End of training
Browse files- README.md +44 -24
- model.safetensors +1 -1
- runs/Dec05_23-35-46_DESKTOP-A45193E/events.out.tfevents.1701812151.DESKTOP-A45193E +3 -0
- trainer_state.json +1119 -919
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
- Mean Distance: 0
|
| 20 |
- Max Distance: 1
|
| 21 |
|
|
@@ -43,32 +43,52 @@ The following hyperparameters were used during training:
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
-
| Training Loss | Epoch | Step
|
| 51 |
-
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.0017 | 14.0 | 37296
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0632
|
| 19 |
- Mean Distance: 0
|
| 20 |
- Max Distance: 1
|
| 21 |
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
+
- num_epochs: 40
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.8541 | 1.0 | 2664 | 0.3404 | 0 | 1 |
|
| 53 |
+
| 0.0451 | 2.0 | 5328 | 0.0605 | 0 | 1 |
|
| 54 |
+
| 0.0112 | 3.0 | 7992 | 0.0411 | 0 | 1 |
|
| 55 |
+
| 0.0068 | 4.0 | 10656 | 0.0205 | 0 | 1 |
|
| 56 |
+
| 0.007 | 5.0 | 13320 | 0.0242 | 0 | 1 |
|
| 57 |
+
| 0.0022 | 6.0 | 15984 | 0.0272 | 0 | 1 |
|
| 58 |
+
| 0.0054 | 7.0 | 18648 | 0.0080 | 0 | 1 |
|
| 59 |
+
| 0.0036 | 8.0 | 21312 | 0.0252 | 0 | 1 |
|
| 60 |
+
| 0.0039 | 9.0 | 23976 | 0.0210 | 0 | 1 |
|
| 61 |
+
| 0.0026 | 10.0 | 26640 | 0.0170 | 0 | 1 |
|
| 62 |
+
| 0.0026 | 11.0 | 29304 | 0.0043 | 0 | 1 |
|
| 63 |
+
| 0.0029 | 12.0 | 31968 | 0.0135 | 0 | 1 |
|
| 64 |
+
| 0.0011 | 13.0 | 34632 | 0.0313 | 0 | 1 |
|
| 65 |
+
| 0.0017 | 14.0 | 37296 | 0.0353 | 0 | 1 |
|
| 66 |
+
| 0.0014 | 15.0 | 39960 | 0.0117 | 0 | 1 |
|
| 67 |
+
| 0.0014 | 16.0 | 42624 | 0.0140 | 0 | 1 |
|
| 68 |
+
| 0.0013 | 17.0 | 45288 | 0.0220 | 0 | 1 |
|
| 69 |
+
| 0.0009 | 18.0 | 47952 | 0.0247 | 0 | 1 |
|
| 70 |
+
| 0.0017 | 19.0 | 50616 | 0.0322 | 0 | 1 |
|
| 71 |
+
| 0.0022 | 20.0 | 53280 | 0.0314 | 0 | 1 |
|
| 72 |
+
| 0.0006 | 21.0 | 55944 | 0.0305 | 0 | 1 |
|
| 73 |
+
| 0.001 | 22.0 | 58608 | 0.0292 | 0 | 1 |
|
| 74 |
+
| 0.0008 | 23.0 | 61272 | 0.0373 | 0 | 1 |
|
| 75 |
+
| 0.0008 | 24.0 | 63936 | 0.0309 | 0 | 1 |
|
| 76 |
+
| 0.0008 | 25.0 | 66600 | 0.0385 | 0 | 1 |
|
| 77 |
+
| 0.0014 | 26.0 | 69264 | 0.0134 | 0 | 1 |
|
| 78 |
+
| 0.0004 | 27.0 | 71928 | 0.0239 | 0 | 1 |
|
| 79 |
+
| 0.0011 | 28.0 | 74592 | 0.0164 | 0 | 1 |
|
| 80 |
+
| 0.0002 | 29.0 | 77256 | 0.0186 | 0 | 1 |
|
| 81 |
+
| 0.0001 | 30.0 | 79920 | 0.0298 | 0 | 1 |
|
| 82 |
+
| 0.0008 | 31.0 | 82584 | 0.0277 | 0 | 1 |
|
| 83 |
+
| 0.0003 | 32.0 | 85248 | 0.0377 | 0 | 1 |
|
| 84 |
+
| 0.0003 | 33.0 | 87912 | 0.0354 | 0 | 1 |
|
| 85 |
+
| 0.0007 | 34.0 | 90576 | 0.0585 | 0 | 1 |
|
| 86 |
+
| 0.0005 | 35.0 | 93240 | 0.0568 | 0 | 1 |
|
| 87 |
+
| 0.0001 | 36.0 | 95904 | 0.0567 | 0 | 1 |
|
| 88 |
+
| 0.0009 | 37.0 | 98568 | 0.0605 | 0 | 1 |
|
| 89 |
+
| 0.0002 | 38.0 | 101232 | 0.0613 | 0 | 1 |
|
| 90 |
+
| 0.0002 | 39.0 | 103896 | 0.0563 | 0 | 1 |
|
| 91 |
+
| 0.0002 | 40.0 | 106560 | 0.0632 | 0 | 1 |
|
| 92 |
|
| 93 |
|
| 94 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1200729512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b231aefa39c9a5055819cb061fe2728111c61d5f415f2208c6a2c7bf69d4cb02
|
| 3 |
size 1200729512
|
runs/Dec05_23-35-46_DESKTOP-A45193E/events.out.tfevents.1701812151.DESKTOP-A45193E
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3503a3389c33e4b4456fe130dbdc3125a33273ba6e52e4dd20c768694f87ec7
|
| 3 |
+
size 52187
|
trainer_state.json
CHANGED
|
@@ -1,1428 +1,1628 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
-
{
|
| 18 |
-
"epoch": 0.1,
|
| 19 |
-
"learning_rate": 5.011261261261262e-06,
|
| 20 |
-
"loss": 28.5448,
|
| 21 |
-
"step": 267
|
| 22 |
-
},
|
| 23 |
{
|
| 24 |
"epoch": 0.2,
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
-
"step":
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.3,
|
| 31 |
-
"learning_rate": 1.5033783783783784e-05,
|
| 32 |
-
"loss": 22.7776,
|
| 33 |
-
"step": 801
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss":
|
| 39 |
-
"step":
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.5,
|
| 43 |
-
"learning_rate": 2.505630630630631e-05,
|
| 44 |
-
"loss": 8.3509,
|
| 45 |
-
"step": 1335
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
-
"step":
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.7,
|
| 55 |
-
"learning_rate": 3.507882882882883e-05,
|
| 56 |
-
"loss": 0.3406,
|
| 57 |
-
"step": 1869
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.8,
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 0.
|
| 63 |
-
"step":
|
| 64 |
-
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 0.9,
|
| 67 |
-
"learning_rate": 4.510135135135135e-05,
|
| 68 |
-
"loss": 0.2324,
|
| 69 |
-
"step": 2403
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
-
"eval_loss": 0.
|
| 74 |
"eval_max_distance": 1,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
-
"eval_runtime": 1.
|
| 77 |
-
"eval_samples_per_second":
|
| 78 |
-
"eval_steps_per_second":
|
| 79 |
"step": 2664
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
-
"learning_rate":
|
| 84 |
-
"loss": 0.
|
| 85 |
-
"step":
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 1.1,
|
| 89 |
-
"learning_rate": 5.512387387387388e-05,
|
| 90 |
-
"loss": 0.1234,
|
| 91 |
-
"step": 2937
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.2,
|
| 95 |
-
"learning_rate":
|
| 96 |
-
"loss": 0.
|
| 97 |
-
"step":
|
| 98 |
-
},
|
| 99 |
-
{
|
| 100 |
-
"epoch": 1.3,
|
| 101 |
-
"learning_rate": 6.514639639639641e-05,
|
| 102 |
-
"loss": 0.0721,
|
| 103 |
-
"step": 3471
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 1.4,
|
| 107 |
-
"learning_rate":
|
| 108 |
-
"loss": 0.
|
| 109 |
-
"step":
|
| 110 |
-
},
|
| 111 |
-
{
|
| 112 |
-
"epoch": 1.5,
|
| 113 |
-
"learning_rate": 7.516891891891891e-05,
|
| 114 |
-
"loss": 0.0262,
|
| 115 |
-
"step": 4005
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.6,
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
-
"step":
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 1.7,
|
| 125 |
-
"learning_rate": 8.519144144144144e-05,
|
| 126 |
-
"loss": 0.0235,
|
| 127 |
-
"step": 4539
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 1.8,
|
| 131 |
-
"learning_rate":
|
| 132 |
-
"loss": 0.
|
| 133 |
-
"step":
|
| 134 |
-
},
|
| 135 |
-
{
|
| 136 |
-
"epoch": 1.9,
|
| 137 |
-
"learning_rate": 9.521396396396397e-05,
|
| 138 |
-
"loss": 0.0151,
|
| 139 |
-
"step": 5073
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
"eval_max_distance": 1,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
-
"eval_runtime": 0.
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second": 26.
|
| 149 |
"step": 5328
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 2.0,
|
| 153 |
-
"learning_rate":
|
| 154 |
-
"loss": 0.
|
| 155 |
-
"step":
|
| 156 |
},
|
| 157 |
{
|
| 158 |
-
"epoch": 2.
|
| 159 |
-
"learning_rate":
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch": 2.
|
| 165 |
-
"learning_rate":
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 2.
|
| 171 |
-
"learning_rate":
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"step":
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 2.
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss": 0.
|
| 179 |
-
"step":
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch":
|
| 183 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
"loss": 0.0109,
|
| 185 |
-
"step":
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 2
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 0.
|
| 191 |
-
"step":
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"learning_rate":
|
| 196 |
-
"loss": 0.
|
| 197 |
-
"step":
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch":
|
| 201 |
-
"learning_rate": 9.
|
| 202 |
-
"loss": 0.
|
| 203 |
-
"step":
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch":
|
| 207 |
-
"learning_rate": 9.
|
| 208 |
-
"loss": 0.
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"eval_loss": 0.
|
| 214 |
"eval_max_distance": 1,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
-
"eval_runtime": 0.
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second":
|
| 219 |
-
"step":
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate": 9.
|
| 224 |
-
"loss": 0.
|
| 225 |
-
"step":
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate": 9.
|
| 230 |
-
"loss": 0.
|
| 231 |
-
"step":
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"learning_rate": 9.
|
| 236 |
-
"loss": 0.
|
| 237 |
-
"step":
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"learning_rate": 9.
|
| 242 |
-
"loss": 0.
|
| 243 |
-
"step":
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"learning_rate": 9.
|
| 248 |
-
"loss": 0.
|
| 249 |
-
"step":
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch":
|
| 259 |
-
"learning_rate": 9.
|
| 260 |
-
"loss": 0.
|
| 261 |
-
"step":
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"learning_rate": 9.
|
| 266 |
-
"loss": 0.
|
| 267 |
-
"step":
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"learning_rate":
|
| 272 |
-
"loss": 0.
|
| 273 |
-
"step":
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch":
|
| 277 |
-
"learning_rate":
|
| 278 |
-
"loss": 0.
|
| 279 |
-
"step":
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch":
|
| 283 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 284 |
"eval_max_distance": 1,
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
-
"eval_runtime": 0.
|
| 287 |
-
"eval_samples_per_second":
|
| 288 |
-
"eval_steps_per_second":
|
| 289 |
-
"step":
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch":
|
| 293 |
-
"learning_rate":
|
| 294 |
-
"loss": 0.
|
| 295 |
-
"step":
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch":
|
| 299 |
-
"learning_rate":
|
| 300 |
-
"loss": 0.
|
| 301 |
-
"step":
|
| 302 |
},
|
| 303 |
{
|
| 304 |
-
"epoch": 4
|
| 305 |
-
"learning_rate":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 306 |
"loss": 0.0034,
|
| 307 |
-
"step":
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch":
|
| 311 |
-
"learning_rate":
|
| 312 |
-
"loss": 0.
|
| 313 |
-
"step":
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch":
|
| 317 |
-
"
|
| 318 |
-
"
|
| 319 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 320 |
},
|
| 321 |
{
|
| 322 |
-
"epoch":
|
| 323 |
-
"learning_rate":
|
| 324 |
-
"loss": 0.
|
| 325 |
-
"step":
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch":
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 0.
|
| 331 |
-
"step":
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 4
|
| 335 |
-
"learning_rate":
|
| 336 |
-
"loss": 0.
|
| 337 |
-
"step":
|
| 338 |
},
|
| 339 |
{
|
| 340 |
-
"epoch":
|
| 341 |
-
"learning_rate": 8.
|
| 342 |
-
"loss": 0.
|
| 343 |
-
"step":
|
| 344 |
},
|
| 345 |
{
|
| 346 |
-
"epoch":
|
| 347 |
-
"learning_rate": 8.
|
| 348 |
-
"loss": 0.
|
| 349 |
-
"step":
|
| 350 |
},
|
| 351 |
{
|
| 352 |
-
"epoch":
|
| 353 |
-
"eval_loss": 0.
|
| 354 |
"eval_max_distance": 1,
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
-
"eval_runtime": 0.
