End of training
Browse files- README.md +107 -15
- pytorch_model.bin +1 -1
- trainer_state.json +1063 -1063
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,27 +1,119 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
|
| 4 |
-
- ru
|
| 5 |
-
library_name: transformers
|
| 6 |
tags:
|
| 7 |
-
-
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
It was designed for Silero TTS model which cant handle english and numbers for russian text to speach.
|
| 13 |
|
| 14 |
-
|
| 15 |
|
|
|
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 0.
|
| 18 |
- Mean Distance: 0
|
| 19 |
-
- Max Distance:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model: cointegrated/rut5-small
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: text-normalization-ru-new
|
| 8 |
+
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
| 13 |
|
| 14 |
+
# text-normalization-ru-new
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [cointegrated/rut5-small](https://huggingface.co/cointegrated/rut5-small) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0318
|
| 19 |
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 11
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.001
|
| 40 |
+
- train_batch_size: 30
|
| 41 |
+
- eval_batch_size: 30
|
| 42 |
+
- seed: 42
|
| 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: 60
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.2251 | 1.0 | 3334 | 0.1190 | 3 | 29 |
|
| 53 |
+
| 0.1179 | 2.0 | 6668 | 0.0574 | 2 | 31 |
|
| 54 |
+
| 0.0848 | 3.0 | 10002 | 0.0436 | 1 | 15 |
|
| 55 |
+
| 0.0618 | 4.0 | 13336 | 0.0359 | 1 | 20 |
|
| 56 |
+
| 0.0532 | 5.0 | 16670 | 0.0315 | 0 | 11 |
|
| 57 |
+
| 0.0446 | 6.0 | 20004 | 0.0299 | 0 | 16 |
|
| 58 |
+
| 0.0388 | 7.0 | 23338 | 0.0295 | 0 | 15 |
|
| 59 |
+
| 0.0311 | 8.0 | 26672 | 0.0287 | 0 | 15 |
|
| 60 |
+
| 0.0269 | 9.0 | 30006 | 0.0241 | 0 | 15 |
|
| 61 |
+
| 0.0232 | 10.0 | 33340 | 0.0228 | 0 | 13 |
|
| 62 |
+
| 0.0203 | 11.0 | 36674 | 0.0243 | 0 | 16 |
|
| 63 |
+
| 0.0173 | 12.0 | 40008 | 0.0250 | 0 | 15 |
|
| 64 |
+
| 0.0151 | 13.0 | 43342 | 0.0244 | 0 | 9 |
|
| 65 |
+
| 0.0136 | 14.0 | 46676 | 0.0234 | 0 | 15 |
|
| 66 |
+
| 0.0123 | 15.0 | 50010 | 0.0221 | 0 | 9 |
|
| 67 |
+
| 0.0113 | 16.0 | 53344 | 0.0244 | 0 | 12 |
|
| 68 |
+
| 0.01 | 17.0 | 56678 | 0.0226 | 0 | 13 |
|
| 69 |
+
| 0.0089 | 18.0 | 60012 | 0.0271 | 0 | 13 |
|
| 70 |
+
| 0.0085 | 19.0 | 63346 | 0.0248 | 0 | 13 |
|
| 71 |
+
| 0.0074 | 20.0 | 66680 | 0.0277 | 0 | 12 |
|
| 72 |
+
| 0.007 | 21.0 | 70014 | 0.0309 | 0 | 13 |
|
| 73 |
+
| 0.0066 | 22.0 | 73348 | 0.0306 | 0 | 11 |
|
| 74 |
+
| 0.0056 | 23.0 | 76682 | 0.0287 | 0 | 10 |
|
| 75 |
+
| 0.0053 | 24.0 | 80016 | 0.0312 | 0 | 12 |
|
| 76 |
+
| 0.0049 | 25.0 | 83350 | 0.0276 | 0 | 11 |
|
| 77 |
+
| 0.0053 | 26.0 | 86684 | 0.0308 | 0 | 10 |
|
| 78 |
+
| 0.0041 | 27.0 | 90018 | 0.0279 | 0 | 10 |
|
| 79 |
+
| 0.0041 | 28.0 | 93352 | 0.0292 | 0 | 11 |
|
| 80 |
+
| 0.0037 | 29.0 | 96686 | 0.0306 | 0 | 11 |
|
| 81 |
+
| 0.0035 | 30.0 | 100020 | 0.0272 | 0 | 12 |
|
| 82 |
+
| 0.0032 | 31.0 | 103354 | 0.0255 | 0 | 9 |
|
| 83 |
+
| 0.0031 | 32.0 | 106688 | 0.0293 | 0 | 10 |
|
| 84 |
+
| 0.0029 | 33.0 | 110022 | 0.0300 | 0 | 13 |
|
| 85 |
+
| 0.0026 | 34.0 | 113356 | 0.0305 | 0 | 11 |
|
| 86 |
+
| 0.0024 | 35.0 | 116690 | 0.0273 | 0 | 9 |
|
| 87 |
+
| 0.0023 | 36.0 | 120024 | 0.0284 | 0 | 10 |
|
| 88 |
+
| 0.0022 | 37.0 | 123358 | 0.0313 | 0 | 13 |
|
| 89 |
+
| 0.002 | 38.0 | 126692 | 0.0341 | 0 | 13 |
|
| 90 |
+
| 0.0017 | 39.0 | 130026 | 0.0301 | 0 | 13 |
|
| 91 |
+
| 0.0017 | 40.0 | 133360 | 0.0330 | 0 | 11 |
|
| 92 |
+
| 0.0016 | 41.0 | 136694 | 0.0344 | 0 | 11 |
|
| 93 |
+
| 0.0014 | 42.0 | 140028 | 0.0337 | 0 | 10 |
|
| 94 |
+
| 0.0013 | 43.0 | 143362 | 0.0292 | 0 | 12 |
|
| 95 |
+
| 0.0012 | 44.0 | 146696 | 0.0339 | 0 | 11 |
|
| 96 |
+
| 0.0012 | 45.0 | 150030 | 0.0330 | 0 | 11 |
|
| 97 |
+
| 0.001 | 46.0 | 153364 | 0.0307 | 0 | 11 |
|
| 98 |
+
| 0.001 | 47.0 | 156698 | 0.0330 | 0 | 10 |
|
| 99 |
+
| 0.0009 | 48.0 | 160032 | 0.0338 | 0 | 11 |
|
| 100 |
+
| 0.0009 | 49.0 | 163366 | 0.0288 | 0 | 10 |
|
| 101 |
+
| 0.0008 | 50.0 | 166700 | 0.0256 | 0 | 10 |
|
| 102 |
+
| 0.0007 | 51.0 | 170034 | 0.0284 | 0 | 11 |
|
| 103 |
+
| 0.0006 | 52.0 | 173368 | 0.0342 | 0 | 10 |
|
| 104 |
+
| 0.0006 | 53.0 | 176702 | 0.0312 | 0 | 10 |
|
| 105 |
+
| 0.0005 | 54.0 | 180036 | 0.0326 | 0 | 10 |
|
| 106 |
+
| 0.0005 | 55.0 | 183370 | 0.0304 | 0 | 11 |
|
| 107 |
+
| 0.0005 | 56.0 | 186704 | 0.0300 | 0 | 11 |
|
| 108 |
+
| 0.0004 | 57.0 | 190038 | 0.0313 | 0 | 11 |
|
| 109 |
+
| 0.0003 | 58.0 | 193372 | 0.0321 | 0 | 11 |
|
| 110 |
+
| 0.0003 | 59.0 | 196706 | 0.0316 | 0 | 10 |
|
| 111 |
+
| 0.0004 | 60.0 | 200040 | 0.0318 | 0 | 11 |
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
### Framework versions
|
| 115 |
+
|
| 116 |
+
- Transformers 4.32.1
|
| 117 |
+
- Pytorch 2.0.1+cu117
|
| 118 |
+
- Datasets 2.14.4
|
| 119 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 258643461
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:640ab93c6e6932ab1eb56e93439e8e20cf9ed1484ccd6ca0aa7250c2acf8ab00
|
| 3 |
size 258643461
|
trainer_state.json
CHANGED
|
@@ -3,1826 +3,1826 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 60.0,
|
| 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": 0.3,
|
| 19 |
-
"learning_rate": 5.
|
| 20 |
-
"loss": 3.
|
| 21 |
-
"step":
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.6,
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss": 0.
|
| 27 |
-
"step":
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.9,
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 0.
|
| 33 |
-
"step":
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 1.0,
|
| 37 |
-
"eval_loss": 0.
|
| 38 |
-
"eval_max_distance":
|
| 39 |
-
"eval_mean_distance":
|
| 40 |
-
"eval_runtime": 0.
|
| 41 |
-
"eval_samples_per_second":
|
| 42 |
-
"eval_steps_per_second":
|
| 43 |
-
"step":
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"epoch": 1.2,
|
| 47 |
-
"learning_rate": 0.
|
| 48 |
-
"loss": 0.
|
| 49 |
-
"step":
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 1.5,
|
| 53 |
-
"learning_rate": 0.
|
| 54 |
-
"loss": 0.
|
| 55 |
-
"step":
|
| 56 |
},
|
| 57 |
{
|
| 58 |
"epoch": 1.8,
|
| 59 |
-
"learning_rate": 0.
|
| 60 |
"loss": 0.1179,
|
| 61 |
-
"step":
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 2.0,
|
| 65 |
-
"eval_loss": 0.
|
| 66 |
-
"eval_max_distance":
|
| 67 |
-
"eval_mean_distance":
|
| 68 |
-
"eval_runtime": 0.
|
| 69 |
-
"eval_samples_per_second":
|
| 70 |
-
"eval_steps_per_second":
|
| 71 |
-
"step":
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 2.1,
|
| 75 |
-
"learning_rate": 0.
|
| 76 |
-
"loss": 0.
|
| 77 |
-
"step":
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 2.4,
|
| 81 |
-
"learning_rate": 0.
|
| 82 |
-
"loss": 0.
|
| 83 |
-
"step":
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 2.7,
|
| 87 |
-
"learning_rate": 0.
|
| 88 |
-
"loss": 0.
|
| 89 |
-
"step":
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 3.0,
|
| 93 |
-
"eval_loss": 0.
|
| 94 |
-
"eval_max_distance":
|
| 95 |
"eval_mean_distance": 1,
|
| 96 |
-
"eval_runtime": 0.
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second":
|
| 99 |
-
"step":
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.0,
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 0.
|
| 105 |
-
"step":
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 3.3,
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 0.
|
| 111 |
-
"step":
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 3.6,
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
"loss": 0.0653,
|
| 117 |
-
"step":
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 3.9,
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss": 0.
|
| 123 |
-
"step":
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 4.0,
|
| 127 |
-
"eval_loss": 0.
|
| 128 |
-
"eval_max_distance":
|
| 129 |
"eval_mean_distance": 1,
|
| 130 |
-
"eval_runtime": 0.
|
| 131 |
-
"eval_samples_per_second":
|
| 132 |
-
"eval_steps_per_second":
|
| 133 |
-
"step":
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 4.2,
|
| 137 |
-
"learning_rate": 0.
|
| 138 |
-
"loss": 0.
|
| 139 |
-
"step":
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 4.5,
|
| 143 |
-
"learning_rate": 0.
|
| 144 |
-
"loss": 0.
|
| 145 |
-
"step":
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 4.8,
|
| 149 |
-
"learning_rate": 0.
|
| 150 |
-
"loss": 0.
|
| 151 |
-
"step":
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 5.0,
|
| 155 |
-
"eval_loss": 0.
|
| 156 |
-
"eval_max_distance":
|
| 157 |
-
"eval_mean_distance":
|
| 158 |
-
"eval_runtime": 0.
|
| 159 |
-
"eval_samples_per_second":
|
| 160 |
-
"eval_steps_per_second":
|
| 161 |
-
"step":
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 5.1,
|
| 165 |
-
"learning_rate": 0.
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 5.4,
|
| 171 |
-
"learning_rate": 0.
