
| 2228 |
+
"eval_steps_per_second": 0.582,
|
| 2229 |
"step": 1728
|
| 2230 |
},
|
| 2231 |
{
|
| 2232 |
"epoch": 18.02,
|
| 2233 |
+
"learning_rate": 2.9534986782112306e-07,
|
| 2234 |
+
"loss": 2.608,
|
| 2235 |
"step": 1730
|
| 2236 |
},
|
| 2237 |
{
|
| 2238 |
"epoch": 18.07,
|
| 2239 |
+
"learning_rate": 2.80154604581197e-07,
|
| 2240 |
+
"loss": 2.5554,
|
| 2241 |
"step": 1735
|
| 2242 |
},
|
| 2243 |
{
|
| 2244 |
"epoch": 18.12,
|
| 2245 |
+
"learning_rate": 2.653493525244721e-07,
|
| 2246 |
+
"loss": 2.6435,
|
| 2247 |
"step": 1740
|
| 2248 |
},
|
| 2249 |
{
|
| 2250 |
"epoch": 18.18,
|
| 2251 |
+
"learning_rate": 2.5093533504141786e-07,
|
| 2252 |
+
"loss": 2.5905,
|
| 2253 |
"step": 1745
|
| 2254 |
},
|
| 2255 |
{
|
| 2256 |
"epoch": 18.23,
|
| 2257 |
+
"learning_rate": 2.3691374319393168e-07,
|
| 2258 |
+
"loss": 2.5416,
|
| 2259 |
"step": 1750
|
| 2260 |
},
|
| 2261 |
{
|
| 2262 |
"epoch": 18.28,
|
| 2263 |
+
"learning_rate": 2.232857356169199e-07,
|
| 2264 |
+
"loss": 2.5946,
|
| 2265 |
"step": 1755
|
| 2266 |
},
|
| 2267 |
{
|
| 2268 |
"epoch": 18.33,
|
| 2269 |
+
"learning_rate": 2.1005243842255552e-07,
|
| 2270 |
+
"loss": 2.5916,
|
| 2271 |
"step": 1760
|
| 2272 |
},
|
| 2273 |
{
|
| 2274 |
"epoch": 18.39,
|
| 2275 |
+
"learning_rate": 1.972149451072297e-07,
|
| 2276 |
+
"loss": 2.5382,
|
| 2277 |
"step": 1765
|
| 2278 |
},
|
| 2279 |
{
|
| 2280 |
"epoch": 18.44,
|
| 2281 |
+
"learning_rate": 1.8477431646118648e-07,
|
| 2282 |
+
"loss": 2.6638,
|
| 2283 |
"step": 1770
|
| 2284 |
},
|
| 2285 |
{
|
| 2286 |
"epoch": 18.49,
|
| 2287 |
+
"learning_rate": 1.7273158048087434e-07,
|
| 2288 |
+
"loss": 2.5931,
|
| 2289 |
"step": 1775
|
| 2290 |
},
|
| 2291 |
{
|
| 2292 |
"epoch": 18.54,
|
| 2293 |
+
"learning_rate": 1.6108773228399543e-07,
|
| 2294 |
+
"loss": 2.5053,
|
| 2295 |
"step": 1780
|
| 2296 |
},
|
| 2297 |
{
|
| 2298 |
"epoch": 18.59,
|
| 2299 |
+
"learning_rate": 1.4984373402728014e-07,
|
| 2300 |
+
"loss": 2.5557,
|
| 2301 |
"step": 1785
|
| 2302 |
},
|
| 2303 |
{
|
| 2304 |
"epoch": 18.65,
|
| 2305 |
+
"learning_rate": 1.3900051482698074e-07,
|
| 2306 |
+
"loss": 2.5686,
|
| 2307 |
"step": 1790
|
| 2308 |
},
|
| 2309 |
{
|
| 2310 |
"epoch": 18.7,
|
| 2311 |
+
"learning_rate": 1.2855897068209555e-07,
|
| 2312 |
+
"loss": 2.594,
|
| 2313 |
"step": 1795
|
| 2314 |
},
|
| 2315 |
{
|
| 2316 |
"epoch": 18.75,
|
| 2317 |
+
"learning_rate": 1.185199644003332e-07,
|
| 2318 |
+