|
| 357 |
-
"eval_samples_per_second":
|
| 358 |
-
"eval_steps_per_second":
|
| 359 |
-
"step":
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch":
|
| 363 |
-
"learning_rate": 8.
|
| 364 |
-
"loss": 0.
|
| 365 |
-
"step":
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch":
|
| 369 |
-
"learning_rate": 8.
|
| 370 |
-
"loss": 0.
|
| 371 |
-
"step":
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch":
|
| 375 |
-
"learning_rate": 8.
|
| 376 |
-
"loss": 0.
|
| 377 |
-
"step":
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch":
|
| 381 |
-
"learning_rate": 8.
|
| 382 |
-
"loss": 0.
|
| 383 |
-
"step":
|
| 384 |
},
|
| 385 |
{
|
| 386 |
-
"epoch":
|
| 387 |
-
"learning_rate": 8.
|
| 388 |
-
"loss": 0.
|
| 389 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch":
|
| 393 |
-
"learning_rate": 8.
|
| 394 |
-
"loss": 0.
|
| 395 |
-
"step":
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch":
|
| 399 |
-
"learning_rate":
|
| 400 |
-
"loss": 0.
|
| 401 |
-
"step":
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch":
|
| 405 |
-
"learning_rate":
|
| 406 |
-
"loss": 0.
|
| 407 |
-
"step":
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"epoch":
|
| 411 |
-
"learning_rate":
|
| 412 |
-
"loss": 0.
|
| 413 |
-
"step":
|
| 414 |
},
|
| 415 |
{
|
| 416 |
-
"epoch":
|
| 417 |
-
"learning_rate":
|
| 418 |
-
"loss": 0.
|
| 419 |
-
"step":
|
| 420 |
},
|
| 421 |
{
|
| 422 |
-
"epoch":
|
| 423 |
-
"eval_loss": 0.
|
| 424 |
"eval_max_distance": 1,
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
-
"eval_runtime": 0.
|
| 427 |
-
"eval_samples_per_second":
|
| 428 |
-
"eval_steps_per_second":
|
| 429 |
-
"step":
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch":
|
| 433 |
-
"learning_rate":
|
| 434 |
-
"loss": 0.
|
| 435 |
-
"step":
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch":
|
| 439 |
-
"learning_rate":
|
| 440 |
-
"loss": 0.
|
| 441 |
-
"step":
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch":
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 0.
|
| 447 |
-
"step":
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch": 6
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
-
"step":
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch":
|
| 457 |
-
"learning_rate":
|
| 458 |
-
"loss": 0.
|
| 459 |
-
"step":
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch":
|
| 463 |
-
"
|
| 464 |
-
"
|
| 465 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch":
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 0.
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch":
|
| 475 |
-
"learning_rate": 7.
|
| 476 |
-
"loss": 0.
|
| 477 |
-
"step":
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch":
|
| 481 |
-
"learning_rate": 7.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 482 |
"loss": 0.0009,
|
| 483 |
-
"step":
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch":
|
| 487 |
-
"learning_rate": 7.
|
| 488 |
-
"loss": 0.
|
| 489 |
-
"step":
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch":
|
| 493 |
-
"eval_loss": 0.
|
| 494 |
"eval_max_distance": 1,
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
-
"eval_runtime": 0.
|
| 497 |
-
"eval_samples_per_second":
|
| 498 |
-
"eval_steps_per_second": 26.
|
| 499 |
-
"step":
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch":
|
| 503 |
-
"learning_rate": 7.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 504 |
"loss": 0.0027,
|
| 505 |
-
"step":
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch":
|
| 509 |
-
"learning_rate": 7.
|
| 510 |
-
"loss": 0.
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch":
|
| 515 |
-
"learning_rate": 7.
|
| 516 |
-
"loss": 0.
|
| 517 |
-
"step":
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch":
|
| 521 |
-
"
|
| 522 |
-
"
|
| 523 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 524 |
},
|
| 525 |
{
|
| 526 |
-
"epoch":
|
| 527 |
-
"learning_rate":
|
| 528 |
-
"loss": 0.
|
| 529 |
-
"step":
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch":
|
| 533 |
-
"learning_rate":
|
| 534 |
-
"loss": 0.
|
| 535 |
-
"step":
|
| 536 |
},
|
| 537 |
{
|
| 538 |
-
"epoch":
|
| 539 |
-
"learning_rate":
|
| 540 |
-
"loss": 0.
|
| 541 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch":
|
| 545 |
-
"learning_rate":
|
| 546 |
"loss": 0.0017,
|
| 547 |
-
"step":
|
| 548 |
},
|
| 549 |
{
|
| 550 |
-
"epoch":
|
| 551 |
-
"
|
| 552 |
-
"
|
| 553 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch":
|
| 557 |
-
"learning_rate":
|
| 558 |
-
"loss": 0.
|
| 559 |
-
"step":
|
| 560 |
},
|
| 561 |
{
|
| 562 |
-
"epoch":
|
| 563 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 564 |
"eval_max_distance": 1,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
-
"eval_runtime": 0.
|
| 567 |
-
"eval_samples_per_second":
|
| 568 |
-
"eval_steps_per_second":
|
| 569 |
-
"step":
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch":
|
| 573 |
-
"learning_rate": 6.
|
| 574 |
-
"loss": 0.
|
| 575 |
-
"step":
|
| 576 |
},
|
| 577 |
{
|
| 578 |
-
"epoch":
|
| 579 |
-
"learning_rate": 6.
|
| 580 |
-
"loss": 0.
|
| 581 |
-
"step":
|
| 582 |
},
|
| 583 |
{
|
| 584 |
-
"epoch":
|
| 585 |
-
"learning_rate": 6.
|
| 586 |
-
"loss": 0.
|
| 587 |
-
"step":
|
| 588 |
},
|
| 589 |
{
|
| 590 |
-
"epoch":
|
| 591 |
-
"learning_rate": 6.
|
| 592 |
-
"loss": 0.
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
-
"epoch":
|
| 597 |
-
"learning_rate": 6.
|
| 598 |
-
"loss": 0.
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
-
"epoch":
|
| 603 |
-
"
|
| 604 |
-
"
|
| 605 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 606 |
},
|
| 607 |
{
|
| 608 |
-
"epoch":
|
| 609 |
-
"learning_rate": 6.
|
| 610 |
-
"loss": 0.
|
| 611 |
-
"step":
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"learning_rate": 6.
|
| 616 |
-
"loss": 0.
|
| 617 |
-
"step":
|
| 618 |
},
|
| 619 |
{
|
| 620 |
-
"epoch":
|
| 621 |
-
"learning_rate": 6.
|
| 622 |
"loss": 0.0006,
|
| 623 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 624 |
},
|
| 625 |
{
|
| 626 |
-
"epoch":
|
| 627 |
-
"learning_rate": 6.
|
| 628 |
-
"loss": 0.
|
| 629 |
-
"step":
|
| 630 |
},
|
| 631 |
{
|
| 632 |
-
"epoch":
|
| 633 |
-
"eval_loss": 0.
|
| 634 |
"eval_max_distance": 1,
|
| 635 |
"eval_mean_distance": 0,
|
| 636 |
-
"eval_runtime": 0.
|
| 637 |
-
"eval_samples_per_second":
|
| 638 |
-
"eval_steps_per_second": 26.
|
| 639 |
-
"step":
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"learning_rate": 6.
|
| 644 |
-
"loss": 0.
|
| 645 |
-
"step":
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch":
|
| 649 |
-
"learning_rate": 6.
|
| 650 |
-
"loss": 0.
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch":
|
| 655 |
-
"learning_rate":
|
| 656 |
"loss": 0.0011,
|
| 657 |
-
"step":
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch":
|
| 661 |
-
"learning_rate":
|
| 662 |
-
"loss": 0.
|
| 663 |
-
"step":
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch":
|
| 667 |
-
"learning_rate":
|
| 668 |
-
"loss": 0.
|
| 669 |
-
"step":
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch":
|
| 673 |
-
"
|
| 674 |
-
"
|
| 675 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 676 |
},
|
| 677 |
{
|
| 678 |
-
"epoch":
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
-
"step":
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch":
|
| 685 |
-
"learning_rate":
|
| 686 |
-
"loss": 0.
|
| 687 |
-
"step":
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"epoch":
|
| 691 |
-
"learning_rate": 5.
|
| 692 |
-
"loss": 0.
|
| 693 |
-
"step":
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch":
|
| 697 |
-
"learning_rate": 5.
|
| 698 |
-
"loss": 0.
|
| 699 |
-
"step":
|
| 700 |
},
|
| 701 |
{
|
| 702 |
-
"epoch":
|
| 703 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 704 |
"eval_max_distance": 1,
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
-
"eval_runtime": 0.
|
| 707 |
-
"eval_samples_per_second":
|
| 708 |
-
"eval_steps_per_second": 26.
|
| 709 |
-
"step":
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch":
|
| 713 |
-
"learning_rate": 5.
|
| 714 |
-
"loss": 0.
|
| 715 |
-
"step":
|
| 716 |
},
|
| 717 |
{
|
| 718 |
-
"epoch":
|
| 719 |
-
"learning_rate": 5.
|
| 720 |
-
"loss": 0.
|
| 721 |
-
"step":
|
| 722 |
},
|
| 723 |
{
|
| 724 |
-
"epoch":
|
| 725 |
-
"learning_rate": 5.
|
| 726 |
-
"loss": 0.
|
| 727 |
-
"step":
|
| 728 |
},
|
| 729 |
{
|
| 730 |
-
"epoch":
|
| 731 |
-
"learning_rate": 5.
|
| 732 |
-
"loss": 0.
|
| 733 |
-
"step":
|
| 734 |
},
|
| 735 |
{
|
| 736 |
-
"epoch":
|
| 737 |
-
"learning_rate": 5.
|
| 738 |
-
"loss": 0.
|
| 739 |
-
"step":
|
| 740 |
},
|
| 741 |
{
|
| 742 |
-
"epoch":
|
| 743 |
-
"
|
| 744 |
-
"
|
| 745 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 746 |
},
|
| 747 |
{
|
| 748 |
-
"epoch":
|
| 749 |
-
"learning_rate": 5.
|
| 750 |
-
"loss": 0.
|
| 751 |
-
"step":
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch":
|
| 755 |
-
"learning_rate": 5.
|
| 756 |
-
"loss": 0.
|
| 757 |
-
"step":
|
| 758 |
},
|
| 759 |
{
|
| 760 |
-
"epoch":
|
| 761 |
-
"learning_rate": 5.
|
| 762 |
-
"loss": 0.
|
| 763 |
-
"step":
|
| 764 |
},
|
| 765 |
{
|
| 766 |
-
"epoch":
|
| 767 |
-
"learning_rate": 5.
|
| 768 |
-
"loss": 0.
|
| 769 |
-
"step":
|
| 770 |
},
|
| 771 |
{
|
| 772 |
-
"epoch":
|
| 773 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 774 |
"eval_max_distance": 1,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
-
"eval_runtime": 0.
|
| 777 |
-
"eval_samples_per_second":
|
| 778 |
-
"eval_steps_per_second":
|
| 779 |
-
"step":
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch":
|
| 783 |
-
"learning_rate":
|
| 784 |
-
"loss": 0.
|
| 785 |
-
"step":
|
| 786 |
},
|
| 787 |
{
|
| 788 |
-
"epoch":
|
| 789 |
-
"learning_rate":
|
| 790 |
-
"loss": 0.
|
| 791 |
-
"step":
|
| 792 |
},
|
| 793 |
{
|
| 794 |
-
"epoch":
|
| 795 |
-
"learning_rate":
|
| 796 |
-
"loss": 0.
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch":
|
| 801 |
-
"learning_rate":
|
| 802 |
-
"loss": 0.
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch":
|
| 807 |
-
"learning_rate":
|
| 808 |
-
"loss": 0.
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch":
|
| 813 |
-
"
|
| 814 |
-
"
|
| 815 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 816 |
},
|
| 817 |
{
|
| 818 |
-
"epoch":
|
| 819 |
-
"learning_rate": 4.
|
| 820 |
-
"loss": 0.
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch":
|
| 825 |
-
"learning_rate": 4.
|
| 826 |
-
"loss": 0.