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"step":
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 5.7,
|
| 177 |
-
"learning_rate": 0.
|
| 178 |
-
"loss": 0.
|
| 179 |
-
"step":
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 6.0,
|
| 183 |
-
"eval_loss": 0.
|
| 184 |
-
"eval_max_distance":
|
| 185 |
-
"eval_mean_distance":
|
| 186 |
-
"eval_runtime": 0.
|
| 187 |
-
"eval_samples_per_second":
|
| 188 |
-
"eval_steps_per_second":
|
| 189 |
-
"step":
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 6.0,
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss": 0.
|
| 195 |
-
"step":
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 6.
|
| 199 |
-
"learning_rate": 0.
|
| 200 |
-
"loss": 0.
|
| 201 |
-
"step":
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 6.
|
| 205 |
-
"learning_rate": 0.
|
| 206 |
-
"loss": 0.
|
| 207 |
-
"step":
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 6.
|
| 211 |
-
"learning_rate": 0.
|
| 212 |
-
"loss": 0.
|
| 213 |
-
"step":
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 7.0,
|
| 217 |
-
"eval_loss": 0.
|
| 218 |
-
"eval_max_distance":
|
| 219 |
-
"eval_mean_distance":
|
| 220 |
-
"eval_runtime": 0.
|
| 221 |
-
"eval_samples_per_second":
|
| 222 |
-
"eval_steps_per_second":
|
| 223 |
-
"step":
|
| 224 |
},
|
| 225 |
{
|
| 226 |
-
"epoch": 7.
|
| 227 |
-
"learning_rate": 0.
|
| 228 |
-
"loss": 0.
|
| 229 |
-
"step":
|
| 230 |
},
|
| 231 |
{
|
| 232 |
-
"epoch": 7.
|
| 233 |
-
"learning_rate": 0.
|
| 234 |
-
"loss": 0.
|
| 235 |
-
"step":
|
| 236 |
},
|
| 237 |
{
|
| 238 |
-
"epoch": 7.
|
| 239 |
-
"learning_rate": 0.
|
| 240 |
-
"loss": 0.
|
| 241 |
-
"step":
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 8.0,
|
| 245 |
-
"eval_loss": 0.
|
| 246 |
-
"eval_max_distance":
|
| 247 |
-
"eval_mean_distance":
|
| 248 |
-
"eval_runtime": 0.
|
| 249 |
-
"eval_samples_per_second":
|
| 250 |
-
"eval_steps_per_second":
|
| 251 |
-
"step":
|
| 252 |
},
|
| 253 |
{
|
| 254 |
-
"epoch": 8.
|
| 255 |
-
"learning_rate": 0.
|
| 256 |
-
"loss": 0.
|
| 257 |
-
"step":
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 8.41,
|
| 261 |
-
"learning_rate": 0.
|
| 262 |
-
"loss": 0.
|
| 263 |
-
"step":
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 8.71,
|
| 267 |
-
"learning_rate": 0.
|
| 268 |
-
"loss": 0.
|
| 269 |
-
"step":
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 9.0,
|
| 273 |
-
"eval_loss": 0.
|
| 274 |
-
"eval_max_distance":
|
| 275 |
-
"eval_mean_distance":
|
| 276 |
-
"eval_runtime": 0.
|
| 277 |
-
"eval_samples_per_second":
|
| 278 |
-
"eval_steps_per_second":
|
| 279 |
-
"step":
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 9.01,
|
| 283 |
-
"learning_rate": 0.
|
| 284 |
-
"loss": 0.
|
| 285 |
-
"step":
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 9.31,
|
| 289 |
-
"learning_rate": 0.
|
| 290 |
-
"loss": 0.
|
| 291 |
-
"step":
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 9.61,
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss": 0.
|
| 297 |
-
"step":
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 9.91,
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 0.
|
| 303 |
-
"step":
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 10.0,
|
| 307 |
-
"eval_loss": 0.
|
| 308 |
-
"eval_max_distance":
|
| 309 |
-
"eval_mean_distance":
|
| 310 |
-
"eval_runtime": 0.
|
| 311 |
-
"eval_samples_per_second":
|
| 312 |
-
"eval_steps_per_second":
|
| 313 |
-
"step":
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 10.21,
|
| 317 |
-
"learning_rate": 0.
|
| 318 |
-
"loss": 0.
|
| 319 |
-
"step":
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 10.51,
|
| 323 |
-
"learning_rate": 0.
|
| 324 |
-
"loss": 0.
|
| 325 |
-
"step":
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 10.81,
|
| 329 |
-
"learning_rate": 0.
|
| 330 |
"loss": 0.0203,
|
| 331 |
-
"step":
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 11.0,
|
| 335 |
-
"eval_loss": 0.
|
| 336 |
-
"eval_max_distance":
|
| 337 |
-
"eval_mean_distance":
|
| 338 |
-
"eval_runtime": 0.
|
| 339 |
-
"eval_samples_per_second":
|
| 340 |
-
"eval_steps_per_second":
|
| 341 |
-
"step":
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 11.11,
|
| 345 |
-
"learning_rate": 0.
|
| 346 |
-
"loss": 0.
|
| 347 |
-
"step":
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 11.41,
|
| 351 |
-
"learning_rate": 0.
|
| 352 |
-
"loss": 0.
|
| 353 |
-
"step":
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 11.71,
|
| 357 |
-
"learning_rate": 0.
|
| 358 |
-
"loss": 0.
|
| 359 |
-
"step":
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 12.0,
|
| 363 |
-
"eval_loss": 0.
|
| 364 |
-
"eval_max_distance":
|
| 365 |
-
"eval_mean_distance":
|
| 366 |
-
"eval_runtime": 0.
|
| 367 |
-
"eval_samples_per_second":
|
| 368 |
-
"eval_steps_per_second":
|
| 369 |
-
"step":
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 12.01,
|
| 373 |
-
"learning_rate": 0.
|
| 374 |
-
"loss": 0.
|
| 375 |
-
"step":
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 12.31,
|
| 379 |
-
"learning_rate": 0.
|
| 380 |
-
"loss": 0.
|
| 381 |
-
"step":
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 12.61,
|
| 385 |
-
"learning_rate": 0.
|
| 386 |
-
"loss": 0.
|
| 387 |
-
"step":
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 12.91,
|
| 391 |
-
"learning_rate": 0.
|
| 392 |
-
"loss": 0.
|
| 393 |
-
"step":
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 13.0,
|
| 397 |
-
"eval_loss": 0.
|
| 398 |
-
"eval_max_distance":
|
| 399 |
-
"eval_mean_distance":
|
| 400 |
-
"eval_runtime": 0.
|
| 401 |
-
"eval_samples_per_second":
|
| 402 |
-
"eval_steps_per_second":
|
| 403 |
-
"step":
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 13.21,
|
| 407 |
-
"learning_rate": 0.
|
| 408 |
-
"loss": 0.
|
| 409 |
-
"step":
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 13.51,
|
| 413 |
-
"learning_rate": 0.
|
| 414 |
-
"loss": 0.
|
| 415 |
-
"step":
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 13.81,
|
| 419 |
-
"learning_rate": 0.
|
| 420 |
-
"loss": 0.
|
| 421 |
-
"step":
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 14.0,
|
| 425 |
-
"eval_loss": 0.
|
| 426 |
-
"eval_max_distance":
|
| 427 |
-
"eval_mean_distance":
|
| 428 |
-
"eval_runtime": 0.
|
| 429 |
-
"eval_samples_per_second":
|
| 430 |
-
"eval_steps_per_second":
|
| 431 |
-
"step":
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 14.11,
|
| 435 |
-
"learning_rate": 0.
|
| 436 |
-
"loss": 0.
|
| 437 |
-
"step":
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 14.41,
|
| 441 |
-
"learning_rate": 0.
|
| 442 |
"loss": 0.0121,
|
| 443 |
-
"step":
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 14.71,
|
| 447 |
-
"learning_rate": 0.
|
| 448 |
-
"loss": 0.
|
| 449 |
-
"step":
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 15.0,
|
| 453 |
-
"eval_loss": 0.
|
| 454 |
-
"eval_max_distance":
|
| 455 |
-
"eval_mean_distance":
|
| 456 |
-
"eval_runtime": 0.
|
| 457 |
-
"eval_samples_per_second":
|
| 458 |
-
"eval_steps_per_second":
|
| 459 |
-
"step":
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 15.01,
|
| 463 |
-
"learning_rate": 0.
|
| 464 |
-
"loss": 0.
|
| 465 |
-
"step":
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 15.31,
|
| 469 |
-
"learning_rate": 0.
|
| 470 |
-
"loss": 0.
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 15.61,
|
| 475 |
-
"learning_rate": 0.
|
| 476 |
-
"loss": 0.
|
| 477 |
-
"step":
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 15.91,
|
| 481 |
-
"learning_rate": 0.
|
| 482 |
-
"loss": 0.
|
| 483 |
-
"step":
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 16.0,
|
| 487 |
-
"eval_loss": 0.
|
| 488 |
-
"eval_max_distance":
|
| 489 |
-
"eval_mean_distance":
|
| 490 |
-
"eval_runtime": 0.
|
| 491 |
-
"eval_samples_per_second":
|
| 492 |
-
"eval_steps_per_second":
|
| 493 |
-
"step":
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 16.21,
|
| 497 |
-
"learning_rate": 0.
|
| 498 |
-
"loss": 0.
|
| 499 |
-
"step":
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 16.51,
|
| 503 |
-
"learning_rate": 0.
|
| 504 |
-
"loss": 0.
|
| 505 |
-
"step":
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 16.81,
|
| 509 |
-
"learning_rate": 0.
|
| 510 |
-
"loss": 0.
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 17.0,
|
| 515 |
-
"eval_loss": 0.
|
| 516 |
-
"eval_max_distance":
|
| 517 |
-
"eval_mean_distance":
|
| 518 |
-
"eval_runtime": 0.
|
| 519 |
-
"eval_samples_per_second":
|
| 520 |
-
"eval_steps_per_second":
|
| 521 |
-
"step":
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 17.11,
|
| 525 |
-
"learning_rate": 0.
|
| 526 |
-
"loss": 0.
|
| 527 |
-
"step":
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 17.41,
|
| 531 |
-
"learning_rate": 0.
|
| 532 |
-
"loss": 0.
|
| 533 |
-
"step":
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 17.71,
|
| 537 |
-
"learning_rate": 0.
|
| 538 |
-
"loss": 0.
|
| 539 |
-
"step":
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 18.0,
|
| 543 |
-
"eval_loss": 0.
|
| 544 |
-
"eval_max_distance":
|
| 545 |
-
"eval_mean_distance":
|
| 546 |
-
"eval_runtime": 0.
|
| 547 |
-
"eval_samples_per_second":
|
| 548 |
-
"eval_steps_per_second":
|
| 549 |
-
"step":
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 18.01,
|
| 553 |
-
"learning_rate": 0.
|
| 554 |
-
"loss": 0.
|
| 555 |
-
"step":
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 18.31,
|
| 559 |
-
"learning_rate": 0.
|
| 560 |
"loss": 0.0075,
|
| 561 |
-
"step":
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 18.61,
|
| 565 |
-
"learning_rate": 0.
|
| 566 |
-
"loss": 0.
|
| 567 |
-
"step":
|
| 568 |
},
|
| 569 |
{
|
| 570 |
-
"epoch": 18.
|
| 571 |
-
"learning_rate": 0.
|
| 572 |
-
"loss": 0.
|
| 573 |
-
"step":
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 19.0,
|
| 577 |
-
"eval_loss": 0.
|
| 578 |
-
"eval_max_distance":
|
| 579 |
-
"eval_mean_distance":
|
| 580 |
-
"eval_runtime": 0.
|
| 581 |
-
"eval_samples_per_second":
|
| 582 |
-
"eval_steps_per_second":
|
| 583 |
-
"step":
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch": 19.
|
| 587 |
-
"learning_rate": 0.
|
| 588 |
-
"loss": 0.
|
| 589 |
-
"step":
|
| 590 |
},
|
| 591 |
{
|
| 592 |
-
"epoch": 19.