"loss": 2.4774,
|
| 2319 |
"step": 1800
|
| 2320 |
},
|
| 2321 |
{
|
| 2322 |
"epoch": 18.8,
|
| 2323 |
+
"learning_rate": 1.0888432552681405e-07,
|
| 2324 |
+
"loss": 2.6601,
|
| 2325 |
"step": 1805
|
| 2326 |
},
|
| 2327 |
{
|
| 2328 |
"epoch": 18.85,
|
| 2329 |
+
"learning_rate": 9.965285027552452e-08,
|
| 2330 |
+
"loss": 2.5226,
|
| 2331 |
"step": 1810
|
| 2332 |
},
|
| 2333 |
{
|
| 2334 |
"epoch": 18.91,
|
| 2335 |
+
"learning_rate": 9.082630146352356e-08,
|
| 2336 |
+
"loss": 2.4359,
|
| 2337 |
"step": 1815
|
| 2338 |
},
|
| 2339 |
{
|
| 2340 |
"epoch": 18.96,
|
| 2341 |
+
"learning_rate": 8.240540844791145e-08,
|
| 2342 |
+
"loss": 2.5317,
|
| 2343 |
"step": 1820
|
| 2344 |
},
|
| 2345 |
{
|
| 2346 |
"epoch": 19.0,
|
| 2347 |
+
"eval_loss": 2.567706346511841,
|
| 2348 |
+
"eval_runtime": 164.8443,
|
| 2349 |
+
"eval_samples_per_second": 4.647,
|
| 2350 |
+
"eval_steps_per_second": 0.582,
|
| 2351 |
"step": 1824
|
| 2352 |
},
|
| 2353 |
{
|
| 2354 |
"epoch": 19.01,
|
| 2355 |
+
"learning_rate": 7.439086706555743e-08,
|
| 2356 |
+
"loss": 2.5861,
|
| 2357 |
"step": 1825
|
| 2358 |
},
|
| 2359 |
{
|
| 2360 |
"epoch": 19.06,
|
| 2361 |
+
"learning_rate": 6.678333957560513e-08,
|
| 2362 |
+
"loss": 2.6277,
|
| 2363 |
"step": 1830
|
| 2364 |
},
|
| 2365 |
{
|
| 2366 |
"epoch": 19.11,
|
| 2367 |
+
"learning_rate": 5.958345460474635e-08,
|
| 2368 |
+
"loss": 2.533,
|
| 2369 |
"step": 1835
|
| 2370 |
},
|
| 2371 |
{
|
| 2372 |
"epoch": 19.17,
|
| 2373 |
+
"learning_rate": 5.279180709527765e-08,
|
| 2374 |
+
"loss": 2.5901,
|
| 2375 |
"step": 1840
|
| 2376 |
},
|
| 2377 |
{
|
| 2378 |
"epoch": 19.22,
|
| 2379 |
+
"learning_rate": 4.640895825593683e-08,
|
| 2380 |
+
"loss": 2.6011,
|
| 2381 |
"step": 1845
|
| 2382 |
},
|
| 2383 |
{
|
| 2384 |
"epoch": 19.27,
|
| 2385 |
+
"learning_rate": 4.0435435515532304e-08,
|
| 2386 |
+
"loss": 2.6357,
|
| 2387 |
"step": 1850
|
| 2388 |
},
|
| 2389 |
{
|
| 2390 |
"epoch": 19.32,
|
| 2391 |
+
"learning_rate": 3.487173247935627e-08,
|
| 2392 |
+
"loss": 2.5523,
|
| 2393 |
"step": 1855
|
| 2394 |
},
|
| 2395 |
{
|
| 2396 |
"epoch": 19.38,
|
| 2397 |
+
"learning_rate": 2.971830888840177e-08,
|
| 2398 |
+
"loss": 2.5988,
|
| 2399 |
"step": 1860
|
| 2400 |
},
|
| 2401 |
{
|
| 2402 |
"epoch": 19.43,
|
| 2403 |
+
"learning_rate": 2.4975590581369778e-08,
|
| 2404 |
+
"loss": 2.6604,
|
| 2405 |
"step": 1865
|
| 2406 |
},
|
| 2407 |
{
|
| 2408 |
"epoch": 19.48,
|