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch":
|
| 831 |
-
"learning_rate": 4.
|
| 832 |
-
"loss": 0.
|
| 833 |
-
"step":
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch":
|
| 837 |
-
"learning_rate": 4.
|
| 838 |
-
"loss": 0.
|
| 839 |
-
"step":
|
| 840 |
},
|
| 841 |
{
|
| 842 |
-
"epoch":
|
| 843 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 844 |
"eval_max_distance": 1,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
-
"eval_runtime": 0.
|
| 847 |
-
"eval_samples_per_second":
|
| 848 |
-
"eval_steps_per_second":
|
| 849 |
-
"step":
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch":
|
| 853 |
-
"learning_rate": 4.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 854 |
"loss": 0.0006,
|
| 855 |
-
"step":
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch":
|
| 859 |
-
"learning_rate": 4.
|
| 860 |
-
"loss": 0.
|
| 861 |
-
"step":
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch":
|
| 865 |
-
"learning_rate": 4.
|
| 866 |
-
"loss": 0.
|
| 867 |
-
"step":
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch":
|
| 871 |
-
"learning_rate": 4.
|
| 872 |
-
"loss": 0.
|
| 873 |
-
"step":
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch":
|
| 877 |
-
"
|
| 878 |
-
"
|
| 879 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 880 |
},
|
| 881 |
{
|
| 882 |
-
"epoch":
|
| 883 |
-
"learning_rate": 4.
|
| 884 |
-
"loss": 0.
|
| 885 |
-
"step":
|
| 886 |
},
|
| 887 |
{
|
| 888 |
-
"epoch":
|
| 889 |
-
"learning_rate": 4.
|
| 890 |
-
"loss": 0.
|
| 891 |
-
"step":
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch":
|
| 895 |
-
"learning_rate": 4.
|
| 896 |
-
"loss": 0.
|
| 897 |
-
"step":
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch":
|
| 901 |
-
"learning_rate":
|
| 902 |
"loss": 0.0001,
|
| 903 |
-
"step":
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch":
|
| 907 |
-
"learning_rate":
|
| 908 |
-
"loss": 0.
|
| 909 |
-
"step":
|
| 910 |
},
|
| 911 |
{
|
| 912 |
-
"epoch":
|
| 913 |
-
"eval_loss": 0.
|
| 914 |
"eval_max_distance": 1,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
-
"eval_runtime": 0.
|
| 917 |
-
"eval_samples_per_second":
|
| 918 |
-
"eval_steps_per_second":
|
| 919 |
-
"step":
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch":
|
| 923 |
-
"learning_rate":
|
| 924 |
"loss": 0.0006,
|
| 925 |
-
"step":
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"epoch":
|
| 929 |
-
"learning_rate":
|
| 930 |
-
"loss": 0.
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch":
|
| 935 |
-
"learning_rate":
|
| 936 |
-
"loss": 0.
|
| 937 |
-
"step":
|
| 938 |
},
|
| 939 |
{
|
| 940 |
-
"epoch":
|
| 941 |
-
"learning_rate": 3.
|
| 942 |
-
"loss": 0.
|
| 943 |
-
"step":
|
| 944 |
},
|
| 945 |
{
|
| 946 |
-
"epoch":
|
| 947 |
-
"learning_rate": 3.
|
| 948 |
"loss": 0.0014,
|
| 949 |
-
"step":
|
| 950 |
},
|
| 951 |
{
|
| 952 |
-
"epoch":
|
| 953 |
-
"
|
| 954 |
-
"
|
| 955 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"epoch":
|
| 959 |
-
"learning_rate": 3.
|
| 960 |
-
"loss": 0.
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch":
|
| 965 |
-
"learning_rate": 3.
|
| 966 |
-
"loss": 0.
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch":
|
| 971 |
-
"learning_rate": 3.
|
| 972 |
-
"loss": 0.
|
| 973 |
-
"step":
|
| 974 |
},
|
| 975 |
{
|
| 976 |
-
"epoch":
|
| 977 |
-
"learning_rate": 3.
|
| 978 |
-
"loss": 0.
|
| 979 |
-
"step":
|
| 980 |
},
|
| 981 |
{
|
| 982 |
-
"epoch":
|
| 983 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 984 |
"eval_max_distance": 1,
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
-
"eval_runtime": 0.
|
| 987 |
-
"eval_samples_per_second":
|
| 988 |
-
"eval_steps_per_second":
|
| 989 |
-
"step":
|
| 990 |
},
|
| 991 |
{
|
| 992 |
-
"epoch":
|
| 993 |
-
"learning_rate": 3.
|
| 994 |
-
"loss": 0.
|
| 995 |
-
"step":
|
| 996 |
},
|
| 997 |
{
|
| 998 |
-
"epoch":
|
| 999 |
-
"learning_rate": 3.
|
| 1000 |
-
"loss": 0.
|
| 1001 |
-
"step":
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
-
"epoch":
|
| 1005 |
-
"learning_rate": 3.
|
| 1006 |
-
"loss": 0.
|
| 1007 |
-
"step":
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
-
"epoch":
|
| 1011 |
-
"learning_rate": 3.
|
| 1012 |
-
"loss": 0.
|
| 1013 |
-
"step":
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch":
|
| 1017 |
-
"learning_rate": 3.
|
| 1018 |
-
"loss": 0.
|
| 1019 |
-
"step":
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
-
"epoch":
|
| 1023 |
-
"
|
| 1024 |
-
"
|
| 1025 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"epoch":
|
| 1029 |
-
"learning_rate":
|
| 1030 |
-
"loss": 0.
|
| 1031 |
-
"step":
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
-
"epoch":
|
| 1035 |
-
"learning_rate":
|
| 1036 |
-
"loss": 0.
|
| 1037 |
-
"step":
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch":
|
| 1041 |
-
"learning_rate":
|
| 1042 |
-
"loss": 0.
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch":
|
| 1047 |
-
"learning_rate":
|
| 1048 |
-
"loss": 0.
|
| 1049 |
-
"step":
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
-
"epoch":
|
| 1053 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1054 |
"eval_max_distance": 1,
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
-
"eval_runtime": 0.
|
| 1057 |
-
"eval_samples_per_second":
|
| 1058 |
-
"eval_steps_per_second":
|
| 1059 |
-
"step":
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
-
"epoch":
|
| 1063 |
-
"learning_rate":
|
| 1064 |
"loss": 0.0003,
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch":
|
| 1069 |
-
"learning_rate": 2.
|
| 1070 |
"loss": 0.0002,
|
| 1071 |
-
"step":
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch":
|
| 1075 |
-
"learning_rate": 2.
|
| 1076 |
-
"loss": 0.
|
| 1077 |
-
"step":
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch":
|
| 1081 |
-
"learning_rate": 2.
|
| 1082 |
-
"loss": 0.
|
| 1083 |
-
"step":
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch":
|
| 1087 |
-
"learning_rate": 2.
|
| 1088 |
-
"loss": 0.
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch":
|
| 1093 |
-
"
|
| 1094 |
-
"
|
| 1095 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch":
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
-
"loss": 0.
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch":
|
| 1105 |
-
"learning_rate": 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1106 |
"loss": 0.0001,
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch":
|
| 1111 |
-
"learning_rate": 2.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch":
|
| 1117 |
-
"learning_rate": 2.
|
| 1118 |
-
"loss": 0.
|
| 1119 |
-
"step":
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
-
"epoch":
|
| 1123 |
-
"eval_loss": 0.
|
| 1124 |
"eval_max_distance": 1,
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
-
"eval_runtime": 0.
|
| 1127 |
-
"eval_samples_per_second":
|
| 1128 |
-
"eval_steps_per_second":
|
| 1129 |
-
"step":
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
-
"epoch":
|
| 1133 |
-
"learning_rate": 2.
|
| 1134 |
-
"loss": 0.
|
| 1135 |
-
"step":
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
-
"epoch":
|
| 1139 |
-
"learning_rate": 2.
|
| 1140 |
-
"loss": 0.
|
| 1141 |
-
"step":
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
-
"epoch":
|
| 1145 |
-
"learning_rate": 2.
|
| 1146 |
-
"loss": 0.
|
| 1147 |
-
"step":
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
-
"epoch":
|
| 1151 |
-
"learning_rate": 2.
|
| 1152 |
-
"loss": 0.
|
| 1153 |
-
"step":
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"epoch":
|
| 1157 |
-
"learning_rate":
|
| 1158 |
"loss": 0.0003,
|
| 1159 |
-
"step":
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
-
"epoch":
|
| 1163 |
-
"
|
| 1164 |
-
"
|
| 1165 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
-
"epoch":
|
| 1169 |
-
"learning_rate":
|
| 1170 |
-
"loss": 0.
|
| 1171 |
-
"step":
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
-
"epoch":
|
| 1175 |
-
"learning_rate":
|
| 1176 |
-
"loss": 0.
|
| 1177 |
-
"step":
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
-
"epoch":
|
| 1181 |
-
"learning_rate":
|
| 1182 |
-
"loss": 0.
|
| 1183 |
-
"step":
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
-
"epoch":
|
| 1187 |
-
"learning_rate":
|
| 1188 |
"loss": 0.0002,
|
| 1189 |
-
"step":
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
-
"epoch":
|
| 1193 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1194 |
"eval_max_distance": 1,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
-
"eval_runtime": 0.
|
| 1197 |
-
"eval_samples_per_second":
|
| 1198 |
-
"eval_steps_per_second":
|
| 1199 |
-
"step":
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
-
"epoch":
|
| 1203 |
-
"learning_rate": 1.
|
| 1204 |
-
"loss": 0.
|
| 1205 |
-
"step":
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
-
"epoch":
|
| 1209 |
-
"learning_rate": 1.
|
| 1210 |
-
"loss": 0.
|
| 1211 |
-
"step":
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
-
"epoch":
|
| 1215 |
-
"learning_rate": 1.
|
| 1216 |
-
"loss": 0.
|
| 1217 |
-
"step":
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
-
"epoch":
|
| 1221 |
-
"learning_rate": 1.
|
| 1222 |
-
"loss": 0.
|
| 1223 |
-
"step":
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
-
"epoch":
|
| 1227 |
-
"learning_rate": 1.
|
| 1228 |
-
"loss": 0.
|
| 1229 |
-
"step":
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
-
"epoch":
|
| 1233 |
-
"
|
| 1234 |
-
"
|
| 1235 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
-
"epoch":
|
| 1239 |
-
"learning_rate": 1.
|
| 1240 |
-
"loss": 0.
|
| 1241 |
-
"step":
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
-
"epoch":
|
| 1245 |
-
"learning_rate": 1.
|
| 1246 |
-
"loss": 0.
|
| 1247 |
-
"step":
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
-
"epoch":
|
| 1251 |
-
"learning_rate": 1.
|
| 1252 |
-
"loss": 0.
|
| 1253 |
-
"step":
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
-
"epoch":
|
| 1257 |
-
"learning_rate": 1.
|
| 1258 |
-
"loss": 0.
|
| 1259 |
-
"step":
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
-
"epoch":
|
| 1263 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1264 |
"eval_max_distance": 1,
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
-
"eval_runtime": 0.
|
| 1267 |
-
"eval_samples_per_second":
|
| 1268 |
-
"eval_steps_per_second":
|
| 1269 |
-
"step":
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
-
"epoch":
|
| 1273 |
-
"learning_rate": 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1274 |
"loss": 0.0005,
|
| 1275 |
-
"step":
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
-
"epoch":
|
| 1279 |
-
"learning_rate": 1.
|
| 1280 |
-
"loss": 0.
|
| 1281 |
-
"step":
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
-
"epoch":
|
| 1285 |
-
"learning_rate":
|
| 1286 |
-
"loss": 0.
|
| 1287 |
-
"step":
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
-
"epoch":
|
| 1291 |
-
"learning_rate":
|
| 1292 |
-
"loss": 0.
|
| 1293 |
-
"step":
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
-
"epoch":
|
| 1297 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1298 |
"loss": 0.0003,
|
| 1299 |
-
"step":
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
-
"epoch":
|
| 1303 |
-
"learning_rate":
|
| 1304 |
-
"loss": 0.
|
| 1305 |
-
"step":
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
-
"epoch":
|
| 1309 |
-
"learning_rate":
|
| 1310 |
-
"loss": 0.
|
| 1311 |
-
"step":
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch":
|
| 1315 |
-
"learning_rate":
|
| 1316 |
-
"loss": 0.
|
| 1317 |
-
"step":
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch":
|
| 1321 |
-
"learning_rate":
|
| 1322 |
-
"loss": 0.
|
| 1323 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch":
|
| 1327 |
-
"learning_rate":
|
| 1328 |
"loss": 0.0001,
|
| 1329 |
-
"step":
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
-
"epoch":
|
| 1333 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1334 |
"eval_max_distance": 1,
|
| 1335 |
"eval_mean_distance": 0,
|
| 1336 |
-
"eval_runtime": 0.
|
| 1337 |
-
"eval_samples_per_second":
|
| 1338 |
-
"eval_steps_per_second":
|
| 1339 |
-
"step":
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
-
"epoch":
|
| 1343 |
-
"learning_rate": 5.
|
| 1344 |
-
"loss": 0.
|
| 1345 |
-
"step":
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
-
"epoch":
|
| 1349 |
-
"learning_rate": 4.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1350 |
"loss": 0.0001,
|
| 1351 |
-
"step":
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
-
"epoch":
|
| 1355 |
-
"learning_rate":
|
| 1356 |
-
"loss": 0.
|
| 1357 |
-
"step":
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
-
"epoch":
|
| 1361 |
-
"learning_rate": 3.
|
| 1362 |
-
"loss": 0.
|
| 1363 |
-
"step":
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
-
"epoch":
|
| 1367 |
-
"
|
| 1368 |
-
"
|
| 1369 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
-
"epoch":
|
| 1373 |
-
"learning_rate": 2.
|
| 1374 |
-
"loss": 0.
|
| 1375 |
-
"step":
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
-
"epoch":
|
| 1379 |
-
"learning_rate":
|
| 1380 |
-
"loss": 0.
|
| 1381 |
-
"step":
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
-
"epoch":
|
| 1385 |
-
"learning_rate": 1.
|
| 1386 |
"loss": 0.0001,
|
| 1387 |
-
"step":
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
-
"epoch":
|
| 1391 |
-
"learning_rate":
|
| 1392 |
-
"loss": 0.
|
| 1393 |
-
"step":
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
-
"epoch":
|
| 1397 |
-
"learning_rate":
|
| 1398 |
-
"loss": 0.
|
| 1399 |
-
"step":
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
-
"epoch":
|
| 1403 |
-
"eval_loss": 0.
|
| 1404 |
"eval_max_distance": 1,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
-
"eval_runtime": 0.
|
| 1407 |
-
"eval_samples_per_second":
|
| 1408 |
-
"eval_steps_per_second":
|
| 1409 |
-
"step":
|
| 1410 |
-
},
|
| 1411 |
-
{
|
| 1412 |
-
"epoch":
|
| 1413 |
-
"step":
|
| 1414 |
-
"total_flos":
|
| 1415 |
-
"train_loss": 0.
|
| 1416 |
-
"train_runtime":
|
| 1417 |
-
"train_samples_per_second":
|
| 1418 |
-
"train_steps_per_second": 10.