|
| 593 |
-
"learning_rate": 0.
|
| 594 |
-
"loss": 0.
|
| 595 |
-
"step":
|
| 596 |
},
|
| 597 |
{
|
| 598 |
-
"epoch": 19.
|
| 599 |
-
"learning_rate": 0.
|
| 600 |
-
"loss": 0.
|
| 601 |
-
"step":
|
| 602 |
},
|
| 603 |
{
|
| 604 |
"epoch": 20.0,
|
| 605 |
-
"eval_loss": 0.
|
| 606 |
-
"eval_max_distance":
|
| 607 |
-
"eval_mean_distance":
|
| 608 |
-
"eval_runtime": 0.
|
| 609 |
-
"eval_samples_per_second":
|
| 610 |
-
"eval_steps_per_second":
|
| 611 |
-
"step":
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch": 20.
|
| 615 |
-
"learning_rate": 0.
|
| 616 |
-
"loss": 0.
|
| 617 |
-
"step":
|
| 618 |
},
|
| 619 |
{
|
| 620 |
-
"epoch": 20.
|
| 621 |
-
"learning_rate": 0.
|
| 622 |
-
"loss": 0.
|
| 623 |
-
"step":
|
| 624 |
},
|
| 625 |
{
|
| 626 |
-
"epoch": 20.
|
| 627 |
-
"learning_rate": 0.
|
| 628 |
-
"loss": 0.
|
| 629 |
-
"step":
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 21.0,
|
| 633 |
-
"eval_loss": 0.
|
| 634 |
-
"eval_max_distance":
|
| 635 |
-
"eval_mean_distance":
|
| 636 |
-
"eval_runtime": 0.
|
| 637 |
-
"eval_samples_per_second":
|
| 638 |
-
"eval_steps_per_second":
|
| 639 |
-
"step":
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 21.
|
| 643 |
-
"learning_rate": 0.
|
| 644 |
-
"loss": 0.
|
| 645 |
-
"step":
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch": 21.
|
| 649 |
-
"learning_rate": 0.
|
| 650 |
-
"loss": 0.
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch": 21.
|
| 655 |
-
"learning_rate": 0.
|
| 656 |
-
"loss": 0.
|
| 657 |
-
"step":
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch": 21.
|
| 661 |
-
"learning_rate": 0.
|
| 662 |
-
"loss": 0.
|
| 663 |
-
"step":
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 22.0,
|
| 667 |
-
"eval_loss": 0.
|
| 668 |
-
"eval_max_distance":
|
| 669 |
-
"eval_mean_distance":
|
| 670 |
-
"eval_runtime": 0.
|
| 671 |
-
"eval_samples_per_second":
|
| 672 |
-
"eval_steps_per_second":
|
| 673 |
-
"step":
|
| 674 |
},
|
| 675 |
{
|
| 676 |
-
"epoch": 22.
|
| 677 |
-
"learning_rate": 0.
|
| 678 |
-
"loss": 0.
|
| 679 |
-
"step":
|
| 680 |
},
|
| 681 |
{
|
| 682 |
-
"epoch": 22.
|
| 683 |
-
"learning_rate": 0.
|
| 684 |
-
"loss": 0.
|
| 685 |
-
"step":
|
| 686 |
},
|
| 687 |
{
|
| 688 |
-
"epoch": 22.
|
| 689 |
-
"learning_rate": 0.
|
| 690 |
-
"loss": 0.
|
| 691 |
-
"step":
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 23.0,
|
| 695 |
-
"eval_loss": 0.
|
| 696 |
-
"eval_max_distance":
|
| 697 |
"eval_mean_distance": 0,
|
| 698 |
-
"eval_runtime": 0.
|
| 699 |
-
"eval_samples_per_second":
|
| 700 |
-
"eval_steps_per_second":
|
| 701 |
-
"step":
|
| 702 |
},
|
| 703 |
{
|
| 704 |
-
"epoch": 23.
|
| 705 |
-
"learning_rate": 0.
|
| 706 |
-
"loss": 0.
|
| 707 |
-
"step":
|
| 708 |
},
|
| 709 |
{
|
| 710 |
-
"epoch": 23.
|
| 711 |
-
"learning_rate": 0.
|
| 712 |
-
"loss": 0.
|
| 713 |
-
"step":
|
| 714 |
},
|
| 715 |
{
|
| 716 |
-
"epoch": 23.
|
| 717 |
-
"learning_rate": 0.
|
| 718 |
-
"loss": 0.
|
| 719 |
-
"step":
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 24.0,
|
| 723 |
-
"eval_loss": 0.
|
| 724 |
-
"eval_max_distance":
|
| 725 |
-
"eval_mean_distance":
|
| 726 |
-
"eval_runtime": 0.
|
| 727 |
-
"eval_samples_per_second":
|
| 728 |
-
"eval_steps_per_second":
|
| 729 |
-
"step":
|
| 730 |
},
|
| 731 |
{
|
| 732 |
-
"epoch": 24.
|
| 733 |
-
"learning_rate": 0.
|
| 734 |
-
"loss": 0.
|
| 735 |
-
"step":
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch": 24.
|
| 739 |
-
"learning_rate": 0.
|
| 740 |
-
"loss": 0.
|
| 741 |
-
"step":
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"epoch": 24.
|
| 745 |
-
"learning_rate": 0.
|
| 746 |
-
"loss": 0.
|
| 747 |
-
"step":
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 24.92,
|
| 751 |
-
"learning_rate": 0.
|
| 752 |
-
"loss": 0.
|
| 753 |
-
"step":
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 25.0,
|
| 757 |
-
"eval_loss": 0.
|
| 758 |
-
"eval_max_distance":
|
| 759 |
-
"eval_mean_distance":
|
| 760 |
-
"eval_runtime": 0.
|
| 761 |
-
"eval_samples_per_second":
|
| 762 |
-
"eval_steps_per_second":
|
| 763 |
-
"step":
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 25.22,
|
| 767 |
-
"learning_rate": 0.
|
| 768 |
-
"loss": 0.
|
| 769 |
-
"step":
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 25.52,
|
| 773 |
-
"learning_rate": 0.
|
| 774 |
"loss": 0.0045,
|
| 775 |
-
"step":
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 25.82,
|
| 779 |
-
"learning_rate": 0.
|
| 780 |
-
"loss": 0.
|
| 781 |
-
"step":
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 26.0,
|
| 785 |
-
"eval_loss": 0.
|
| 786 |
-
"eval_max_distance":
|
| 787 |
-
"eval_mean_distance":
|
| 788 |
-
"eval_runtime": 0.
|
| 789 |
-
"eval_samples_per_second":
|
| 790 |
-
"eval_steps_per_second":
|
| 791 |
-
"step":
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 26.12,
|
| 795 |
-
"learning_rate": 0.
|
| 796 |
-
"loss": 0.
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 26.42,
|
| 801 |
-
"learning_rate": 0.
|
| 802 |
-
"loss": 0.
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 26.72,
|
| 807 |
-
"learning_rate": 0.
|
| 808 |
-
"loss": 0.
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
"epoch": 27.0,
|
| 813 |
-
"eval_loss": 0.
|
| 814 |
-
"eval_max_distance":
|
| 815 |
-
"eval_mean_distance":
|
| 816 |
-
"eval_runtime": 0.
|
| 817 |
-
"eval_samples_per_second":
|
| 818 |
-
"eval_steps_per_second":
|
| 819 |
-
"step":
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 27.02,
|
| 823 |
-
"learning_rate": 0.
|
| 824 |
"loss": 0.0043,
|
| 825 |
-
"step":
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 27.32,
|
| 829 |
-
"learning_rate": 0.
|
| 830 |
-
"loss": 0.
|
| 831 |
-
"step":
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 27.62,
|
| 835 |
-
"learning_rate": 0.
|
| 836 |
-
"loss": 0.
|
| 837 |
-
"step":
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 27.92,
|
| 841 |
-
"learning_rate": 0.
|
| 842 |
-
"loss": 0.
|
| 843 |
-
"step":
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 28.0,
|
| 847 |
-
"eval_loss": 0.
|
| 848 |
-
"eval_max_distance":
|
| 849 |
-
"eval_mean_distance":
|
| 850 |
-
"eval_runtime": 0.
|
| 851 |
-
"eval_samples_per_second":
|
| 852 |
-
"eval_steps_per_second":
|
| 853 |
-
"step":
|
| 854 |
},
|
| 855 |
{
|
| 856 |
"epoch": 28.22,
|
| 857 |
-
"learning_rate": 0.
|
| 858 |
"loss": 0.0037,
|
| 859 |
-
"step":
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 28.52,
|
| 863 |
-
"learning_rate": 0.
|
| 864 |
-
"loss": 0.
|
| 865 |
-
"step":
|
| 866 |
},
|
| 867 |
{
|
| 868 |
"epoch": 28.82,
|
| 869 |
-
"learning_rate": 0.
|
| 870 |
-
"loss": 0.
|
| 871 |
-
"step":
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 29.0,
|
| 875 |
-
"eval_loss": 0.
|
| 876 |
-
"eval_max_distance":
|
| 877 |
-
"eval_mean_distance":
|
| 878 |
-
"eval_runtime": 0.
|
| 879 |
-
"eval_samples_per_second":
|
| 880 |
-
"eval_steps_per_second":
|
| 881 |
-
"step":
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 29.12,
|
| 885 |
-
"learning_rate": 0.
|
| 886 |
-
"loss": 0.
|
| 887 |
-
"step":
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 29.42,
|
| 891 |
-
"learning_rate": 0.
|
| 892 |
"loss": 0.0033,
|
| 893 |
-
"step":
|
| 894 |
},
|
| 895 |
{
|
| 896 |
"epoch": 29.72,
|
| 897 |
-
"learning_rate": 0.
|
| 898 |
-
"loss": 0.
|
| 899 |
-
"step":
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 30.0,
|
| 903 |
-
"eval_loss": 0.
|
| 904 |
-
"eval_max_distance":
|
| 905 |
-
"eval_mean_distance":
|
| 906 |
-
"eval_runtime": 0.
|
| 907 |
-
"eval_samples_per_second":
|
| 908 |
-
"eval_steps_per_second":
|
| 909 |
-
"step":
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 30.02,
|
| 913 |
-
"learning_rate": 0.
|
| 914 |
-
"loss": 0.
|
| 915 |
-
"step":
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 30.32,
|
| 919 |
-
"learning_rate": 0.
|
| 920 |
"loss": 0.003,
|
| 921 |
-
"step":
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 30.62,
|
| 925 |
-
"learning_rate": 0.
|
| 926 |
-
"loss": 0.
|
| 927 |
-
"step":
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 30.92,
|
| 931 |
-
"learning_rate": 0.
|
| 932 |
-
"loss": 0.
|
| 933 |
-
"step":
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 31.0,
|
| 937 |
-
"eval_loss": 0.
|
| 938 |
-
"eval_max_distance":
|
| 939 |
-
"eval_mean_distance":
|
| 940 |
-
"eval_runtime": 0.
|
| 941 |
-
"eval_samples_per_second":
|
| 942 |
-
"eval_steps_per_second":
|
| 943 |
-
"step":
|
| 944 |
},
|
| 945 |
{
|
| 946 |
"epoch": 31.22,
|
| 947 |
-
"learning_rate": 0.
|
| 948 |
-
"loss": 0.
|
| 949 |
-
"step":
|
| 950 |
},
|
| 951 |
{
|
| 952 |
-
"epoch": 31.
|
| 953 |
-
"learning_rate": 0.
|
| 954 |
-
"loss": 0.
|
| 955 |
-
"step":
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"epoch": 31.
|
| 959 |
-
"learning_rate": 0.
|
| 960 |
-
"loss": 0.