| 2409 |
+
"learning_rate": 2.0643969459482326e-08,
|
| 2410 |
+
"loss": 2.5515,
|
| 2411 |
"step": 1870
|
| 2412 |
},
|
| 2413 |
{
|
| 2414 |
"epoch": 19.53,
|
| 2415 |
+
"learning_rate": 1.6723803454098408e-08,
|
| 2416 |
+
"loss": 2.6021,
|
| 2417 |
"step": 1875
|
| 2418 |
},
|
| 2419 |
{
|
| 2420 |
"epoch": 19.58,
|
| 2421 |
+
"learning_rate": 1.3215416497138756e-08,
|
| 2422 |
+
"loss": 2.5515,
|
| 2423 |
"step": 1880
|
| 2424 |
},
|
| 2425 |
{
|
| 2426 |
"epoch": 19.64,
|
| 2427 |
+
"learning_rate": 1.0119098494316693e-08,
|
| 2428 |
+
"loss": 2.4397,
|
| 2429 |
"step": 1885
|
| 2430 |
},
|
| 2431 |
{
|
| 2432 |
"epoch": 19.69,
|
| 2433 |
+
"learning_rate": 7.43510530118452e-09,
|
| 2434 |
+
"loss": 2.5337,
|
| 2435 |
"step": 1890
|
| 2436 |
},
|
| 2437 |
{
|
| 2438 |
"epoch": 19.74,
|
| 2439 |
+
"learning_rate": 5.163658701989316e-09,
|
| 2440 |
+
"loss": 2.4587,
|
| 2441 |
"step": 1895
|
| 2442 |
},
|
| 2443 |
{
|
| 2444 |
"epoch": 19.79,
|
| 2445 |
+
"learning_rate": 3.304946391349817e-09,
|
| 2446 |
+
"loss": 2.5766,
|
| 2447 |
"step": 1900
|
| 2448 |
},
|
| 2449 |
{
|
| 2450 |
"epoch": 19.84,
|
| 2451 |
+
"learning_rate": 1.8591219587416053e-09,
|
| 2452 |
+
"loss": 2.4665,
|
| 2453 |
"step": 1905
|
| 2454 |
},
|
| 2455 |
{
|
| 2456 |
"epoch": 19.9,
|
| 2457 |
+
"learning_rate": 8.26304875812256e-10,
|
| 2458 |
+
"loss": 2.6275,
|
| 2459 |
"step": 1910
|
| 2460 |
},
|
| 2461 |
{
|
| 2462 |
"epoch": 19.95,
|
| 2463 |
+
"learning_rate": 2.0658048650257223e-10,
|
| 2464 |
+
"loss": 2.5522,
|
| 2465 |
"step": 1915
|
| 2466 |
},
|
| 2467 |
{
|
| 2468 |
"epoch": 20.0,
|
| 2469 |
"learning_rate": 0.0,
|
| 2470 |
+
"loss": 2.632,
|
| 2471 |
"step": 1920
|
| 2472 |
},
|
| 2473 |
{
|
| 2474 |
"epoch": 20.0,
|
| 2475 |
+
"eval_loss": 2.5677051544189453,
|
| 2476 |
+
"eval_runtime": 164.798,
|
| 2477 |
+
"eval_samples_per_second": 4.648,
|
| 2478 |
+
"eval_steps_per_second": 0.583,
|
| 2479 |
"step": 1920
|
| 2480 |
},
|
| 2481 |
{
|
| 2482 |
"epoch": 20.0,
|
| 2483 |
"step": 1920,
|
| 2484 |
"total_flos": 1.0984887148766822e+18,
|
| 2485 |
+
"train_loss": 0.428011018037796,
|
| 2486 |
+
"train_runtime": 2530.9924,
|
| 2487 |
+
"train_samples_per_second": 6.053,
|
| 2488 |
+
"train_steps_per_second": 0.759
|
| 2489 |
}
|
| 2490 |
],
|
| 2491 |
"logging_steps": 5,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fcd2d34fa2a07b0718ff1754f0d2b0590e8818ecf133c21ffda74cf3db65e8b
|
| 3 |
size 4728
|