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
-
"logging_steps":
|
| 1422 |
-
"max_steps":
|
| 1423 |
-
"num_train_epochs":
|
| 1424 |
-
"save_steps":
|
| 1425 |
-
"total_flos":
|
| 1426 |
"trial_name": null,
|
| 1427 |
"trial_params": null
|
| 1428 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 106560,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 9.384384384384385e-09,
|
| 14 |
+
"loss": 30.0191,
|
| 15 |
"step": 1
|
| 16 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
{
|
| 18 |
"epoch": 0.2,
|
| 19 |
+
"learning_rate": 5.001876876876877e-06,
|
| 20 |
+
"loss": 28.4983,
|
| 21 |
+
"step": 533
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.4,
|
| 25 |
+
"learning_rate": 1.0003753753753754e-05,
|
| 26 |
+
"loss": 21.5164,
|
| 27 |
+
"step": 1066
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.6,
|
| 31 |
+
"learning_rate": 1.5005630630630632e-05,
|
| 32 |
+
"loss": 7.132,
|
| 33 |
+
"step": 1599
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.8,
|
| 37 |
+
"learning_rate": 2.000750750750751e-05,
|
| 38 |
+
"loss": 0.8541,
|
| 39 |
+
"step": 2132
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 1.0,
|
| 43 |
+
"eval_loss": 0.3403850197792053,
|
| 44 |
"eval_max_distance": 1,
|
| 45 |
"eval_mean_distance": 0,
|
| 46 |
+
"eval_runtime": 1.1154,
|
| 47 |
+
"eval_samples_per_second": 320.968,
|
| 48 |
+
"eval_steps_per_second": 21.517,
|
| 49 |
"step": 2664
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 1.0,
|
| 53 |
+
"learning_rate": 2.500938438438439e-05,
|
| 54 |
+
"loss": 0.3348,
|
| 55 |
+
"step": 2665
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
},
|
| 57 |
{
|
| 58 |
"epoch": 1.2,
|
| 59 |
+
"learning_rate": 3.0011261261261263e-05,
|
| 60 |
+
"loss": 0.5279,
|
| 61 |
+
"step": 3198
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 1.4,
|
| 65 |
+
"learning_rate": 3.501313813813814e-05,
|
| 66 |
+
"loss": 0.2294,
|
| 67 |
+
"step": 3731
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"epoch": 1.6,
|
| 71 |
+
"learning_rate": 4.001501501501502e-05,
|
| 72 |
+
"loss": 0.0605,
|
| 73 |
+
"step": 4264
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 1.8,
|
| 77 |
+
"learning_rate": 4.5016891891891895e-05,
|
| 78 |
+
"loss": 0.0451,
|
| 79 |
+
"step": 4797
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 2.0,
|
| 83 |
+
"eval_loss": 0.060470160096883774,
|
| 84 |
"eval_max_distance": 1,
|
| 85 |
"eval_mean_distance": 0,
|
| 86 |
+
"eval_runtime": 0.9182,
|
| 87 |
+
"eval_samples_per_second": 389.888,
|
| 88 |
+
"eval_steps_per_second": 26.138,
|
| 89 |
"step": 5328
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 2.0,
|
| 93 |
+
"learning_rate": 5.001876876876878e-05,
|
| 94 |
+
"loss": 0.0605,
|
| 95 |
+
"step": 5330
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 2.2,
|
| 99 |
+
"learning_rate": 5.502064564564565e-05,
|
| 100 |
+
"loss": 0.025,
|
| 101 |
+
"step": 5863
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 2.4,
|
| 105 |
+
"learning_rate": 6.0022522522522526e-05,
|
| 106 |
+
"loss": 0.0193,
|
| 107 |
+
"step": 6396
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 2.6,
|
| 111 |
+
"learning_rate": 6.502439939939941e-05,
|
| 112 |
+
"loss": 0.0153,
|
| 113 |
+
"step": 6929
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 2.8,
|
| 117 |
+
"learning_rate": 7.002627627627628e-05,
|
| 118 |
+
"loss": 0.0112,
|
| 119 |
+
"step": 7462
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 3.0,
|
| 123 |
+
"eval_loss": 0.04112406447529793,
|
| 124 |
+
"eval_max_distance": 1,
|
| 125 |
+
"eval_mean_distance": 0,
|
| 126 |
+
"eval_runtime": 0.9146,
|
| 127 |
+
"eval_samples_per_second": 391.418,
|
| 128 |
+
"eval_steps_per_second": 26.24,
|
| 129 |
+
"step": 7992
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.0,
|
| 133 |
+
"learning_rate": 7.502815315315315e-05,
|
| 134 |
"loss": 0.0109,
|
| 135 |
+
"step": 7995
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 3.2,
|
| 139 |
+
"learning_rate": 8.003003003003004e-05,
|
| 140 |
+
"loss": 0.0095,
|
| 141 |
+
"step": 8528
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 3.4,
|
| 145 |
+
"learning_rate": 8.50319069069069e-05,
|
| 146 |
+
"loss": 0.012,
|
| 147 |
+
"step": 9061
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 3.6,
|
| 151 |
+
"learning_rate": 9.003378378378379e-05,
|
| 152 |
+
"loss": 0.0223,
|
| 153 |
+
"step": 9594
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 3.8,
|
| 157 |
+
"learning_rate": 9.503566066066066e-05,
|
| 158 |
+
"loss": 0.0068,
|
| 159 |
+
"step": 10127
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"eval_loss": 0.020507752895355225,
|
| 164 |
"eval_max_distance": 1,
|
| 165 |
"eval_mean_distance": 0,
|
| 166 |
+
"eval_runtime": 0.9253,
|
| 167 |
+
"eval_samples_per_second": 386.912,
|
| 168 |
+
"eval_steps_per_second": 25.938,
|
| 169 |
+
"step": 10656
|
| 170 |
},
|
| 171 |
{
|
| 172 |
+
"epoch": 4.0,
|
| 173 |
+
"learning_rate": 9.999582916249583e-05,
|
| 174 |
+
"loss": 0.0077,
|
| 175 |
+
"step": 10660
|
| 176 |
},
|
| 177 |
{
|
| 178 |
+
"epoch": 4.2,
|
| 179 |
+
"learning_rate": 9.944006506506507e-05,
|
| 180 |
+
"loss": 0.0058,
|
| 181 |
+
"step": 11193
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 4.4,
|
| 185 |
+
"learning_rate": 9.88843009676343e-05,
|
| 186 |
+
"loss": 0.0072,
|
| 187 |
+
"step": 11726
|
| 188 |
},
|
| 189 |
{
|
| 190 |
+
"epoch": 4.6,
|
| 191 |
+
"learning_rate": 9.832853687020355e-05,
|
| 192 |
+
"loss": 0.0097,
|
| 193 |
+
"step": 12259
|
| 194 |
},
|
| 195 |
{
|
| 196 |
+
"epoch": 4.8,
|
| 197 |
+
"learning_rate": 9.777277277277279e-05,
|
| 198 |
+
"loss": 0.007,
|
| 199 |
+
"step": 12792
|
| 200 |
},
|
| 201 |
{
|
| 202 |
+
"epoch": 5.0,
|
| 203 |
+
"eval_loss": 0.02420434169471264,
|
| 204 |
+
"eval_max_distance": 1,
|
| 205 |
+
"eval_mean_distance": 0,
|
| 206 |
+
"eval_runtime": 0.9141,
|
| 207 |
+
"eval_samples_per_second": 391.658,
|
| 208 |
+
"eval_steps_per_second": 26.256,
|
| 209 |
+
"step": 13320
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 5.0,
|
| 213 |
+
"learning_rate": 9.721700867534201e-05,
|
| 214 |
+
"loss": 0.0049,
|
| 215 |
+
"step": 13325
|
| 216 |
},
|
| 217 |
{
|
| 218 |
+
"epoch": 5.2,
|
| 219 |
+
"learning_rate": 9.666124457791124e-05,
|
| 220 |
+
"loss": 0.005,
|
| 221 |
+
"step": 13858
|
| 222 |
},
|
| 223 |
{
|
| 224 |
+
"epoch": 5.4,
|
| 225 |
+
"learning_rate": 9.610548048048048e-05,
|
| 226 |
+
"loss": 0.0035,
|
| 227 |
+
"step": 14391
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 5.6,
|
| 231 |
+
"learning_rate": 9.554971638304973e-05,
|
| 232 |
+
"loss": 0.0061,
|
| 233 |
+
"step": 14924
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 5.8,
|
| 237 |
+
"learning_rate": 9.499395228561896e-05,
|
| 238 |
+
"loss": 0.0022,
|
| 239 |
+
"step": 15457
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 6.0,
|
| 243 |
+
"eval_loss": 0.027173461392521858,
|
| 244 |
"eval_max_distance": 1,
|
| 245 |
"eval_mean_distance": 0,
|
| 246 |
+
"eval_runtime": 0.9101,
|
| 247 |
+
"eval_samples_per_second": 393.378,
|
| 248 |
+
"eval_steps_per_second": 26.372,
|
| 249 |
+
"step": 15984
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 6.0,
|
| 253 |
+
"learning_rate": 9.44381881881882e-05,
|
| 254 |
+
"loss": 0.0048,
|
| 255 |
+
"step": 15990
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 6.2,
|
| 259 |
+
"learning_rate": 9.388242409075743e-05,
|
| 260 |
+
"loss": 0.0053,
|
| 261 |
+
"step": 16523
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 6.4,
|
| 265 |
+
"learning_rate": 9.332665999332665e-05,
|
| 266 |
+
"loss": 0.005,
|
| 267 |
+
"step": 17056
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 6.6,
|
| 271 |
+
"learning_rate": 9.27708958958959e-05,
|
| 272 |
"loss": 0.0034,
|
| 273 |
+
"step": 17589
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 6.8,
|
| 277 |
+
"learning_rate": 9.221513179846514e-05,
|
| 278 |
+
"loss": 0.0054,
|
| 279 |
+
"step": 18122
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 7.0,
|
| 283 |
+
"eval_loss": 0.008011276833713055,
|
| 284 |
+
"eval_max_distance": 1,
|
| 285 |
+
"eval_mean_distance": 0,
|
| 286 |
+
"eval_runtime": 0.9187,
|
| 287 |
+
"eval_samples_per_second": 389.697,
|
| 288 |
+
"eval_steps_per_second": 26.125,
|
| 289 |
+
"step": 18648
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 7.0,
|
| 293 |
+
"learning_rate": 9.165936770103437e-05,
|
| 294 |
+
"loss": 0.0036,
|
| 295 |
+
"step": 18655
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 7.2,
|
| 299 |
+
"learning_rate": 9.110360360360361e-05,
|
| 300 |
+
"loss": 0.002,
|
| 301 |
+
"step": 19188
|
| 302 |
},
|
| 303 |
{
|
| 304 |
+
"epoch": 7.4,
|
| 305 |
+
"learning_rate": 9.054783950617284e-05,
|
| 306 |
+
"loss": 0.0029,
|
| 307 |
+
"step": 19721
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 7.6,
|
| 311 |
+
"learning_rate": 8.999207540874208e-05,
|
| 312 |
+
"loss": 0.0031,
|
| 313 |
+
"step": 20254
|
| 314 |
},
|
| 315 |
{
|
| 316 |
+
"epoch": 7.8,
|
| 317 |
+
"learning_rate": 8.943631131131131e-05,
|
| 318 |
+
"loss": 0.0036,
|
| 319 |
+
"step": 20787
|
| 320 |
},
|
| 321 |
{
|
| 322 |
+
"epoch": 8.0,
|
| 323 |
+
"eval_loss": 0.025212394073605537,
|
| 324 |
"eval_max_distance": 1,
|
| 325 |
"eval_mean_distance": 0,
|
| 326 |
+
"eval_runtime": 0.9136,
|
| 327 |
+
"eval_samples_per_second": 391.872,
|
| 328 |
+
"eval_steps_per_second": 26.271,
|
| 329 |
+
"step": 21312
|
| 330 |
},
|
| 331 |
{
|
| 332 |
+
"epoch": 8.0,
|
| 333 |
+
"learning_rate": 8.888054721388055e-05,
|
| 334 |
+
"loss": 0.0022,
|
| 335 |
+
"step": 21320