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
"epoch": 32.0,
|
| 965 |
-
"eval_loss": 0.
|
| 966 |
-
"eval_max_distance":
|
| 967 |
-
"eval_mean_distance":
|
| 968 |
-
"eval_runtime": 0.
|
| 969 |
-
"eval_samples_per_second":
|
| 970 |
-
"eval_steps_per_second":
|
| 971 |
-
"step":
|
| 972 |
},
|
| 973 |
{
|
| 974 |
-
"epoch": 32.
|
| 975 |
-
"learning_rate": 0.
|
| 976 |
"loss": 0.0028,
|
| 977 |
-
"step":
|
| 978 |
},
|
| 979 |
{
|
| 980 |
-
"epoch": 32.
|
| 981 |
-
"learning_rate": 0.
|
| 982 |
-
"loss": 0.
|
| 983 |
-
"step":
|
| 984 |
},
|
| 985 |
{
|
| 986 |
-
"epoch": 32.
|
| 987 |
-
"learning_rate": 0.
|
| 988 |
-
"loss": 0.
|
| 989 |
-
"step":
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 33.0,
|
| 993 |
-
"eval_loss": 0.
|
| 994 |
-
"eval_max_distance":
|
| 995 |
"eval_mean_distance": 0,
|
| 996 |
-
"eval_runtime": 0.
|
| 997 |
-
"eval_samples_per_second":
|
| 998 |
-
"eval_steps_per_second":
|
| 999 |
-
"step":
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
-
"epoch": 33.
|
| 1003 |
-
"learning_rate": 0.
|
| 1004 |
-
"loss": 0.
|
| 1005 |
-
"step":
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
-
"epoch": 33.
|
| 1009 |
-
"learning_rate": 0.
|
| 1010 |
-
"loss": 0.
|
| 1011 |
-
"step":
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
-
"epoch": 33.
|
| 1015 |
-
"learning_rate": 0.
|
| 1016 |
"loss": 0.0026,
|
| 1017 |
-
"step":
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
-
"epoch": 33.
|
| 1021 |
-
"learning_rate": 0.
|
| 1022 |
-
"loss": 0.
|
| 1023 |
-
"step":
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 34.0,
|
| 1027 |
-
"eval_loss": 0.
|
| 1028 |
-
"eval_max_distance":
|
| 1029 |
-
"eval_mean_distance":
|
| 1030 |
-
"eval_runtime": 0.
|
| 1031 |
-
"eval_samples_per_second":
|
| 1032 |
-
"eval_steps_per_second":
|
| 1033 |
-
"step":
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
-
"epoch": 34.
|
| 1037 |
-
"learning_rate": 0.
|
| 1038 |
-
"loss": 0.
|
| 1039 |
-
"step":
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
-
"epoch": 34.
|
| 1043 |
-
"learning_rate": 0.
|
| 1044 |
"loss": 0.0023,
|
| 1045 |
-
"step":
|
| 1046 |
},
|
| 1047 |
{
|
| 1048 |
-
"epoch": 34.
|
| 1049 |
-
"learning_rate": 0.
|
| 1050 |
-
"loss": 0.
|
| 1051 |
-
"step":
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
"epoch": 35.0,
|
| 1055 |
-
"eval_loss": 0.
|
| 1056 |
-
"eval_max_distance":
|
| 1057 |
"eval_mean_distance": 0,
|
| 1058 |
-
"eval_runtime": 0.
|
| 1059 |
-
"eval_samples_per_second":
|
| 1060 |
-
"eval_steps_per_second":
|
| 1061 |
-
"step":
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
-
"epoch": 35.
|
| 1065 |
-
"learning_rate": 0.
|
| 1066 |
-
"loss": 0.
|
| 1067 |
-
"step":
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
-
"epoch": 35.
|
| 1071 |
-
"learning_rate": 0.
|
| 1072 |
-
"loss": 0.
|
| 1073 |
-
"step":
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
-
"epoch": 35.
|
| 1077 |
-
"learning_rate": 0.
|
| 1078 |
"loss": 0.0023,
|
| 1079 |
-
"step":
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 36.0,
|
| 1083 |
-
"eval_loss": 0.
|
| 1084 |
-
"eval_max_distance":
|
| 1085 |
"eval_mean_distance": 0,
|
| 1086 |
-
"eval_runtime": 0.
|
| 1087 |
-
"eval_samples_per_second":
|
| 1088 |
-
"eval_steps_per_second":
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch": 36.
|
| 1093 |
-
"learning_rate": 0.
|
| 1094 |
-
"loss": 0.
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch": 36.
|
| 1099 |
-
"learning_rate": 0.
|
| 1100 |
-
"loss": 0.
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch": 36.
|
| 1105 |
-
"learning_rate": 0.
|
| 1106 |
-
"loss": 0.
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch": 36.
|
| 1111 |
-
"learning_rate": 0.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 37.0,
|
| 1117 |
-
"eval_loss": 0.
|
| 1118 |
-
"eval_max_distance":
|
| 1119 |
-
"eval_mean_distance":
|
| 1120 |
-
"eval_runtime": 0.
|
| 1121 |
-
"eval_samples_per_second":
|
| 1122 |
-
"eval_steps_per_second":
|
| 1123 |
-
"step":
|
| 1124 |
},
|
| 1125 |
{
|
| 1126 |
-
"epoch": 37.
|
| 1127 |
-
"learning_rate": 0.
|
| 1128 |
-
"loss": 0.
|
| 1129 |
-
"step":
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
-
"epoch": 37.
|
| 1133 |
-
"learning_rate": 0.
|
| 1134 |
"loss": 0.0019,
|
| 1135 |
-
"step":
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
-
"epoch": 37.
|
| 1139 |
-
"learning_rate": 0.
|
| 1140 |
-
"loss": 0.
|
| 1141 |
-
"step":
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 38.0,
|
| 1145 |
-
"eval_loss": 0.
|
| 1146 |
-
"eval_max_distance":
|
| 1147 |
-
"eval_mean_distance":
|
| 1148 |
-
"eval_runtime": 0.
|
| 1149 |
-
"eval_samples_per_second":
|
| 1150 |
-
"eval_steps_per_second":
|
| 1151 |
-
"step":
|
| 1152 |
},
|
| 1153 |
{
|
| 1154 |
-
"epoch": 38.
|
| 1155 |
-
"learning_rate": 0.
|
| 1156 |
-
"loss": 0.
|
| 1157 |
-
"step":
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
-
"epoch": 38.
|
| 1161 |
-
"learning_rate": 0.
|
| 1162 |
"loss": 0.0018,
|
| 1163 |
-
"step":
|
| 1164 |
},
|
| 1165 |
{
|
| 1166 |
-
"epoch": 38.
|
| 1167 |
-
"learning_rate": 0.
|
| 1168 |
"loss": 0.0017,
|
| 1169 |
-
"step":
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 39.0,
|
| 1173 |
-
"eval_loss": 0.
|
| 1174 |
-
"eval_max_distance":
|
| 1175 |
"eval_mean_distance": 0,
|
| 1176 |
-
"eval_runtime": 0.
|
| 1177 |
-
"eval_samples_per_second":
|
| 1178 |
-
"eval_steps_per_second":
|
| 1179 |
-
"step":
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
-
"epoch": 39.
|
| 1183 |
-
"learning_rate": 0.
|
| 1184 |
-
"loss": 0.
|
| 1185 |
-
"step":
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
-
"epoch": 39.
|
| 1189 |
-
"learning_rate": 0.
|
| 1190 |
"loss": 0.0016,
|
| 1191 |
-
"step":
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
-
"epoch": 39.
|
| 1195 |
-
"learning_rate": 0.
|
| 1196 |
"loss": 0.0017,
|
| 1197 |
-
"step":
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
-
"epoch": 39.
|
| 1201 |
-
"learning_rate": 0.
|
| 1202 |
"loss": 0.0017,
|
| 1203 |
-
"step":
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 40.0,
|
| 1207 |
-
"eval_loss": 0.
|
| 1208 |
-
"eval_max_distance":
|
| 1209 |
"eval_mean_distance": 0,
|
| 1210 |
-
"eval_runtime": 0.
|
| 1211 |
-
"eval_samples_per_second":
|
| 1212 |
-
"eval_steps_per_second":
|
| 1213 |
-
"step":
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
-
"epoch": 40.
|
| 1217 |
-
"learning_rate": 0.
|
| 1218 |
"loss": 0.0015,
|
| 1219 |
-
"step":
|
| 1220 |
},
|
| 1221 |
{
|
| 1222 |
-
"epoch": 40.
|
| 1223 |
-
"learning_rate": 0.
|
| 1224 |
-
"loss": 0.
|
| 1225 |
-
"step":
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
-
"epoch": 40.
|
| 1229 |
-
"learning_rate": 0.
|
| 1230 |
"loss": 0.0016,
|
| 1231 |
-
"step":
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
"epoch": 41.0,
|
| 1235 |
-
"eval_loss": 0.
|
| 1236 |
-
"eval_max_distance":
|
| 1237 |
"eval_mean_distance": 0,
|
| 1238 |
-
"eval_runtime": 0.
|
| 1239 |
-
"eval_samples_per_second":
|
| 1240 |
-
"eval_steps_per_second":
|
| 1241 |
-
"step":
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
-
"epoch": 41.
|
| 1245 |
-
"learning_rate": 0.
|
| 1246 |
"loss": 0.0015,
|
| 1247 |
-
"step":
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
"epoch": 41.43,
|
| 1251 |
-
"learning_rate": 0.
|
| 1252 |
"loss": 0.0014,
|
| 1253 |
-
"step":
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 41.73,
|
| 1257 |
-
"learning_rate": 0.
|
| 1258 |
-
"loss": 0.
|
| 1259 |
-
"step":
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 42.0,
|
| 1263 |
-
"eval_loss": 0.
|
| 1264 |
-
"eval_max_distance":
|
| 1265 |
-
"eval_mean_distance":
|
| 1266 |
-
"eval_runtime": 0.
|
| 1267 |
-
"eval_samples_per_second":
|
| 1268 |
-
"eval_steps_per_second":
|
| 1269 |
-
"step":
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 42.03,
|
| 1273 |
-
"learning_rate": 0.
|
| 1274 |
-
"loss": 0.
|
| 1275 |
-
"step":
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 42.33,
|
| 1279 |
-
"learning_rate": 0.
|
| 1280 |
-
"loss": 0.
|
| 1281 |
-
"step":
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 42.63,
|
| 1285 |
-
"learning_rate": 0.
|
| 1286 |
-
"loss": 0.
|
| 1287 |
-
"step":
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 42.93,
|
| 1291 |
-
"learning_rate": 0.
|
| 1292 |
-
"loss": 0.
|
| 1293 |
-
"step":
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 43.0,
|
| 1297 |
-
"eval_loss": 0.
|
| 1298 |
-
"eval_max_distance":
|
| 1299 |
"eval_mean_distance": 0,
|
| 1300 |
-
"eval_runtime": 0.
|
| 1301 |
-
"eval_samples_per_second":
|
| 1302 |
-
"eval_steps_per_second":
|
| 1303 |
-
"step":
|
| 1304 |
},
|
| 1305 |
{
|
| 1306 |
"epoch": 43.23,
|
| 1307 |
-
"learning_rate": 0.
|
| 1308 |
-
"loss": 0.
|
| 1309 |
-
"step":
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 43.53,
|
| 1313 |
-
"learning_rate": 0.
|
| 1314 |
-
"loss": 0.
|
| 1315 |
-
"step":
|
| 1316 |
},
|
| 1317 |
{
|
| 1318 |
-
"epoch": 43.
|
| 1319 |
-
"learning_rate": 0.
|
| 1320 |
-
"loss": 0.
|
| 1321 |
-
"step":
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"epoch": 44.0,
|
| 1325 |
-
"eval_loss": 0.
|
| 1326 |
-
"eval_max_distance":
|
| 1327 |
-
"eval_mean_distance":
|
| 1328 |
-
"eval_runtime": 0.
|
| 1329 |
-
"eval_samples_per_second":
|
| 1330 |
-
"eval_steps_per_second":
|
| 1331 |
-
"step":
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
-
"epoch": 44.
|
| 1335 |
-
"learning_rate": 0.
|
| 1336 |
"loss": 0.0012,
|
| 1337 |
-
"step":
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
-
"epoch": 44.