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 8.2,
|
| 339 |
+
"learning_rate": 8.832478311644978e-05,
|
| 340 |
+
"loss": 0.0021,
|
| 341 |
+
"step": 21853
|
| 342 |
},
|
| 343 |
{
|
| 344 |
+
"epoch": 8.4,
|
| 345 |
+
"learning_rate": 8.776901901901903e-05,
|
| 346 |
+
"loss": 0.0016,
|
| 347 |
+
"step": 22386
|
| 348 |
},
|
| 349 |
{
|
| 350 |
+
"epoch": 8.6,
|
| 351 |
+
"learning_rate": 8.721325492158827e-05,
|
| 352 |
+
"loss": 0.0021,
|
| 353 |
+
"step": 22919
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 8.8,
|
| 357 |
+
"learning_rate": 8.665749082415749e-05,
|
| 358 |
+
"loss": 0.0039,
|
| 359 |
+
"step": 23452
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 9.0,
|
| 363 |
+
"eval_loss": 0.020978303626179695,
|
| 364 |
+
"eval_max_distance": 1,
|
| 365 |
+
"eval_mean_distance": 0,
|
| 366 |
+
"eval_runtime": 0.9126,
|
| 367 |
+
"eval_samples_per_second": 392.285,
|
| 368 |
+
"eval_steps_per_second": 26.298,
|
| 369 |
+
"step": 23976
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 9.0,
|
| 373 |
+
"learning_rate": 8.610172672672672e-05,
|
| 374 |
+
"loss": 0.0032,
|
| 375 |
+
"step": 23985
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 9.2,
|
| 379 |
+
"learning_rate": 8.554596262929596e-05,
|
| 380 |
+
"loss": 0.0027,
|
| 381 |
+
"step": 24518
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 9.4,
|
| 385 |
+
"learning_rate": 8.499019853186521e-05,
|
| 386 |
+
"loss": 0.0022,
|
| 387 |
+
"step": 25051
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 9.6,
|
| 391 |
+
"learning_rate": 8.443443443443444e-05,
|
| 392 |
+
"loss": 0.002,
|
| 393 |
+
"step": 25584
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 9.8,
|
| 397 |
+
"learning_rate": 8.387867033700368e-05,
|
| 398 |
+
"loss": 0.0026,
|
| 399 |
+
"step": 26117
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 10.0,
|
| 403 |
+
"eval_loss": 0.017031751573085785,
|
| 404 |
"eval_max_distance": 1,
|
| 405 |
"eval_mean_distance": 0,
|
| 406 |
+
"eval_runtime": 0.9145,
|
| 407 |
+
"eval_samples_per_second": 391.481,
|
| 408 |
+
"eval_steps_per_second": 26.245,
|
| 409 |
+
"step": 26640
|
| 410 |
},
|
| 411 |
{
|
| 412 |
+
"epoch": 10.0,
|
| 413 |
+
"learning_rate": 8.332290623957291e-05,
|
| 414 |
+
"loss": 0.0014,
|
| 415 |
+
"step": 26650
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 10.2,
|
| 419 |
+
"learning_rate": 8.276714214214215e-05,
|
| 420 |
+
"loss": 0.0016,
|
| 421 |
+
"step": 27183
|
| 422 |
},
|
| 423 |
{
|
| 424 |
+
"epoch": 10.4,
|
| 425 |
+
"learning_rate": 8.221137804471138e-05,
|
| 426 |
+
"loss": 0.0045,
|
| 427 |
+
"step": 27716
|
| 428 |
},
|
| 429 |
{
|
| 430 |
+
"epoch": 10.6,
|
| 431 |
+
"learning_rate": 8.165561394728062e-05,
|
| 432 |
+
"loss": 0.0017,
|
| 433 |
+
"step": 28249
|
| 434 |
},
|
| 435 |
{
|
| 436 |
+
"epoch": 10.8,
|
| 437 |
+
"learning_rate": 8.109984984984985e-05,
|
| 438 |
+
"loss": 0.0026,
|
| 439 |
+
"step": 28782
|
| 440 |
},
|
| 441 |
{
|
| 442 |
+
"epoch": 11.0,
|
| 443 |
+
"eval_loss": 0.004335461650043726,
|
| 444 |
+
"eval_max_distance": 1,
|
| 445 |
+
"eval_mean_distance": 0,
|
| 446 |
+
"eval_runtime": 0.9104,
|
| 447 |
+
"eval_samples_per_second": 393.245,
|
| 448 |
+
"eval_steps_per_second": 26.363,
|
| 449 |
+
"step": 29304
|
| 450 |
},
|
| 451 |
{
|
| 452 |
+
"epoch": 11.0,
|
| 453 |
+
"learning_rate": 8.054408575241909e-05,
|
| 454 |
+
"loss": 0.0016,
|
| 455 |
+
"step": 29315
|
| 456 |
},
|
| 457 |
{
|
| 458 |
+
"epoch": 11.2,
|
| 459 |
+
"learning_rate": 7.998832165498832e-05,
|
| 460 |
+
"loss": 0.0006,
|
| 461 |
+
"step": 29848
|
| 462 |
},
|
| 463 |
{
|
| 464 |
+
"epoch": 11.4,
|
| 465 |
+
"learning_rate": 7.943255755755756e-05,
|
| 466 |
+
"loss": 0.0011,
|
| 467 |
+
"step": 30381
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 11.6,
|
| 471 |
+
"learning_rate": 7.88767934601268e-05,
|
| 472 |
"loss": 0.0009,
|
| 473 |
+
"step": 30914
|
| 474 |
},
|
| 475 |
{
|
| 476 |
+
"epoch": 11.8,
|
| 477 |
+
"learning_rate": 7.832102936269603e-05,
|
| 478 |
+
"loss": 0.0029,
|
| 479 |
+
"step": 31447
|
| 480 |
},
|
| 481 |
{
|
| 482 |
+
"epoch": 12.0,
|
| 483 |
+
"eval_loss": 0.013542454689741135,
|
| 484 |
"eval_max_distance": 1,
|
| 485 |
"eval_mean_distance": 0,
|
| 486 |
+
"eval_runtime": 0.9125,
|
| 487 |
+
"eval_samples_per_second": 392.323,
|
| 488 |
+
"eval_steps_per_second": 26.301,
|
| 489 |
+
"step": 31968
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 12.0,
|
| 493 |
+
"learning_rate": 7.776526526526526e-05,
|
| 494 |
+
"loss": 0.0029,
|
| 495 |
+
"step": 31980
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 12.2,
|
| 499 |
+
"learning_rate": 7.720950116783451e-05,
|
| 500 |
+
"loss": 0.0008,
|
| 501 |
+
"step": 32513
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 12.4,
|
| 505 |
+
"learning_rate": 7.665373707040375e-05,
|
| 506 |
"loss": 0.0027,
|
| 507 |
+
"step": 33046
|
| 508 |
},
|
| 509 |
{
|
| 510 |
+
"epoch": 12.6,
|
| 511 |
+
"learning_rate": 7.609797297297297e-05,
|
| 512 |
+
"loss": 0.0016,
|
| 513 |
+
"step": 33579
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 12.8,
|
| 517 |
+
"learning_rate": 7.55422088755422e-05,
|
| 518 |
+
"loss": 0.0011,
|
| 519 |
+
"step": 34112
|
| 520 |
},
|
| 521 |
{
|
| 522 |
+
"epoch": 13.0,
|
| 523 |
+
"eval_loss": 0.03128792718052864,
|
| 524 |
+
"eval_max_distance": 1,
|
| 525 |
+
"eval_mean_distance": 0,
|
| 526 |
+
"eval_runtime": 0.9117,
|
| 527 |
+
"eval_samples_per_second": 392.662,
|
| 528 |
+
"eval_steps_per_second": 26.324,
|
| 529 |
+
"step": 34632
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 13.0,
|
| 533 |
+
"learning_rate": 7.498644477811145e-05,
|
| 534 |
+
"loss": 0.0007,
|
| 535 |
+
"step": 34645
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 13.2,
|
| 539 |
+
"learning_rate": 7.443068068068069e-05,
|
| 540 |
+
"loss": 0.0014,
|
| 541 |
+
"step": 35178
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 13.41,
|
| 545 |
+
"learning_rate": 7.387491658324992e-05,
|
| 546 |
+
"loss": 0.0067,
|
| 547 |
+
"step": 35711
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 13.61,
|
| 551 |
+
"learning_rate": 7.331915248581916e-05,
|
| 552 |
+
"loss": 0.0008,
|
| 553 |
+
"step": 36244
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 13.81,
|
| 557 |
+
"learning_rate": 7.27633883883884e-05,
|
| 558 |
"loss": 0.0017,
|
| 559 |
+
"step": 36777
|
| 560 |
},
|
| 561 |
{
|
| 562 |
+
"epoch": 14.0,
|
| 563 |
+
"eval_loss": 0.03530227765440941,
|
| 564 |
+
"eval_max_distance": 1,
|
| 565 |
+
"eval_mean_distance": 0,
|
| 566 |
+
"eval_runtime": 0.9178,
|
| 567 |
+
"eval_samples_per_second": 390.083,
|
| 568 |
+
"eval_steps_per_second": 26.151,
|
| 569 |
+
"step": 37296
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 14.01,
|
| 573 |
+
"learning_rate": 7.220762429095763e-05,
|
| 574 |
+
"loss": 0.001,
|
| 575 |
+
"step": 37310
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 14.21,
|
| 579 |
+
"learning_rate": 7.165186019352686e-05,
|
| 580 |
+
"loss": 0.001,
|
| 581 |
+
"step": 37843
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 14.41,
|
| 585 |
+
"learning_rate": 7.10960960960961e-05,
|
| 586 |
+
"loss": 0.0012,
|
| 587 |
+
"step": 38376
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 14.61,
|
| 591 |
+
"learning_rate": 7.054033199866533e-05,
|
| 592 |
+
"loss": 0.0011,
|
| 593 |
+
"step": 38909
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 14.81,
|
| 597 |
+
"learning_rate": 6.998456790123458e-05,
|
| 598 |
+
"loss": 0.0014,
|
| 599 |
+
"step": 39442
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 15.0,
|
| 603 |
+
"eval_loss": 0.011675473302602768,
|
| 604 |
"eval_max_distance": 1,
|
| 605 |
"eval_mean_distance": 0,
|
| 606 |
+
"eval_runtime": 0.916,
|
| 607 |
+
"eval_samples_per_second": 390.823,
|
| 608 |
+
"eval_steps_per_second": 26.2,
|
| 609 |
+
"step": 39960
|
| 610 |
},
|
| 611 |
{
|
| 612 |
+
"epoch": 15.01,
|
| 613 |
+
"learning_rate": 6.94288038038038e-05,
|
| 614 |
+
"loss": 0.001,
|
| 615 |
+
"step": 39975
|
| 616 |
},
|
| 617 |
{
|
| 618 |
+
"epoch": 15.21,
|
| 619 |
+
"learning_rate": 6.887303970637304e-05,
|
| 620 |
+
"loss": 0.0003,
|
| 621 |
+
"step": 40508
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"epoch": 15.41,
|
| 625 |
+
"learning_rate": 6.831727560894227e-05,
|
| 626 |
+
"loss": 0.002,
|
| 627 |
+
"step": 41041
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 15.61,
|
| 631 |
+
"learning_rate": 6.776151151151151e-05,
|
| 632 |
+
"loss": 0.001,
|
| 633 |
+
"step": 41574
|
| 634 |
},
|
| 635 |
{
|
| 636 |
+
"epoch": 15.81,
|
| 637 |
+
"learning_rate": 6.720574741408076e-05,
|
| 638 |
+
"loss": 0.0014,
|
| 639 |
+
"step": 42107
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 16.0,
|
| 643 |
+
"eval_loss": 0.0139808664098382,
|
| 644 |
+
"eval_max_distance": 1,
|
| 645 |
+
"eval_mean_distance": 0,
|
| 646 |
+
"eval_runtime": 0.9131,
|
| 647 |
+
"eval_samples_per_second": 392.074,
|
| 648 |
+
"eval_steps_per_second": 26.284,
|
| 649 |
+
"step": 42624
|
| 650 |
},
|
| 651 |
{
|
| 652 |
+
"epoch": 16.01,
|
| 653 |
+
"learning_rate": 6.664998331665e-05,
|
| 654 |
+
"loss": 0.0007,
|
| 655 |
+
"step": 42640
|
| 656 |
},
|
| 657 |
{
|
| 658 |
+
"epoch": 16.21,
|
| 659 |
+
"learning_rate": 6.609421921921923e-05,
|
| 660 |
+
"loss": 0.0004,
|
| 661 |
+
"step": 43173
|
| 662 |
},
|
| 663 |
{
|
| 664 |
+
"epoch": 16.41,
|
| 665 |
+
"learning_rate": 6.553845512178845e-05,
|
| 666 |
"loss": 0.0006,
|
| 667 |
+
"step": 43706
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 16.61,
|
| 671 |
+
"learning_rate": 6.498269102435769e-05,
|
| 672 |
+
"loss": 0.0017,
|
| 673 |
+
"step": 44239
|
| 674 |
},
|
| 675 |
{
|
| 676 |
+
"epoch": 16.81,
|
| 677 |
+
"learning_rate": 6.442692692692693e-05,
|
| 678 |
+
"loss": 0.0013,
|
| 679 |
+
"step": 44772
|
| 680 |
},
|
| 681 |
{
|
| 682 |
+
"epoch": 17.0,
|
| 683 |
+
"eval_loss": 0.022025227546691895,
|
| 684 |
"eval_max_distance": 1,
|
| 685 |
"eval_mean_distance": 0,
|
| 686 |
+
"eval_runtime": 0.9176,
|
| 687 |
+
"eval_samples_per_second": 390.127,
|
| 688 |
+
"eval_steps_per_second": 26.154,
|
| 689 |
+
"step": 45288
|
| 690 |
},
|
| 691 |
{
|
| 692 |
+
"epoch": 17.01,
|
| 693 |
+
"learning_rate": 6.387116282949617e-05,
|
| 694 |
+
"loss": 0.0013,
|
| 695 |
+
"step": 45305
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 17.21,
|
| 699 |
+
"learning_rate": 6.33153987320654e-05,
|
| 700 |
+
"loss": 0.0003,
|
| 701 |
+
"step": 45838
|
| 702 |
},
|
| 703 |
{
|
| 704 |
+
"epoch": 17.41,
|
| 705 |
+
"learning_rate": 6.275963463463464e-05,
|
| 706 |
"loss": 0.0011,
|
| 707 |
+
"step": 46371
|
| 708 |
},
|
| 709 |
{
|
| 710 |
+
"epoch": 17.61,
|
| 711 |
+
"learning_rate": 6.220387053720387e-05,
|
| 712 |
+
"loss": 0.0004,
|
| 713 |
+
"step": 46904
|
| 714 |
},
|
| 715 |
{
|
| 716 |
+
"epoch": 17.81,
|
| 717 |
+
"learning_rate": 6.164810643977311e-05,
|
| 718 |
+
"loss": 0.0009,
|
| 719 |
+
"step": 47437
|
| 720 |
},
|
| 721 |
{
|
| 722 |
+
"epoch": 18.0,
|
| 723 |
+
"eval_loss": 0.024678541347384453,
|
| 724 |
+
"eval_max_distance": 1,
|
| 725 |
+
"eval_mean_distance": 0,
|
| 726 |
+
"eval_runtime": 0.908,
|
| 727 |
+
"eval_samples_per_second": 394.28,
|
| 728 |
+
"eval_steps_per_second": 26.432,
|
| 729 |
+
"step": 47952
|
| 730 |
},
|
| 731 |
{
|
| 732 |
+
"epoch": 18.01,
|
| 733 |
+
"learning_rate": 6.109234234234234e-05,
|
| 734 |
+
"loss": 0.0023,
|
| 735 |
+
"step": 47970
|
| 736 |
},
|
| 737 |
{
|
| 738 |
+
"epoch": 18.21,
|
| 739 |
+
"learning_rate": 6.053657824491158e-05,
|
| 740 |
+
"loss": 0.0007,
|
| 741 |
+
"step": 48503
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 18.41,
|
| 745 |
+
"learning_rate": 5.9980814147480815e-05,
|
| 746 |
+
"loss": 0.0015,
|
| 747 |
+
"step": 49036
|
| 748 |
},
|
| 749 |
{
|
| 750 |
+
"epoch": 18.61,
|
| 751 |
+
"learning_rate": 5.9425050050050057e-05,
|
| 752 |
+
"loss": 0.0004,
|
| 753 |
+
"step": 49569
|
| 754 |
},
|
| 755 |
{
|
| 756 |
+
"epoch": 18.81,
|
| 757 |
+
"learning_rate": 5.886928595261929e-05,
|
| 758 |
+
"loss": 0.0017,
|
| 759 |
+
"step": 50102
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 19.0,
|
| 763 |
+
"eval_loss": 0.03220739960670471,
|
| 764 |
"eval_max_distance": 1,
|
| 765 |
"eval_mean_distance": 0,
|
| 766 |
+
"eval_runtime": 0.9151,
|
| 767 |
+
"eval_samples_per_second": 391.2,
|
| 768 |
+
"eval_steps_per_second": 26.226,
|
| 769 |
+
"step": 50616
|
| 770 |
},
|
| 771 |
{
|
| 772 |
+
"epoch": 19.01,
|
| 773 |
+
"learning_rate": 5.831352185518853e-05,
|
| 774 |
+
"loss": 0.0011,
|
| 775 |
+
"step": 50635
|
| 776 |
},
|
| 777 |
{
|
| 778 |
+
"epoch": 19.21,
|
| 779 |
+
"learning_rate": 5.7757757757757755e-05,
|
| 780 |
+
"loss": 0.0009,
|
| 781 |
+
"step": 51168
|
| 782 |
},
|
| 783 |
{
|
| 784 |
+
"epoch": 19.41,
|
| 785 |
+
"learning_rate": 5.720199366032699e-05,
|
| 786 |
+
"loss": 0.0005,
|
| 787 |
+
"step": 51701
|
| 788 |
},
|
| 789 |
{
|
| 790 |
+
"epoch": 19.61,
|
| 791 |
+
"learning_rate": 5.664622956289624e-05,
|
| 792 |
+
"loss": 0.0011,
|
| 793 |
+
"step": 52234
|
| 794 |
},
|
| 795 |
{
|
| 796 |
+
"epoch": 19.81,
|
| 797 |
+
"learning_rate": 5.609046546546547e-05,
|
| 798 |
+
"loss": 0.0022,
|
| 799 |
+
"step": 52767
|
| 800 |
},
|
| 801 |
{
|
| 802 |
+
"epoch": 20.0,
|
| 803 |
+
"eval_loss": 0.0314439982175827,
|
| 804 |
+
"eval_max_distance": 1,
|
| 805 |
+
"eval_mean_distance": 0,
|
| 806 |
+
"eval_runtime": 0.9074,
|
| 807 |
+
"eval_samples_per_second": 394.526,
|
| 808 |
+
"eval_steps_per_second": 26.449,
|
| 809 |
+
"step": 53280
|
| 810 |
},
|
| 811 |
{
|
| 812 |
+
"epoch": 20.01,
|
| 813 |
+
"learning_rate": 5.55347013680347e-05,
|
| 814 |
+
"loss": 0.001,
|
| 815 |
+
"step": 53300
|
| 816 |
},
|
| 817 |
{
|
| 818 |
+
"epoch": 20.21,
|
| 819 |
+
"learning_rate": 5.497893727060394e-05,
|
| 820 |
+
"loss": 0.001,
|
| 821 |
+
"step": 53833
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 20.41,
|
| 825 |
+
"learning_rate": 5.442317317317318e-05,
|
| 826 |
+
"loss": 0.0,
|
| 827 |
+
"step": 54366
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"epoch": 20.61,
|
| 831 |
+
"learning_rate": 5.3867409075742415e-05,
|
| 832 |
+
"loss": 0.0015,
|
| 833 |
+
"step": 54899
|
| 834 |
},
|
| 835 |
{
|
| 836 |
+
"epoch": 20.81,
|
| 837 |
+
"learning_rate": 5.331164497831165e-05,
|
| 838 |
+
"loss": 0.0006,
|
| 839 |
+
"step": 55432
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 21.0,
|
| 843 |
+
"eval_loss": 0.030524656176567078,
|
| 844 |
"eval_max_distance": 1,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
+
"eval_runtime": 0.9097,
|
| 847 |
+
"eval_samples_per_second": 393.555,
|
| 848 |
+
"eval_steps_per_second": 26.384,
|
| 849 |
+
"step": 55944
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 21.01,
|
| 853 |
+
"learning_rate": 5.275588088088088e-05,
|
| 854 |
+
"loss": 0.0005,
|
| 855 |
+
"step": 55965
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 21.21,
|
| 859 |
+
"learning_rate": 5.220011678345011e-05,
|
| 860 |
+
"loss": 0.0006,
|
| 861 |
+
"step": 56498
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 21.41,
|
| 865 |
+
"learning_rate": 5.164435268601936e-05,
|
| 866 |
+
"loss": 0.0012,
|
| 867 |
+
"step": 57031
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 21.61,
|
| 871 |
+
"learning_rate": 5.108858858858859e-05,
|
| 872 |
+
"loss": 0.0005,
|
| 873 |
+
"step": 57564
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 21.81,
|
| 877 |
+
"learning_rate": 5.0532824491157825e-05,
|
| 878 |
+
"loss": 0.001,
|
| 879 |
+
"step": 58097
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 22.0,
|
| 883 |
+
"eval_loss": 0.029209736734628677,
|
| 884 |
+
"eval_max_distance": 1,
|
| 885 |
+
"eval_mean_distance": 0,
|
| 886 |
+
"eval_runtime": 0.9114,
|
| 887 |
+
"eval_samples_per_second": 392.814,
|
| 888 |
+
"eval_steps_per_second": 26.334,
|
| 889 |
+
"step": 58608
|
| 890 |
},
|
| 891 |
{
|
| 892 |
+
"epoch": 22.01,
|
| 893 |
+
"learning_rate": 4.997706039372707e-05,
|
| 894 |
+
"loss": 0.0007,
|
| 895 |
+
"step": 58630
|
| 896 |
},
|
| 897 |
{
|
| 898 |
+
"epoch": 22.21,
|
| 899 |
+
"learning_rate": 4.94212962962963e-05,
|
| 900 |
+
"loss": 0.0011,
|
| 901 |
+
"step": 59163
|
| 902 |
},
|
| 903 |
{
|
| 904 |
+
"epoch": 22.41,
|
| 905 |
+
"learning_rate": 4.886553219886553e-05,
|
| 906 |
+
"loss": 0.0004,
|
| 907 |
+
"step": 59696
|
| 908 |
},
|
| 909 |
{
|
| 910 |
+
"epoch": 22.61,
|
| 911 |
+
"learning_rate": 4.830976810143477e-05,
|
| 912 |
+
"loss": 0.001,
|
| 913 |
+
"step": 60229
|
| 914 |
},
|
| 915 |
{
|
| 916 |
+
"epoch": 22.81,
|
| 917 |
+
"learning_rate": 4.775400400400401e-05,
|
| 918 |
+
"loss": 0.0008,
|
| 919 |
+
"step": 60762
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 23.0,
|
| 923 |
+
"eval_loss": 0.03728558123111725,
|
| 924 |
"eval_max_distance": 1,
|
| 925 |
"eval_mean_distance": 0,
|
| 926 |
+
"eval_runtime": 0.9095,
|
| 927 |
+
"eval_samples_per_second": 393.613,
|
| 928 |
+
"eval_steps_per_second": 26.387,
|
| 929 |
+
"step": 61272
|
| 930 |
},
|
| 931 |
{
|
| 932 |
+
"epoch": 23.01,
|
| 933 |
+
"learning_rate": 4.719823990657324e-05,
|
| 934 |
+
"loss": 0.0001,
|
| 935 |
+
"step": 61295
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 23.21,
|
| 939 |
+
"learning_rate": 4.664247580914248e-05,
|
| 940 |
"loss": 0.0006,
|
| 941 |
+
"step": 61828
|
| 942 |
},
|
| 943 |
{
|
| 944 |
+
"epoch": 23.41,
|
| 945 |
+
"learning_rate": 4.608671171171172e-05,
|
| 946 |
+
"loss": 0.0002,
|
| 947 |
+
"step": 62361
|
| 948 |
},
|
| 949 |
{
|
| 950 |
+
"epoch": 23.61,
|
| 951 |
+
"learning_rate": 4.553094761428095e-05,
|
| 952 |
+
"loss": 0.0009,
|
| 953 |
+
"step": 62894
|
| 954 |
},
|
| 955 |
{
|
| 956 |
+
"epoch": 23.81,
|
| 957 |
+
"learning_rate": 4.497518351685018e-05,
|
| 958 |
+
"loss": 0.0008,
|
| 959 |
+
"step": 63427
|
| 960 |
},
|
| 961 |
{
|
| 962 |
+
"epoch": 24.0,
|
| 963 |
+
"eval_loss": 0.030942877754569054,
|
| 964 |
+
"eval_max_distance": 1,
|
| 965 |
+
"eval_mean_distance": 0,
|
| 966 |
+
"eval_runtime": 0.9149,
|
| 967 |
+
"eval_samples_per_second": 391.282,
|
| 968 |
+
"eval_steps_per_second": 26.231,
|
| 969 |
+
"step": 63936
|
| 970 |
},
|
| 971 |
{
|
| 972 |
+
"epoch": 24.01,
|
| 973 |
+
"learning_rate": 4.4419419419419425e-05,
|
| 974 |
+
"loss": 0.0003,
|
| 975 |
+
"step": 63960
|
| 976 |
},
|
| 977 |
{
|
| 978 |
+
"epoch": 24.21,
|
| 979 |
+
"learning_rate": 4.386365532198865e-05,
|
| 980 |
+
"loss": 0.0007,
|
| 981 |
+
"step": 64493
|
| 982 |
},
|
| 983 |
{
|
| 984 |
+
"epoch": 24.41,
|
| 985 |
+
"learning_rate": 4.3307891224557895e-05,
|
| 986 |
+
"loss": 0.0004,
|
| 987 |
+
"step": 65026
|
| 988 |
},
|
| 989 |
{
|
| 990 |
+
"epoch": 24.61,
|
| 991 |
+
"learning_rate": 4.275212712712713e-05,
|
| 992 |
"loss": 0.0001,
|
| 993 |
+
"step": 65559
|
| 994 |
},
|
| 995 |
{
|
| 996 |
+
"epoch": 24.81,
|
| 997 |
+
"learning_rate": 4.2196363029696365e-05,
|
| 998 |
+
"loss": 0.0008,
|
| 999 |
+
"step": 66092
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 25.0,
|
| 1003 |
+
"eval_loss": 0.038451410830020905,
|
| 1004 |
"eval_max_distance": 1,
|
| 1005 |
"eval_mean_distance": 0,
|
| 1006 |
+
"eval_runtime": 0.9087,
|
| 1007 |
+
"eval_samples_per_second": 393.969,