|
| 1341 |
-
"learning_rate": 0.
|
| 1342 |
"loss": 0.0011,
|
| 1343 |
-
"step":
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
-
"epoch": 44.
|
| 1347 |
-
"learning_rate": 0.
|
| 1348 |
-
"loss": 0.
|
| 1349 |
-
"step":
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 45.0,
|
| 1353 |
-
"eval_loss": 0.
|
| 1354 |
-
"eval_max_distance":
|
| 1355 |
-
"eval_mean_distance":
|
| 1356 |
-
"eval_runtime": 0.
|
| 1357 |
-
"eval_samples_per_second":
|
| 1358 |
-
"eval_steps_per_second":
|
| 1359 |
-
"step":
|
| 1360 |
-
},
|
| 1361 |
-
{
|
| 1362 |
-
"epoch": 45.03,
|
| 1363 |
-
"learning_rate": 0.0002772724209958898,
|
| 1364 |
-
"loss": 0.0011,
|
| 1365 |
-
"step": 148500
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
-
"epoch": 45.
|
| 1369 |
-
"learning_rate": 0.
|
| 1370 |
-
"loss": 0.
|
| 1371 |
-
"step":
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
-
"epoch": 45.
|
| 1375 |
-
"learning_rate": 0.
|
| 1376 |
"loss": 0.001,
|
| 1377 |
-
"step":
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
-
"epoch": 45.
|
| 1381 |
-
"learning_rate": 0.
|
| 1382 |
"loss": 0.0011,
|
| 1383 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1384 |
},
|
| 1385 |
{
|
| 1386 |
"epoch": 46.0,
|
| 1387 |
-
"eval_loss": 0.
|
| 1388 |
-
"eval_max_distance":
|
| 1389 |
"eval_mean_distance": 0,
|
| 1390 |
-
"eval_runtime": 0.
|
| 1391 |
-
"eval_samples_per_second":
|
| 1392 |
-
"eval_steps_per_second":
|
| 1393 |
-
"step":
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
-
"epoch": 46.
|
| 1397 |
-
"learning_rate": 0.
|
| 1398 |
"loss": 0.001,
|
| 1399 |
-
"step":
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
-
"epoch": 46.
|
| 1403 |
-
"learning_rate": 0.
|
| 1404 |
-
"loss": 0.
|
| 1405 |
-
"step":
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
-
"epoch": 46.
|
| 1409 |
-
"learning_rate": 0.
|
| 1410 |
"loss": 0.001,
|
| 1411 |
-
"step":
|
| 1412 |
},
|
| 1413 |
{
|
| 1414 |
"epoch": 47.0,
|
| 1415 |
-
"eval_loss": 0.
|
| 1416 |
-
"eval_max_distance":
|
| 1417 |
"eval_mean_distance": 0,
|
| 1418 |
-
"eval_runtime": 0.
|
| 1419 |
-
"eval_samples_per_second":
|
| 1420 |
-
"eval_steps_per_second":
|
| 1421 |
-
"step":
|
| 1422 |
},
|
| 1423 |
{
|
| 1424 |
-
"epoch": 47.
|
| 1425 |
-
"learning_rate": 0.
|
| 1426 |
-
"loss": 0.
|
| 1427 |
-
"step":
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
-
"epoch": 47.
|
| 1431 |
-
"learning_rate": 0.
|
| 1432 |
"loss": 0.0009,
|
| 1433 |
-
"step":
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
-
"epoch": 47.
|
| 1437 |
-
"learning_rate": 0.
|
| 1438 |
"loss": 0.0009,
|
| 1439 |
-
"step":
|
| 1440 |
},
|
| 1441 |
{
|
| 1442 |
"epoch": 48.0,
|
| 1443 |
-
"eval_loss": 0.
|
| 1444 |
-
"eval_max_distance":
|
| 1445 |
"eval_mean_distance": 0,
|
| 1446 |
-
"eval_runtime": 0.
|
| 1447 |
-
"eval_samples_per_second":
|
| 1448 |
-
"eval_steps_per_second":
|
| 1449 |
-
"step":
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
-
"epoch": 48.
|
| 1453 |
-
"learning_rate": 0.
|
| 1454 |
"loss": 0.0009,
|
| 1455 |
-
"step":
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
-
"epoch": 48.
|
| 1459 |
-
"learning_rate": 0.
|
| 1460 |
"loss": 0.0008,
|
| 1461 |
-
"step":
|
| 1462 |
},
|
| 1463 |
{
|
| 1464 |
-
"epoch": 48.
|
| 1465 |
-
"learning_rate": 0.
|
| 1466 |
-
"loss": 0.
|
| 1467 |
-
"step":
|
| 1468 |
},
|
| 1469 |
{
|
| 1470 |
-
"epoch": 48.
|
| 1471 |
-
"learning_rate": 0.
|
| 1472 |
-
"loss": 0.
|
| 1473 |
-
"step":
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 49.0,
|
| 1477 |
-
"eval_loss": 0.
|
| 1478 |
-
"eval_max_distance":
|
| 1479 |
-
"eval_mean_distance":
|
| 1480 |
-
"eval_runtime": 0.
|
| 1481 |
-
"eval_samples_per_second":
|
| 1482 |
-
"eval_steps_per_second":
|
| 1483 |
-
"step":
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
-
"epoch": 49.
|
| 1487 |
-
"learning_rate": 0.
|
| 1488 |
"loss": 0.0008,
|
| 1489 |
-
"step":
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
-
"epoch": 49.
|
| 1493 |
-
"learning_rate": 0.
|
| 1494 |
"loss": 0.0008,
|
| 1495 |
-
"step":
|
| 1496 |
},
|
| 1497 |
{
|
| 1498 |
-
"epoch": 49.
|
| 1499 |
-
"learning_rate": 0.
|
| 1500 |
"loss": 0.0008,
|
| 1501 |
-
"step":
|
| 1502 |
},
|
| 1503 |
{
|
| 1504 |
"epoch": 50.0,
|
| 1505 |
-
"eval_loss": 0.
|
| 1506 |
-
"eval_max_distance":
|
| 1507 |
"eval_mean_distance": 0,
|
| 1508 |
-
"eval_runtime": 0.
|
| 1509 |
-
"eval_samples_per_second":
|
| 1510 |
-
"eval_steps_per_second":
|
| 1511 |
-
"step":
|
| 1512 |
},
|
| 1513 |
{
|
| 1514 |
-
"epoch": 50.
|
| 1515 |
-
"learning_rate": 0.
|
| 1516 |
-
"loss": 0.
|
| 1517 |
-
"step":
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
-
"epoch": 50.
|
| 1521 |
-
"learning_rate": 0.
|
| 1522 |
"loss": 0.0007,
|
| 1523 |
-
"step":
|
| 1524 |
},
|
| 1525 |
{
|
| 1526 |
-
"epoch": 50.
|
| 1527 |
-
"learning_rate": 0.
|
| 1528 |
-
"loss": 0.
|
| 1529 |
-
"step":
|
| 1530 |
},
|
| 1531 |
{
|
| 1532 |
"epoch": 51.0,
|
| 1533 |
-
"eval_loss": 0.
|
| 1534 |
-
"eval_max_distance":
|
| 1535 |
"eval_mean_distance": 0,
|
| 1536 |
-
"eval_runtime": 0.
|
| 1537 |
-
"eval_samples_per_second":
|
| 1538 |
-
"eval_steps_per_second":
|
| 1539 |
-
"step":
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
-
"epoch": 51.
|
| 1543 |
-
"learning_rate": 0.
|
| 1544 |
"loss": 0.0007,
|
| 1545 |
-
"step":
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
-
"epoch": 51.
|
| 1549 |
-
"learning_rate": 0.
|
| 1550 |
"loss": 0.0007,
|
| 1551 |
-
"step":
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
-
"epoch": 51.
|
| 1555 |
-
"learning_rate": 0.
|
| 1556 |
-
"loss": 0.
|
| 1557 |
-
"step":
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
-
"epoch": 51.
|
| 1561 |
-
"learning_rate": 0.
|
| 1562 |
-
"loss": 0.
|
| 1563 |
-
"step":
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 52.0,
|
| 1567 |
-
"eval_loss": 0.
|
| 1568 |
-
"eval_max_distance":
|
| 1569 |
"eval_mean_distance": 0,
|
| 1570 |
-
"eval_runtime": 0.
|
| 1571 |
-
"eval_samples_per_second":
|
| 1572 |
-
"eval_steps_per_second":
|
| 1573 |
-
"step":
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
-
"epoch": 52.
|
| 1577 |
-
"learning_rate": 0.
|
| 1578 |
"loss": 0.0006,
|
| 1579 |
-
"step":
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
-
"epoch": 52.
|
| 1583 |
-
"learning_rate": 0.
|
| 1584 |
"loss": 0.0006,
|
| 1585 |
-
"step":
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
-
"epoch": 52.
|
| 1589 |
-
"learning_rate": 0.
|
| 1590 |
"loss": 0.0006,
|
| 1591 |
-
"step":
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 53.0,
|
| 1595 |
-
"eval_loss": 0.
|
| 1596 |
-
"eval_max_distance":
|
| 1597 |
-
"eval_mean_distance":
|
| 1598 |
-
"eval_runtime": 0.
|
| 1599 |
-
"eval_samples_per_second":
|
| 1600 |
-
"eval_steps_per_second":
|
| 1601 |
-
"step":
|
| 1602 |
},
|
| 1603 |
{
|
| 1604 |
-
"epoch": 53.
|
| 1605 |
-
"learning_rate": 0.
|
| 1606 |
"loss": 0.0006,
|
| 1607 |
-
"step":
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
-
"epoch": 53.
|
| 1611 |
-
"learning_rate": 0.
|
| 1612 |
-
"loss": 0.
|
| 1613 |
-
"step":
|
| 1614 |
},
|
| 1615 |
{
|
| 1616 |
-
"epoch": 53.
|
| 1617 |
-
"learning_rate": 0.
|
| 1618 |
"loss": 0.0005,
|
| 1619 |
-
"step":
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 54.0,
|
| 1623 |
-
"eval_loss": 0.
|
| 1624 |
-
"eval_max_distance":
|
| 1625 |
"eval_mean_distance": 0,
|
| 1626 |
-
"eval_runtime": 0.
|
| 1627 |
-
"eval_samples_per_second":
|
| 1628 |
-
"eval_steps_per_second":
|
| 1629 |
-
"step":
|
| 1630 |
},
|
| 1631 |
{
|
| 1632 |
-
"epoch": 54.
|
| 1633 |
-
"learning_rate": 0.
|
| 1634 |
"loss": 0.0005,
|
| 1635 |
-
"step":
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
-
"epoch": 54.
|
| 1639 |
-
"learning_rate": 0.
|
| 1640 |
-
"loss": 0.
|
| 1641 |
-
"step":
|
| 1642 |
},
|
| 1643 |
{
|
| 1644 |
-
"epoch": 54.
|
| 1645 |
-
"learning_rate": 9.
|
| 1646 |
"loss": 0.0005,
|
| 1647 |
-
"step":
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
-
"epoch": 54.
|
| 1651 |
-
"learning_rate": 9.
|
| 1652 |
-
"loss": 0.
|
| 1653 |
-
"step":
|
| 1654 |
},
|
| 1655 |
{
|
| 1656 |
"epoch": 55.0,
|
| 1657 |
-
"eval_loss": 0.
|
| 1658 |
-
"eval_max_distance":
|
| 1659 |
"eval_mean_distance": 0,
|
| 1660 |
-
"eval_runtime": 0.
|
| 1661 |
-
"eval_samples_per_second":
|
| 1662 |
-
"eval_steps_per_second":
|
| 1663 |
-
"step":
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
-
"epoch": 55.
|
| 1667 |
-
"learning_rate": 8.
|
| 1668 |
"loss": 0.0005,
|
| 1669 |
-
"step":
|
| 1670 |
},
|
| 1671 |
{
|
| 1672 |
-
"epoch": 55.
|
| 1673 |
-
"learning_rate": 8.
|
| 1674 |
"loss": 0.0004,
|
| 1675 |
-
"step":
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
-
"epoch": 55.
|
| 1679 |
-
"learning_rate": 7.
|
| 1680 |
"loss": 0.0005,
|
| 1681 |
-
"step":
|
| 1682 |
},
|
| 1683 |
{
|
| 1684 |
"epoch": 56.0,
|
| 1685 |
-
"eval_loss": 0.
|
| 1686 |
-
"eval_max_distance":
|
| 1687 |
"eval_mean_distance": 0,
|
| 1688 |
-
"eval_runtime": 0.
|
| 1689 |
-
"eval_samples_per_second":
|
| 1690 |
-
"eval_steps_per_second":
|
| 1691 |
-
"step":
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
-
"epoch": 56.
|
| 1695 |
-
"learning_rate": 7.
|
| 1696 |
"loss": 0.0004,
|
| 1697 |
-
"step":
|
| 1698 |
},
|
| 1699 |
{
|
| 1700 |
-
"epoch": 56.
|
| 1701 |
-
"learning_rate": 6.
|
| 1702 |
"loss": 0.0004,
|
| 1703 |
-
"step":
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
-
"epoch": 56.
|
| 1707 |
-
"learning_rate": 6.
|
| 1708 |
"loss": 0.0004,
|
| 1709 |
-
"step":
|
| 1710 |
},
|
| 1711 |
{
|
| 1712 |
"epoch": 57.0,
|
| 1713 |
-
"eval_loss": 0.
|
| 1714 |
-
"eval_max_distance":
|
| 1715 |
"eval_mean_distance": 0,
|
| 1716 |
-
"eval_runtime": 0.
|
| 1717 |
-
"eval_samples_per_second":
|
| 1718 |
-
"eval_steps_per_second":
|
| 1719 |
-
"step":
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
-
"epoch": 57.
|
| 1723 |
-
"learning_rate": 5.
|
| 1724 |
"loss": 0.0004,
|
| 1725 |
-
"step":
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
-
"epoch": 57.
|
| 1729 |
-
"learning_rate": 4.
|
| 1730 |
"loss": 0.0004,
|
| 1731 |
-
"step":
|
| 1732 |
},
|
| 1733 |
{
|
| 1734 |
-
"epoch": 57.
|
| 1735 |
-
"learning_rate": 4.
|
| 1736 |
"loss": 0.0004,
|
| 1737 |
-
"step":
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
-
"epoch": 57.
|
| 1741 |
-
"learning_rate": 3.
|
| 1742 |
"loss": 0.0003,
|
| 1743 |
-
"step":
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 58.0,
|
| 1747 |
-
"eval_loss": 0.
|
| 1748 |
-
"eval_max_distance":
|
| 1749 |
"eval_mean_distance": 0,
|
| 1750 |
-
"eval_runtime": 0.
|
| 1751 |
-
"eval_samples_per_second":
|
| 1752 |
-
"eval_steps_per_second":
|
| 1753 |
-
"step":
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
-
"epoch": 58.
|
| 1757 |
-
"learning_rate": 3.
|
| 1758 |
-
"loss": 0.
|
| 1759 |
-
"step":
|
| 1760 |
},
|
| 1761 |
{
|
| 1762 |
-
"epoch": 58.
|
| 1763 |
-
"learning_rate": 2.
|
| 1764 |
"loss": 0.0004,
|
| 1765 |
-
"step":
|
| 1766 |
},
|
| 1767 |
{
|
| 1768 |
-
"epoch": 58.
|
| 1769 |
-
"learning_rate": 2.
|
| 1770 |
"loss": 0.0003,
|
| 1771 |
-
"step":
|
| 1772 |
},
|
| 1773 |
{
|
| 1774 |
"epoch": 59.0,
|
| 1775 |
-
"eval_loss": 0.
|
| 1776 |
-
"eval_max_distance":
|
| 1777 |
"eval_mean_distance": 0,
|
| 1778 |
-
"eval_runtime": 0.
|
| 1779 |
-
"eval_samples_per_second":
|
| 1780 |
-
"eval_steps_per_second":
|
| 1781 |
-
"step":
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
-
"epoch": 59.
|
| 1785 |
-
"learning_rate": 1.
|
| 1786 |
-
"loss": 0.
|
| 1787 |
-
"step":
|
| 1788 |
},
|
| 1789 |
{
|
| 1790 |
-
"epoch": 59.
|
| 1791 |
-
"learning_rate": 1.
|
| 1792 |
-
"loss": 0.
|
| 1793 |
-
"step":
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
-
"epoch": 59.
|
| 1797 |
-
"learning_rate": 4.
|
| 1798 |
"loss": 0.0004,
|
| 1799 |
-
"step":
|
| 1800 |
},
|
| 1801 |
{
|
| 1802 |
"epoch": 60.0,
|
| 1803 |
-
"eval_loss": 0.
|
| 1804 |
-
"eval_max_distance":
|
| 1805 |
"eval_mean_distance": 0,
|
| 1806 |
-
"eval_runtime": 0.
|
| 1807 |
-
"eval_samples_per_second":
|
| 1808 |
-
"eval_steps_per_second":
|
| 1809 |
-
"step":
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 60.0,
|
| 1813 |
-
"step":
|
| 1814 |
-
"total_flos": 1.
|
| 1815 |
-
"train_loss": 0.
|
| 1816 |
-
"train_runtime":
|
| 1817 |
-
"train_samples_per_second":
|
| 1818 |
-
"train_steps_per_second": 12.
|
| 1819 |
}
|
| 1820 |
],
|
| 1821 |
-
"logging_steps":
|
| 1822 |
-
"max_steps":
|
| 1823 |
"num_train_epochs": 60,
|
| 1824 |
-
"save_steps":
|
| 1825 |
-
"total_flos": 1.
|
| 1826 |
"trial_name": null,
|
| 1827 |
"trial_params": null
|
| 1828 |
}
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 60.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 200040,
|
| 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": 4.999000199960008e-08,
|
| 14 |
+
"loss": 13.1619,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.3,
|
| 19 |
+
"learning_rate": 5.003999200159968e-05,
|
| 20 |
+
"loss": 3.3531,
|
| 21 |
+
"step": 1001
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.6,
|
| 25 |
+
"learning_rate": 0.00010007998400319936,
|
| 26 |
+
"loss": 0.3338,
|
| 27 |
+
"step": 2002
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.9,
|
| 31 |
+
"learning_rate": 0.00015011997600479905,
|
| 32 |
+
"loss": 0.2251,
|
| 33 |
+
"step": 3003
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 1.0,
|
| 37 |
+
"eval_loss": 0.118980273604393,
|
| 38 |
+
"eval_max_distance": 29,
|
| 39 |
+
"eval_mean_distance": 3,
|
| 40 |
+
"eval_runtime": 0.3245,
|
| 41 |
+
"eval_samples_per_second": 154.076,
|
| 42 |
+
"eval_steps_per_second": 6.163,
|
| 43 |
+
"step": 3334
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"epoch": 1.2,
|
| 47 |
+
"learning_rate": 0.00020015996800639872,
|
| 48 |
+
"loss": 0.1668,
|
| 49 |
+
"step": 4004
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 1.5,
|
| 53 |
+
"learning_rate": 0.0002501999600079984,
|
| 54 |
+
"loss": 0.1375,
|
| 55 |
+
"step": 5005
|
| 56 |
},
|
| 57 |
{
|
| 58 |
"epoch": 1.8,
|
| 59 |
+
"learning_rate": 0.0003002399520095981,
|
| 60 |
"loss": 0.1179,
|
| 61 |
+
"step": 6006
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 2.0,
|
| 65 |
+
"eval_loss": 0.057394467294216156,
|
| 66 |
+
"eval_max_distance": 31,
|
| 67 |
+
"eval_mean_distance": 2,
|
| 68 |
+
"eval_runtime": 0.2749,
|
| 69 |
+
"eval_samples_per_second": 181.873,
|
| 70 |
+
"eval_steps_per_second": 7.275,
|
| 71 |
+
"step": 6668
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 2.1,
|
| 75 |
+
"learning_rate": 0.00035027994401119777,
|
| 76 |
+
"loss": 0.0992,
|
| 77 |
+
"step": 7007
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 2.4,
|
| 81 |
+
"learning_rate": 0.00040031993601279744,
|
| 82 |
+
"loss": 0.0886,
|
| 83 |
+
"step": 8008
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 2.7,
|
| 87 |
+
"learning_rate": 0.0004503599280143971,
|
| 88 |
+
"loss": 0.0848,
|
| 89 |
+
"step": 9009
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 3.0,
|
| 93 |
+
"eval_loss": 0.043563079088926315,
|
| 94 |
+
"eval_max_distance": 15,
|
| 95 |
"eval_mean_distance": 1,
|
| 96 |
+
"eval_runtime": 0.2795,
|
| 97 |
+
"eval_samples_per_second": 178.881,
|
| 98 |
+
"eval_steps_per_second": 7.155,
|
| 99 |
+
"step": 10002
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 3.0,
|
| 103 |
+
"learning_rate": 0.0005003999200159968,
|
| 104 |
+
"loss": 0.0757,
|
| 105 |
+
"step": 10010
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 3.3,
|
| 109 |
+
"learning_rate": 0.0005504399120175964,
|
| 110 |
+
"loss": 0.0681,
|
| 111 |
+
"step": 11011
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 3.6,
|
| 115 |
+
"learning_rate": 0.0006004799040191962,
|
| 116 |
"loss": 0.0653,
|
| 117 |
+
"step": 12012
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 3.9,
|
| 121 |
+
"learning_rate": 0.0006505198960207959,
|
| 122 |
+
"loss": 0.0618,
|
| 123 |
+
"step": 13013
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 4.0,
|
| 127 |
+
"eval_loss": 0.035945579409599304,
|
| 128 |
+
"eval_max_distance": 20,
|
| 129 |
"eval_mean_distance": 1,
|
| 130 |
+
"eval_runtime": 0.2802,
|
| 131 |
+
"eval_samples_per_second": 178.422,
|
| 132 |
+
"eval_steps_per_second": 7.137,
|
| 133 |
+
"step": 13336
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 4.2,
|
| 137 |
+
"learning_rate": 0.0007005598880223955,
|
| 138 |
+
"loss": 0.0564,
|
| 139 |
+
"step": 14014
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 4.5,
|
| 143 |
+
"learning_rate": 0.0007505998800239953,
|
| 144 |
+
"loss": 0.0537,
|
| 145 |
+
"step": 15015
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"epoch": 4.8,
|
| 149 |
+
"learning_rate": 0.0008006398720255949,
|
| 150 |
+
"loss": 0.0532,
|
| 151 |
+
"step": 16016
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 5.0,
|
| 155 |
+
"eval_loss": 0.031485434621572495,
|
| 156 |
+
"eval_max_distance": 11,
|
| 157 |
+
"eval_mean_distance": 0,
|
| 158 |
+
"eval_runtime": 0.2717,
|
| 159 |
+
"eval_samples_per_second": 184.007,
|
| 160 |
+
"eval_steps_per_second": 7.36,
|
| 161 |
+
"step": 16670
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 5.1,
|
| 165 |
+
"learning_rate": 0.0008506798640271945,
|
| 166 |
+
"loss": 0.05,
|
| 167 |
+
"step": 17017
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 5.4,
|
| 171 |
+
"learning_rate": 0.0009007198560287942,
|
| 172 |
+
"loss": 0.0468,
|
| 173 |
+
"step": 18018
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 5.7,
|
| 177 |
+
"learning_rate": 0.000950759848030394,
|
| 178 |
+
"loss": 0.0446,
|
| 179 |
+
"step": 19019
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 6.0,
|
| 183 |
+
"eval_loss": 0.0298615675419569,
|
| 184 |
+
"eval_max_distance": 16,
|
| 185 |
+
"eval_mean_distance": 0,
|
| 186 |
+
"eval_runtime": 0.2573,
|
| 187 |
+
"eval_samples_per_second": 194.348,
|
| 188 |
+