|
| 1008 |
+
"eval_steps_per_second": 26.411,
|
| 1009 |
+
"step": 66600
|
| 1010 |
},
|
| 1011 |
{
|
| 1012 |
+
"epoch": 25.01,
|
| 1013 |
+
"learning_rate": 4.16405989322656e-05,
|
| 1014 |
"loss": 0.0006,
|
| 1015 |
+
"step": 66625
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
+
"epoch": 25.21,
|
| 1019 |
+
"learning_rate": 4.1084834834834836e-05,
|
| 1020 |
+
"loss": 0.0,
|
| 1021 |
+
"step": 67158
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
+
"epoch": 25.41,
|
| 1025 |
+
"learning_rate": 4.052907073740407e-05,
|
| 1026 |
+
"loss": 0.0013,
|
| 1027 |
+
"step": 67691
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
+
"epoch": 25.61,
|
| 1031 |
+
"learning_rate": 3.9973306639973306e-05,
|
| 1032 |
+
"loss": 0.0001,
|
| 1033 |
+
"step": 68224
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
+
"epoch": 25.81,
|
| 1037 |
+
"learning_rate": 3.941754254254255e-05,
|
| 1038 |
"loss": 0.0014,
|
| 1039 |
+
"step": 68757
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
+
"epoch": 26.0,
|
| 1043 |
+
"eval_loss": 0.0133729362860322,
|
| 1044 |
+
"eval_max_distance": 1,
|
| 1045 |
+
"eval_mean_distance": 0,
|
| 1046 |
+
"eval_runtime": 0.9209,
|
| 1047 |
+
"eval_samples_per_second": 388.755,
|
| 1048 |
+
"eval_steps_per_second": 26.062,
|
| 1049 |
+
"step": 69264
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
+
"epoch": 26.01,
|
| 1053 |
+
"learning_rate": 3.8861778445111776e-05,
|
| 1054 |
+
"loss": 0.0001,
|
| 1055 |
+
"step": 69290
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
+
"epoch": 26.21,
|
| 1059 |
+
"learning_rate": 3.830601434768102e-05,
|
| 1060 |
+
"loss": 0.0008,
|
| 1061 |
+
"step": 69823
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
+
"epoch": 26.41,
|
| 1065 |
+
"learning_rate": 3.775025025025025e-05,
|
| 1066 |
+
"loss": 0.0008,
|
| 1067 |
+
"step": 70356
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
+
"epoch": 26.61,
|
| 1071 |
+
"learning_rate": 3.719448615281949e-05,
|
| 1072 |
+
"loss": 0.0002,
|
| 1073 |
+
"step": 70889
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
+
"epoch": 26.81,
|
| 1077 |
+
"learning_rate": 3.663872205538872e-05,
|
| 1078 |
+
"loss": 0.0004,
|
| 1079 |
+
"step": 71422
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 27.0,
|
| 1083 |
+
"eval_loss": 0.023867754265666008,
|
| 1084 |
"eval_max_distance": 1,
|
| 1085 |
"eval_mean_distance": 0,
|
| 1086 |
+
"eval_runtime": 0.9071,
|
| 1087 |
+
"eval_samples_per_second": 394.647,
|
| 1088 |
+
"eval_steps_per_second": 26.457,
|
| 1089 |
+
"step": 71928
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
+
"epoch": 27.01,
|
| 1093 |
+
"learning_rate": 3.608295795795796e-05,
|
| 1094 |
+
"loss": 0.0009,
|
| 1095 |
+
"step": 71955
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"epoch": 27.21,
|
| 1099 |
+
"learning_rate": 3.55271938605272e-05,
|
| 1100 |
+
"loss": 0.0005,
|
| 1101 |
+
"step": 72488
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
+
"epoch": 27.41,
|
| 1105 |
+
"learning_rate": 3.497142976309643e-05,
|
| 1106 |
+
"loss": 0.0007,
|
| 1107 |
+
"step": 73021
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 27.61,
|
| 1111 |
+
"learning_rate": 3.441566566566567e-05,
|
| 1112 |
+
"loss": 0.0001,
|
| 1113 |
+
"step": 73554
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
+
"epoch": 27.81,
|
| 1117 |
+
"learning_rate": 3.3859901568234906e-05,
|
| 1118 |
+
"loss": 0.0011,
|
| 1119 |
+
"step": 74087
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
+
"epoch": 28.0,
|
| 1123 |
+
"eval_loss": 0.01642591878771782,
|
| 1124 |
+
"eval_max_distance": 1,
|
| 1125 |
+
"eval_mean_distance": 0,
|
| 1126 |
+
"eval_runtime": 0.9124,
|
| 1127 |
+
"eval_samples_per_second": 392.371,
|
| 1128 |
+
"eval_steps_per_second": 26.304,
|
| 1129 |
+
"step": 74592
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 28.01,
|
| 1133 |
+
"learning_rate": 3.3304137470804134e-05,
|
| 1134 |
+
"loss": 0.0006,
|
| 1135 |
+
"step": 74620
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 28.21,
|
| 1139 |
+
"learning_rate": 3.2748373373373376e-05,
|
| 1140 |
+
"loss": 0.0008,
|
| 1141 |
+
"step": 75153
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 28.41,
|
| 1145 |
+
"learning_rate": 3.219260927594261e-05,
|
| 1146 |
+
"loss": 0.0005,
|
| 1147 |
+
"step": 75686
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
+
"epoch": 28.61,
|
| 1151 |
+
"learning_rate": 3.1636845178511846e-05,
|
| 1152 |
+
"loss": 0.0002,
|
| 1153 |
+
"step": 76219
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 28.81,
|
| 1157 |
+
"learning_rate": 3.108108108108108e-05,
|
| 1158 |
+
"loss": 0.0002,
|
| 1159 |
+
"step": 76752
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 29.0,
|
| 1163 |
+
"eval_loss": 0.018625039607286453,
|
| 1164 |
"eval_max_distance": 1,
|
| 1165 |
"eval_mean_distance": 0,
|
| 1166 |
+
"eval_runtime": 0.9144,
|
| 1167 |
+
"eval_samples_per_second": 391.524,
|
| 1168 |
+
"eval_steps_per_second": 26.247,
|
| 1169 |
+
"step": 77256
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
+
"epoch": 29.01,
|
| 1173 |
+
"learning_rate": 3.052531698365032e-05,
|
| 1174 |
"loss": 0.0003,
|
| 1175 |
+
"step": 77285
|
| 1176 |
},
|
| 1177 |
{
|
| 1178 |
+
"epoch": 29.21,
|
| 1179 |
+
"learning_rate": 2.9969552886219555e-05,
|
| 1180 |
"loss": 0.0002,
|
| 1181 |
+
"step": 77818
|
| 1182 |
},
|
| 1183 |
{
|
| 1184 |
+
"epoch": 29.41,
|
| 1185 |
+
"learning_rate": 2.9413788788788787e-05,
|
| 1186 |
+
"loss": 0.0001,
|
| 1187 |
+
"step": 78351
|
| 1188 |
},
|
| 1189 |
{
|
| 1190 |
+
"epoch": 29.61,
|
| 1191 |
+
"learning_rate": 2.8858024691358025e-05,
|
| 1192 |
+
"loss": 0.0013,
|
| 1193 |
+
"step": 78884
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
+
"epoch": 29.81,
|
| 1197 |
+
"learning_rate": 2.830226059392726e-05,
|
| 1198 |
+
"loss": 0.0001,
|
| 1199 |
+
"step": 79417
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
+
"epoch": 30.0,
|
| 1203 |
+
"eval_loss": 0.029812639579176903,
|
| 1204 |
+
"eval_max_distance": 1,
|
| 1205 |
+
"eval_mean_distance": 0,
|
| 1206 |
+
"eval_runtime": 0.9075,
|
| 1207 |
+
"eval_samples_per_second": 394.481,
|
| 1208 |
+
"eval_steps_per_second": 26.446,
|
| 1209 |
+
"step": 79920
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
+
"epoch": 30.01,
|
| 1213 |
+
"learning_rate": 2.77464964964965e-05,
|
| 1214 |
+
"loss": 0.0012,
|
| 1215 |
+
"step": 79950
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
+
"epoch": 30.21,
|
| 1219 |
+
"learning_rate": 2.7190732399065734e-05,
|
| 1220 |
+
"loss": 0.0003,
|
| 1221 |
+
"step": 80483
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 30.41,
|
| 1225 |
+
"learning_rate": 2.6634968301634972e-05,
|
| 1226 |
"loss": 0.0001,
|
| 1227 |
+
"step": 81016
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
+
"epoch": 30.61,
|
| 1231 |
+
"learning_rate": 2.6079204204204204e-05,
|
| 1232 |
+
"loss": 0.0004,
|
| 1233 |
+
"step": 81549
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
+
"epoch": 30.81,
|
| 1237 |
+
"learning_rate": 2.5523440106773443e-05,
|
| 1238 |
+
"loss": 0.0008,
|
| 1239 |
+
"step": 82082
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
+
"epoch": 31.0,
|
| 1243 |
+
"eval_loss": 0.027695728465914726,
|
| 1244 |
"eval_max_distance": 1,
|
| 1245 |
"eval_mean_distance": 0,
|
| 1246 |
+
"eval_runtime": 0.9096,
|
| 1247 |
+
"eval_samples_per_second": 393.574,
|
| 1248 |
+
"eval_steps_per_second": 26.385,
|
| 1249 |
+
"step": 82584
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
+
"epoch": 31.01,
|
| 1253 |
+
"learning_rate": 2.4967676009342678e-05,
|
| 1254 |
+
"loss": 0.0008,
|
| 1255 |
+
"step": 82615
|
| 1256 |
},
|
| 1257 |
{
|
| 1258 |
+
"epoch": 31.21,
|
| 1259 |
+
"learning_rate": 2.4411911911911913e-05,
|
| 1260 |
+
"loss": 0.0003,
|
| 1261 |
+
"step": 83148
|
| 1262 |
},
|
| 1263 |
{
|
| 1264 |
+
"epoch": 31.41,
|
| 1265 |
+
"learning_rate": 2.385614781448115e-05,
|
| 1266 |
+
"loss": 0.0003,
|
| 1267 |
+
"step": 83681
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
+
"epoch": 31.61,
|
| 1271 |
+
"learning_rate": 2.3300383717050383e-05,
|
| 1272 |
+
"loss": 0.0002,
|
| 1273 |
+
"step": 84214
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
+
"epoch": 31.81,
|
| 1277 |
+
"learning_rate": 2.2744619619619618e-05,
|
| 1278 |
"loss": 0.0003,
|
| 1279 |
+
"step": 84747
|
| 1280 |
},
|
| 1281 |
{
|
| 1282 |
+
"epoch": 32.0,
|
| 1283 |
+
"eval_loss": 0.03773302584886551,
|
| 1284 |
+
"eval_max_distance": 1,
|
| 1285 |
+
"eval_mean_distance": 0,
|
| 1286 |
+
"eval_runtime": 0.9096,
|
| 1287 |
+
"eval_samples_per_second": 393.585,
|
| 1288 |
+
"eval_steps_per_second": 26.386,
|
| 1289 |
+
"step": 85248
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
+
"epoch": 32.01,
|
| 1293 |
+
"learning_rate": 2.2188855522188857e-05,
|
| 1294 |
+
"loss": 0.0007,
|
| 1295 |
+
"step": 85280
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
+
"epoch": 32.21,
|
| 1299 |
+
"learning_rate": 2.1633091424758092e-05,
|
| 1300 |
+
"loss": 0.001,
|
| 1301 |
+
"step": 85813
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
+
"epoch": 32.41,
|
| 1305 |
+
"learning_rate": 2.107732732732733e-05,
|
| 1306 |
+
"loss": 0.0002,
|
| 1307 |
+
"step": 86346
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
+
"epoch": 32.61,
|
| 1311 |
+
"learning_rate": 2.0521563229896565e-05,
|
| 1312 |
"loss": 0.0002,
|
| 1313 |
+
"step": 86879
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
+
"epoch": 32.81,
|
| 1317 |
+
"learning_rate": 1.99657991324658e-05,
|
| 1318 |
+
"loss": 0.0003,
|
| 1319 |
+