"eval_steps_per_second": 7.774,
|
| 189 |
+
"step": 20004
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 6.0,
|
| 193 |
+
"learning_rate": 0.000999911128885334,
|
| 194 |
+
"loss": 0.0465,
|
| 195 |
+
"step": 20020
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 6.31,
|
| 199 |
+
"learning_rate": 0.0009943511297740451,
|
| 200 |
+
"loss": 0.0384,
|
| 201 |
+
"step": 21021
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 6.61,
|
| 205 |
+
"learning_rate": 0.0009887911306627564,
|
| 206 |
+
"loss": 0.0378,
|
| 207 |
+
"step": 22022
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 6.91,
|
| 211 |
+
"learning_rate": 0.0009832311315514674,
|
| 212 |
+
"loss": 0.0388,
|
| 213 |
+
"step": 23023
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 7.0,
|
| 217 |
+
"eval_loss": 0.029532546177506447,
|
| 218 |
+
"eval_max_distance": 15,
|
| 219 |
+
"eval_mean_distance": 0,
|
| 220 |
+
"eval_runtime": 0.2674,
|
| 221 |
+
"eval_samples_per_second": 187.01,
|
| 222 |
+
"eval_steps_per_second": 7.48,
|
| 223 |
+
"step": 23338
|
| 224 |
},
|
| 225 |
{
|
| 226 |
+
"epoch": 7.21,
|
| 227 |
+
"learning_rate": 0.0009776711324401787,
|
| 228 |
+
"loss": 0.0336,
|
| 229 |
+
"step": 24024
|
| 230 |
},
|
| 231 |
{
|
| 232 |
+
"epoch": 7.51,
|
| 233 |
+
"learning_rate": 0.0009721111333288898,
|
| 234 |
+
"loss": 0.032,
|
| 235 |
+
"step": 25025
|
| 236 |
},
|
| 237 |
{
|
| 238 |
+
"epoch": 7.81,
|
| 239 |
+
"learning_rate": 0.000966551134217601,
|
| 240 |
+
"loss": 0.0311,
|
| 241 |
+
"step": 26026
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 8.0,
|
| 245 |
+
"eval_loss": 0.02873826026916504,
|
| 246 |
+
"eval_max_distance": 15,
|
| 247 |
+
"eval_mean_distance": 0,
|
| 248 |
+
"eval_runtime": 0.2674,
|
| 249 |
+
"eval_samples_per_second": 186.98,
|
| 250 |
+
"eval_steps_per_second": 7.479,
|
| 251 |
+
"step": 26672
|
| 252 |
},
|
| 253 |
{
|
| 254 |
+
"epoch": 8.11,
|
| 255 |
+
"learning_rate": 0.0009609911351063121,
|
| 256 |
+
"loss": 0.0304,
|
| 257 |
+
"step": 27027
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 8.41,
|
| 261 |
+
"learning_rate": 0.0009554311359950233,
|
| 262 |
+
"loss": 0.0267,
|
| 263 |
+
"step": 28028
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 8.71,
|
| 267 |
+
"learning_rate": 0.0009498711368837344,
|
| 268 |
+
"loss": 0.0269,
|
| 269 |
+
"step": 29029
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 9.0,
|
| 273 |
+
"eval_loss": 0.02408006228506565,
|
| 274 |
+
"eval_max_distance": 15,
|
| 275 |
+
"eval_mean_distance": 0,
|
| 276 |
+
"eval_runtime": 0.2548,
|
| 277 |
+
"eval_samples_per_second": 196.242,
|
| 278 |
+
"eval_steps_per_second": 7.85,
|
| 279 |
+
"step": 30006
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 9.01,
|
| 283 |
+
"learning_rate": 0.0009443111377724454,
|
| 284 |
+
"loss": 0.0269,
|
| 285 |
+
"step": 30030
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 9.31,
|
| 289 |
+
"learning_rate": 0.0009387511386611567,
|
| 290 |
+
"loss": 0.022,
|
| 291 |
+
"step": 31031
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 9.61,
|
| 295 |
+
"learning_rate": 0.0009331911395498677,
|
| 296 |
+
"loss": 0.0231,
|
| 297 |
+
"step": 32032
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 9.91,
|
| 301 |
+
"learning_rate": 0.000927631140438579,
|
| 302 |
+
"loss": 0.0232,
|
| 303 |
+
"step": 33033
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 10.0,
|
| 307 |
+
"eval_loss": 0.022765493020415306,
|
| 308 |
+
"eval_max_distance": 13,
|
| 309 |
+
"eval_mean_distance": 0,
|
| 310 |
+
"eval_runtime": 0.2488,
|
| 311 |
+
"eval_samples_per_second": 200.959,
|
| 312 |
+
"eval_steps_per_second": 8.038,
|
| 313 |
+
"step": 33340
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 10.21,
|
| 317 |
+
"learning_rate": 0.00092207114132729,
|
| 318 |
+
"loss": 0.0199,
|
| 319 |
+
"step": 34034
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 10.51,
|
| 323 |
+
"learning_rate": 0.0009165111422160013,
|
| 324 |
+
"loss": 0.0196,
|
| 325 |
+
"step": 35035
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 10.81,
|
| 329 |
+
"learning_rate": 0.0009109511431047123,
|
| 330 |
"loss": 0.0203,
|
| 331 |
+
"step": 36036
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 11.0,
|
| 335 |
+
"eval_loss": 0.024308495223522186,
|
| 336 |
+
"eval_max_distance": 16,
|
| 337 |
+
"eval_mean_distance": 0,
|
| 338 |
+
"eval_runtime": 0.2617,
|
| 339 |
+
"eval_samples_per_second": 191.039,
|
| 340 |
+
"eval_steps_per_second": 7.642,
|
| 341 |
+
"step": 36674
|
| 342 |
},
|
| 343 |
{
|
| 344 |
"epoch": 11.11,
|
| 345 |
+
"learning_rate": 0.0009053911439934236,
|
| 346 |
+
"loss": 0.0186,
|
| 347 |
+
"step": 37037
|
| 348 |
},
|
| 349 |
{
|
| 350 |
"epoch": 11.41,
|
| 351 |
+
"learning_rate": 0.0008998311448821347,
|
| 352 |
+
"loss": 0.0167,
|
| 353 |
+
"step": 38038
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 11.71,
|
| 357 |
+
"learning_rate": 0.0008942711457708459,
|
| 358 |
+
"loss": 0.0173,
|
| 359 |
+
"step": 39039
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 12.0,
|
| 363 |
+
"eval_loss": 0.0250206608325243,
|
| 364 |
+
"eval_max_distance": 15,
|
| 365 |
+
"eval_mean_distance": 0,
|
| 366 |
+
"eval_runtime": 0.2565,
|
| 367 |
+
"eval_samples_per_second": 194.951,
|
| 368 |
+
"eval_steps_per_second": 7.798,
|
| 369 |
+
"step": 40008
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 12.01,
|
| 373 |
+
"learning_rate": 0.000888711146659557,
|
| 374 |
+
"loss": 0.0178,
|
| 375 |
+
"step": 40040
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 12.31,
|
| 379 |
+
"learning_rate": 0.0008831511475482682,
|
| 380 |
+
"loss": 0.0146,
|
| 381 |
+
"step": 41041
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 12.61,
|
| 385 |
+
"learning_rate": 0.0008775911484369793,
|
| 386 |
+
"loss": 0.0149,
|
| 387 |
+
"step": 42042
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 12.91,
|
| 391 |
+
"learning_rate": 0.0008720311493256904,
|
| 392 |
+
"loss": 0.0151,
|
| 393 |
+
"step": 43043
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 13.0,
|
| 397 |
+
"eval_loss": 0.024401402100920677,
|
| 398 |
+
"eval_max_distance": 9,
|
| 399 |
+
"eval_mean_distance": 0,
|
| 400 |
+
"eval_runtime": 0.2582,
|
| 401 |
+
"eval_samples_per_second": 193.662,
|
| 402 |
+
"eval_steps_per_second": 7.746,
|
| 403 |
+
"step": 43342
|
| 404 |
},
|
| 405 |
{
|
| 406 |
"epoch": 13.21,
|
| 407 |
+
"learning_rate": 0.0008664711502144016,
|
| 408 |
+
"loss": 0.0138,
|
| 409 |
+
"step": 44044
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 13.51,
|
| 413 |
+
"learning_rate": 0.0008609111511031127,
|
| 414 |
+
"loss": 0.0137,
|
| 415 |
+
"step": 45045
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 13.81,
|
| 419 |
+
"learning_rate": 0.0008553511519918239,
|
| 420 |
+
"loss": 0.0136,
|
| 421 |
+
"step": 46046
|
| 422 |
},
|
| 423 |
{
|
| 424 |
"epoch": 14.0,
|
| 425 |
+
"eval_loss": 0.023412013426423073,
|
| 426 |
+
"eval_max_distance": 15,
|
| 427 |
+
"eval_mean_distance": 0,
|
| 428 |
+
"eval_runtime": 0.2465,
|
| 429 |
+
"eval_samples_per_second": 202.834,
|
| 430 |
+
"eval_steps_per_second": 8.113,
|
| 431 |
+
"step": 46676
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 14.11,
|
| 435 |
+
"learning_rate": 0.000849791152880535,
|
| 436 |
+
"loss": 0.0126,
|
| 437 |
+
"step": 47047
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 14.41,
|
| 441 |
+
"learning_rate": 0.0008442311537692462,
|
| 442 |
"loss": 0.0121,
|
| 443 |
+
"step": 48048
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 14.71,
|
| 447 |
+
"learning_rate": 0.0008386711546579573,
|
| 448 |
+
"loss": 0.0123,
|
| 449 |
+
"step": 49049
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 15.0,
|
| 453 |
+
"eval_loss": 0.022092605009675026,
|
| 454 |
+
"eval_max_distance": 9,
|
| 455 |
+
"eval_mean_distance": 0,
|
| 456 |
+
"eval_runtime": 0.2607,
|
| 457 |
+
"eval_samples_per_second": 191.77,
|
| 458 |
+
"eval_steps_per_second": 7.671,
|
| 459 |
+
"step": 50010
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 15.01,
|
| 463 |
+
"learning_rate": 0.0008331111555466685,
|
| 464 |
+
"loss": 0.0125,
|
| 465 |
+
"step": 50050
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 15.31,
|
| 469 |
+
"learning_rate": 0.0008275511564353796,
|
| 470 |
+
"loss": 0.0101,
|
| 471 |
+
"step": 51051
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 15.61,
|
| 475 |
+
"learning_rate": 0.0008219911573240908,
|
| 476 |
+
"loss": 0.0108,
|
| 477 |
+
"step": 52052
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 15.91,
|
| 481 |
+
"learning_rate": 0.0008164311582128019,
|
| 482 |
+
"loss": 0.0113,
|
| 483 |
+
"step": 53053
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 16.0,
|
| 487 |
+
"eval_loss": 0.024386152625083923,
|
| 488 |
+
"eval_max_distance": 12,
|
| 489 |
+
"eval_mean_distance": 0,
|
| 490 |
+
"eval_runtime": 0.2455,
|
| 491 |
+
"eval_samples_per_second": 203.682,
|
| 492 |
+
"eval_steps_per_second": 8.147,
|
| 493 |
+
"step": 53344
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 16.21,
|
| 497 |
+
"learning_rate": 0.0008108711591015131,
|
| 498 |
+
"loss": 0.0099,
|
| 499 |
+
"step": 54054
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 16.51,
|
| 503 |
+
"learning_rate": 0.0008053111599902242,