"step": 87412
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 33.0,
|
| 1323 |
+
"eval_loss": 0.03536462038755417,
|
| 1324 |
"eval_max_distance": 1,
|
| 1325 |
"eval_mean_distance": 0,
|
| 1326 |
+
"eval_runtime": 0.9089,
|
| 1327 |
+
"eval_samples_per_second": 393.87,
|
| 1328 |
+
"eval_steps_per_second": 26.405,
|
| 1329 |
+
"step": 87912
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
+
"epoch": 33.01,
|
| 1333 |
+
"learning_rate": 1.9410035035035036e-05,
|
| 1334 |
+
"loss": 0.0006,
|
| 1335 |
+
"step": 87945
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
+
"epoch": 33.21,
|
| 1339 |
+
"learning_rate": 1.885427093760427e-05,
|
| 1340 |
+
"loss": 0.0003,
|
| 1341 |
+
"step": 88478
|
| 1342 |
},
|
| 1343 |
{
|
| 1344 |
+
"epoch": 33.41,
|
| 1345 |
+
"learning_rate": 1.8298506840173506e-05,
|
| 1346 |
+
"loss": 0.0003,
|
| 1347 |
+
"step": 89011
|
| 1348 |
},
|
| 1349 |
{
|
| 1350 |
+
"epoch": 33.61,
|
| 1351 |
+
"learning_rate": 1.7742742742742744e-05,
|
| 1352 |
+
"loss": 0.0006,
|
| 1353 |
+
"step": 89544
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
+
"epoch": 33.81,
|
| 1357 |
+
"learning_rate": 1.718697864531198e-05,
|
| 1358 |
+
"loss": 0.0007,
|
| 1359 |
+
"step": 90077
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
+
"epoch": 34.0,
|
| 1363 |
+
"eval_loss": 0.05854496732354164,
|
| 1364 |
+
"eval_max_distance": 1,
|
| 1365 |
+
"eval_mean_distance": 0,
|
| 1366 |
+
"eval_runtime": 0.9101,
|
| 1367 |
+
"eval_samples_per_second": 393.356,
|
| 1368 |
+
"eval_steps_per_second": 26.37,
|
| 1369 |
+
"step": 90576
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
+
"epoch": 34.01,
|
| 1373 |
+
"learning_rate": 1.6631214547881215e-05,
|
| 1374 |
+
"loss": 0.0002,
|
| 1375 |
+
"step": 90610
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
+
"epoch": 34.21,
|
| 1379 |
+
"learning_rate": 1.6075450450450453e-05,
|
| 1380 |
+
"loss": 0.0006,
|
| 1381 |
+
"step": 91143
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
+
"epoch": 34.41,
|
| 1385 |
+
"learning_rate": 1.5519686353019688e-05,
|
| 1386 |
+
"loss": 0.0003,
|
| 1387 |
+
"step": 91676
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
+
"epoch": 34.61,
|
| 1391 |
+
"learning_rate": 1.4963922255588922e-05,
|
| 1392 |
+
"loss": 0.0006,
|
| 1393 |
+
"step": 92209
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 34.81,
|
| 1397 |
+
"learning_rate": 1.4408158158158158e-05,
|
| 1398 |
+
"loss": 0.0005,
|
| 1399 |
+
"step": 92742
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 35.0,
|
| 1403 |
+
"eval_loss": 0.05680559575557709,
|
| 1404 |
"eval_max_distance": 1,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
+
"eval_runtime": 0.9087,
|
| 1407 |
+
"eval_samples_per_second": 393.956,
|
| 1408 |
+
"eval_steps_per_second": 26.41,
|
| 1409 |
+
"step": 93240
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
+
"epoch": 35.01,
|
| 1413 |
+
"learning_rate": 1.3852394060727395e-05,
|
| 1414 |
+
"loss": 0.0,
|
| 1415 |
+
"step": 93275
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 35.21,
|
| 1419 |
+
"learning_rate": 1.329662996329663e-05,
|
| 1420 |
"loss": 0.0005,
|
| 1421 |
+
"step": 93808
|
| 1422 |
},
|
| 1423 |
{
|
| 1424 |
+
"epoch": 35.41,
|
| 1425 |
+
"learning_rate": 1.2740865865865867e-05,
|
| 1426 |
+
"loss": 0.0002,
|
| 1427 |
+
"step": 94341
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
+
"epoch": 35.61,
|
| 1431 |
+
"learning_rate": 1.2185101768435102e-05,
|
| 1432 |
+
"loss": 0.0007,
|
| 1433 |
+
"step": 94874
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
+
"epoch": 35.81,
|
| 1437 |
+
"learning_rate": 1.1629337671004337e-05,
|
| 1438 |
+
"loss": 0.0001,
|
| 1439 |
+
"step": 95407
|
| 1440 |
},
|
| 1441 |
{
|
| 1442 |
+
"epoch": 36.0,
|
| 1443 |
+
"eval_loss": 0.05670797452330589,
|
| 1444 |
+
"eval_max_distance": 1,
|
| 1445 |
+
"eval_mean_distance": 0,
|
| 1446 |
+
"eval_runtime": 0.9196,
|
| 1447 |
+
"eval_samples_per_second": 389.279,
|
| 1448 |
+
"eval_steps_per_second": 26.097,
|
| 1449 |
+
"step": 95904
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 36.01,
|
| 1453 |
+
"learning_rate": 1.1073573573573574e-05,
|
| 1454 |
"loss": 0.0003,
|
| 1455 |
+
"step": 95940
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
+
"epoch": 36.21,
|
| 1459 |
+
"learning_rate": 1.0517809476142811e-05,
|
| 1460 |
+
"loss": 0.0004,
|
| 1461 |
+
"step": 96473
|
| 1462 |
},
|
| 1463 |
{
|
| 1464 |
+
"epoch": 36.41,
|
| 1465 |
+
"learning_rate": 9.962045378712046e-06,
|
| 1466 |
+
"loss": 0.0002,
|
| 1467 |
+
"step": 97006
|
| 1468 |
},
|
| 1469 |
{
|
| 1470 |
+
"epoch": 36.61,
|
| 1471 |
+
"learning_rate": 9.406281281281281e-06,
|
| 1472 |
+
"loss": 0.0006,
|
| 1473 |
+
"step": 97539
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
+
"epoch": 36.81,
|
| 1477 |
+
"learning_rate": 8.850517183850518e-06,
|
| 1478 |
+
"loss": 0.0009,
|
| 1479 |
+
"step": 98072
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 37.0,
|
| 1483 |
+
"eval_loss": 0.060491062700748444,
|
| 1484 |
+
"eval_max_distance": 1,
|
| 1485 |
+
"eval_mean_distance": 0,
|
| 1486 |
+
"eval_runtime": 0.9347,
|
| 1487 |
+
"eval_samples_per_second": 383.022,
|
| 1488 |
+
"eval_steps_per_second": 25.677,
|
| 1489 |
+
"step": 98568
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 37.01,
|
| 1493 |
+
"learning_rate": 8.294753086419753e-06,
|
| 1494 |
+
"loss": 0.0002,
|
| 1495 |
+
"step": 98605
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 37.21,
|
| 1499 |
+
"learning_rate": 7.738988988988988e-06,
|
| 1500 |
+
"loss": 0.001,
|
| 1501 |
+
"step": 99138
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 37.41,
|
| 1505 |
+
"learning_rate": 7.183224891558225e-06,
|
| 1506 |
+
"loss": 0.0003,
|
| 1507 |
+
"step": 99671
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
+
"epoch": 37.61,
|
| 1511 |
+
"learning_rate": 6.627460794127462e-06,
|
| 1512 |
"loss": 0.0001,
|
| 1513 |
+
"step": 100204
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
+
"epoch": 37.81,
|
| 1517 |
+
"learning_rate": 6.071696696696697e-06,
|
| 1518 |
+
"loss": 0.0002,
|
| 1519 |
+
"step": 100737
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 38.0,
|
| 1523 |
+
"eval_loss": 0.06128498166799545,
|
| 1524 |
"eval_max_distance": 1,
|
| 1525 |
"eval_mean_distance": 0,
|
| 1526 |
+
"eval_runtime": 0.9116,
|
| 1527 |
+
"eval_samples_per_second": 392.708,
|
| 1528 |
+
"eval_steps_per_second": 26.327,
|
| 1529 |
+
"step": 101232
|
| 1530 |
},
|
| 1531 |
{
|
| 1532 |
+
"epoch": 38.01,
|
| 1533 |
+
"learning_rate": 5.515932599265933e-06,
|
| 1534 |
+
"loss": 0.0002,
|
| 1535 |
+
"step": 101270
|
| 1536 |
},
|
| 1537 |
{
|
| 1538 |
+
"epoch": 38.21,
|
| 1539 |
+
"learning_rate": 4.960168501835169e-06,
|
| 1540 |
+
"loss": 0.0002,
|
| 1541 |
+
"step": 101803
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 38.41,
|
| 1545 |
+
"learning_rate": 4.404404404404405e-06,
|
| 1546 |
"loss": 0.0001,
|
| 1547 |
+
"step": 102336
|
| 1548 |
},
|
| 1549 |
{
|
| 1550 |
+
"epoch": 38.61,
|
| 1551 |
+
"learning_rate": 3.848640306973641e-06,
|
| 1552 |
+
"loss": 0.0006,
|
| 1553 |
+
"step": 102869
|
| 1554 |
},
|
| 1555 |
{
|
| 1556 |
+
"epoch": 38.81,
|
| 1557 |
+
"learning_rate": 3.2928762095428764e-06,
|
| 1558 |
+
"loss": 0.0002,
|
| 1559 |
+
"step": 103402
|
| 1560 |
},
|
| 1561 |
{
|
| 1562 |
+
"epoch": 39.0,
|
| 1563 |
+
"eval_loss": 0.05631242319941521,
|
| 1564 |
+
"eval_max_distance": 1,
|
| 1565 |
+
"eval_mean_distance": 0,
|
| 1566 |
+
"eval_runtime": 0.9146,
|
| 1567 |
+
"eval_samples_per_second": 391.433,
|
| 1568 |
+
"eval_steps_per_second": 26.241,
|
| 1569 |
+
"step": 103896
|
| 1570 |
},
|
| 1571 |
{
|
| 1572 |
+
"epoch": 39.01,
|
| 1573 |
+
"learning_rate": 2.7371121121121123e-06,
|
| 1574 |
+
"loss": 0.0004,
|
| 1575 |
+
"step": 103935
|
| 1576 |
},
|
| 1577 |
{
|
| 1578 |
+
"epoch": 39.21,
|
| 1579 |
+
"learning_rate": 2.1813480146813483e-06,
|
| 1580 |
+
"loss": 0.0004,
|
| 1581 |
+
"step": 104468
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
+
"epoch": 39.41,
|
| 1585 |
+
"learning_rate": 1.625583917250584e-06,
|
| 1586 |
"loss": 0.0001,
|
| 1587 |
+
"step": 105001
|
| 1588 |
},
|
| 1589 |
{
|
| 1590 |
+
"epoch": 39.61,
|
| 1591 |
+
"learning_rate": 1.0698198198198198e-06,
|
| 1592 |
+
"loss": 0.0013,
|
| 1593 |
+
"step": 105534
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
+
"epoch": 39.81,
|
| 1597 |
+
"learning_rate": 5.140557223890558e-07,
|
| 1598 |
+
"loss": 0.0002,
|
| 1599 |
+
"step": 106067
|
| 1600 |
},
|
| 1601 |
{
|
| 1602 |
+
"epoch": 40.0,
|
| 1603 |
+
"eval_loss": 0.06320372968912125,
|
| 1604 |
"eval_max_distance": 1,
|
| 1605 |
"eval_mean_distance": 0,
|
| 1606 |
+
"eval_runtime": 0.9155,
|
| 1607 |
+
"eval_samples_per_second": 391.055,
|
| 1608 |
+
"eval_steps_per_second": 26.216,
|
| 1609 |
+
"step": 106560
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 40.0,
|
| 1613 |
+
"step": 106560,
|
| 1614 |
+
"total_flos": 6.005678715251712e+16,
|
| 1615 |
+
"train_loss": 0.2983123329788039,
|
| 1616 |
+
"train_runtime": 9788.1362,
|
| 1617 |
+
"train_samples_per_second": 163.251,
|
| 1618 |
+
"train_steps_per_second": 10.887
|
| 1619 |
}
|
| 1620 |
],
|
| 1621 |
+
"logging_steps": 533,
|
| 1622 |
+
"max_steps": 106560,
|
| 1623 |
+
"num_train_epochs": 40,
|
| 1624 |
+
"save_steps": 1066,
|
| 1625 |
+
"total_flos": 6.005678715251712e+16,
|
| 1626 |
"trial_name": null,
|
| 1627 |
"trial_params": null
|
| 1628 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5e0326a3796f2941f5716fa2fff187aa13e78d8388fdce8869a34735725ca5a
|
| 3 |
size 4664
|