|
| 504 |
+
"loss": 0.0096,
|
| 505 |
+
"step": 55055
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 16.81,
|
| 509 |
+
"learning_rate": 0.0007997511608789353,
|
| 510 |
+
"loss": 0.01,
|
| 511 |
+
"step": 56056
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 17.0,
|
| 515 |
+
"eval_loss": 0.02255043014883995,
|
| 516 |
+
"eval_max_distance": 13,
|
| 517 |
+
"eval_mean_distance": 0,
|
| 518 |
+
"eval_runtime": 0.2506,
|
| 519 |
+
"eval_samples_per_second": 199.486,
|
| 520 |
+
"eval_steps_per_second": 7.979,
|
| 521 |
+
"step": 56678
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 17.11,
|
| 525 |
+
"learning_rate": 0.0007941911617676465,
|
| 526 |
+
"loss": 0.0093,
|
| 527 |
+
"step": 57057
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 17.41,
|
| 531 |
+
"learning_rate": 0.0007886311626563576,
|
| 532 |
+
"loss": 0.0087,
|
| 533 |
+
"step": 58058
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 17.71,
|
| 537 |
+
"learning_rate": 0.0007830711635450687,
|
| 538 |
+
"loss": 0.0089,
|
| 539 |
+
"step": 59059
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 18.0,
|
| 543 |
+
"eval_loss": 0.027119183912873268,
|
| 544 |
+
"eval_max_distance": 13,
|
| 545 |
+
"eval_mean_distance": 0,
|
| 546 |
+
"eval_runtime": 0.2424,
|
| 547 |
+
"eval_samples_per_second": 206.232,
|
| 548 |
+
"eval_steps_per_second": 8.249,
|
| 549 |
+
"step": 60012
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 18.01,
|
| 553 |
+
"learning_rate": 0.0007775111644337799,
|
| 554 |
+
"loss": 0.0091,
|
| 555 |
+
"step": 60060
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 18.31,
|
| 559 |
+
"learning_rate": 0.0007719511653224912,
|
| 560 |
"loss": 0.0075,
|
| 561 |
+
"step": 61061
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 18.61,
|
| 565 |
+
"learning_rate": 0.0007663911662112022,
|
| 566 |
+
"loss": 0.0079,
|
| 567 |
+
"step": 62062
|
| 568 |
},
|
| 569 |
{
|
| 570 |
+
"epoch": 18.92,
|
| 571 |
+
"learning_rate": 0.0007608311670999134,
|
| 572 |
+
"loss": 0.0085,
|
| 573 |
+
"step": 63063
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 19.0,
|
| 577 |
+
"eval_loss": 0.024822326377034187,
|
| 578 |
+
"eval_max_distance": 13,
|
| 579 |
+
"eval_mean_distance": 0,
|
| 580 |
+
"eval_runtime": 0.2416,
|
| 581 |
+
"eval_samples_per_second": 206.915,
|
| 582 |
+
"eval_steps_per_second": 8.277,
|
| 583 |
+
"step": 63346
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 19.22,
|
| 587 |
+
"learning_rate": 0.0007552711679886245,
|
| 588 |
+
"loss": 0.0071,
|
| 589 |
+
"step": 64064
|
| 590 |
},
|
| 591 |
{
|
| 592 |
+
"epoch": 19.52,
|
| 593 |
+
"learning_rate": 0.0007497111688773357,
|
| 594 |
+
"loss": 0.0074,
|
| 595 |
+
"step": 65065
|
| 596 |
},
|
| 597 |
{
|
| 598 |
+
"epoch": 19.82,
|
| 599 |
+
"learning_rate": 0.0007441511697660468,
|
| 600 |
+
"loss": 0.0074,
|
| 601 |
+
"step": 66066
|
| 602 |
},
|
| 603 |
{
|
| 604 |
"epoch": 20.0,
|
| 605 |
+
"eval_loss": 0.027729548513889313,
|
| 606 |
+
"eval_max_distance": 12,
|
| 607 |
+
"eval_mean_distance": 0,
|
| 608 |
+
"eval_runtime": 0.2481,
|
| 609 |
+
"eval_samples_per_second": 201.568,
|
| 610 |
+
"eval_steps_per_second": 8.063,
|
| 611 |
+
"step": 66680
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 20.12,
|
| 615 |
+
"learning_rate": 0.000738591170654758,
|
| 616 |
+
"loss": 0.007,
|
| 617 |
+
"step": 67067
|
| 618 |
},
|
| 619 |
{
|
| 620 |
+
"epoch": 20.42,
|
| 621 |
+
"learning_rate": 0.0007330311715434691,
|
| 622 |
+
"loss": 0.0061,
|
| 623 |
+
"step": 68068
|
| 624 |
},
|
| 625 |
{
|
| 626 |
+
"epoch": 20.72,
|
| 627 |
+
"learning_rate": 0.0007274711724321802,
|
| 628 |
+
"loss": 0.007,
|
| 629 |
+
"step": 69069
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 21.0,
|
| 633 |
+
"eval_loss": 0.030854225158691406,
|
| 634 |
+
"eval_max_distance": 13,
|
| 635 |
+
"eval_mean_distance": 0,
|
| 636 |
+
"eval_runtime": 0.2457,
|
| 637 |
+
"eval_samples_per_second": 203.54,
|
| 638 |
+
"eval_steps_per_second": 8.142,
|
| 639 |
+
"step": 70014
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 21.02,
|
| 643 |
+
"learning_rate": 0.0007219111733208914,
|
| 644 |
+
"loss": 0.0069,
|
| 645 |
+
"step": 70070
|
| 646 |
},
|
| 647 |
{
|
| 648 |
+
"epoch": 21.32,
|
| 649 |
+
"learning_rate": 0.0007163511742096025,
|
| 650 |
+
"loss": 0.006,
|
| 651 |
+
"step": 71071
|
| 652 |
},
|
| 653 |
{
|
| 654 |
+
"epoch": 21.62,
|
| 655 |
+
"learning_rate": 0.0007107911750983137,
|
| 656 |
+
"loss": 0.0061,
|
| 657 |
+
"step": 72072
|
| 658 |
},
|
| 659 |
{
|
| 660 |
+
"epoch": 21.92,
|
| 661 |
+
"learning_rate": 0.0007052311759870248,
|
| 662 |
+
"loss": 0.0066,
|
| 663 |
+
"step": 73073
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 22.0,
|
| 667 |
+
"eval_loss": 0.030563361942768097,
|
| 668 |
+
"eval_max_distance": 11,
|
| 669 |
+
"eval_mean_distance": 0,
|
| 670 |
+
"eval_runtime": 0.2419,
|
| 671 |
+
"eval_samples_per_second": 206.734,
|
| 672 |
+
"eval_steps_per_second": 8.269,
|
| 673 |
+
"step": 73348
|
| 674 |
},
|
| 675 |
{
|
| 676 |
+
"epoch": 22.22,
|
| 677 |
+
"learning_rate": 0.000699671176875736,
|
| 678 |
+
"loss": 0.0054,
|
| 679 |
+
"step": 74074
|
| 680 |
},
|
| 681 |
{
|
| 682 |
+
"epoch": 22.52,
|
| 683 |
+
"learning_rate": 0.0006941111777644471,
|
| 684 |
+
"loss": 0.0061,
|
| 685 |
+
"step": 75075
|
| 686 |
},
|
| 687 |
{
|
| 688 |
+
"epoch": 22.82,
|
| 689 |
+
"learning_rate": 0.0006885511786531583,
|
| 690 |
+
"loss": 0.0056,
|
| 691 |
+
"step": 76076
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 23.0,
|
| 695 |
+
"eval_loss": 0.028730520978569984,
|
| 696 |
+
"eval_max_distance": 10,
|
| 697 |
"eval_mean_distance": 0,
|
| 698 |
+
"eval_runtime": 0.2431,
|
| 699 |
+
"eval_samples_per_second": 205.684,
|
| 700 |
+
"eval_steps_per_second": 8.227,
|
| 701 |
+
"step": 76682
|
| 702 |
},
|
| 703 |
{
|
| 704 |
+
"epoch": 23.12,
|
| 705 |
+
"learning_rate": 0.0006829911795418694,
|
| 706 |
+
"loss": 0.0054,
|
| 707 |
+
"step": 77077
|
| 708 |
},
|
| 709 |
{
|
| 710 |
+
"epoch": 23.42,
|
| 711 |
+
"learning_rate": 0.0006774311804305806,
|
| 712 |
+
"loss": 0.0052,
|
| 713 |
+
"step": 78078
|
| 714 |
},
|
| 715 |
{
|
| 716 |
+
"epoch": 23.72,
|
| 717 |
+
"learning_rate": 0.0006718711813192917,
|
| 718 |
+
"loss": 0.0053,
|
| 719 |
+
"step": 79079
|
| 720 |
},
|
| 721 |
{
|
| 722 |
"epoch": 24.0,
|
| 723 |
+
"eval_loss": 0.031197942793369293,
|
| 724 |
+
"eval_max_distance": 12,
|
| 725 |
+
"eval_mean_distance": 0,
|
| 726 |
+
"eval_runtime": 0.2517,
|
| 727 |
+
"eval_samples_per_second": 198.643,
|
| 728 |
+
"eval_steps_per_second": 7.946,
|
| 729 |
+
"step": 80016
|
| 730 |
},
|
| 731 |
{
|
| 732 |
+
"epoch": 24.02,
|
| 733 |
+
"learning_rate": 0.0006663111822080029,
|
| 734 |
+
"loss": 0.0054,
|
| 735 |
+
"step": 80080
|
| 736 |
},
|
| 737 |
{
|
| 738 |
+
"epoch": 24.32,
|
| 739 |
+
"learning_rate": 0.000660751183096714,
|
| 740 |
+
"loss": 0.0044,
|
| 741 |
+
"step": 81081
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 24.62,
|
| 745 |
+
"learning_rate": 0.000655191183985425,
|
| 746 |
+
"loss": 0.0048,
|
| 747 |
+
"step": 82082
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 24.92,
|
| 751 |
+
"learning_rate": 0.0006496311848741363,
|
| 752 |
+
"loss": 0.0049,
|
| 753 |
+
"step": 83083
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 25.0,
|
| 757 |
+
"eval_loss": 0.0276066605001688,
|
| 758 |
+
"eval_max_distance": 11,
|
| 759 |
+
"eval_mean_distance": 0,
|
| 760 |
+
"eval_runtime": 0.2475,
|
| 761 |
+
"eval_samples_per_second": 202.046,
|
| 762 |
+
"eval_steps_per_second": 8.082,
|
| 763 |
+
"step": 83350
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 25.22,
|
| 767 |
+
"learning_rate": 0.0006440711857628475,
|
| 768 |
+
"loss": 0.0045,
|
| 769 |
+
"step": 84084
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 25.52,
|
| 773 |
+
"learning_rate": 0.0006385111866515586,
|
| 774 |
"loss": 0.0045,
|
| 775 |
+
"step": 85085
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 25.82,
|
| 779 |
+
"learning_rate": 0.0006329511875402698,
|
| 780 |
+
"loss": 0.0053,
|
| 781 |
+
"step": 86086
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 26.0,
|
| 785 |
+
"eval_loss": 0.030818996950984,
|
| 786 |
+
"eval_max_distance": 10,
|
| 787 |
+
"eval_mean_distance": 0,
|
| 788 |
+
"eval_runtime": 0.2424,
|
| 789 |
+
"eval_samples_per_second": 206.301,
|
| 790 |
+
"eval_steps_per_second": 8.252,
|
| 791 |
+
"step": 86684
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 26.12,
|
| 795 |
+
"learning_rate": 0.0006273911884289809,
|
| 796 |
+
"loss": 0.0045,
|
| 797 |
+
"step": 87087
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 26.42,
|
| 801 |
+
"learning_rate": 0.000621831189317692,
|
| 802 |
+
"loss": 0.0041,
|
| 803 |
+
"step": 88088
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 26.72,
|
| 807 |
+
"learning_rate": 0.0006162711902064032,
|
| 808 |
+
"loss": 0.0041,
|
| 809 |
+
"step": 89089
|
| 810 |
},
|
| 811 |
{
|
| 812 |
"epoch": 27.0,
|
| 813 |
+
"eval_loss": 0.027929000556468964,
|
| 814 |
+
"eval_max_distance": 10,
|
| 815 |
+
"eval_mean_distance": 0,
|
| 816 |
+
"eval_runtime": 0.2471,
|
| 817 |
+
"eval_samples_per_second": 202.312,
|
| 818 |
+
"eval_steps_per_second": 8.092,
|
| 819 |
+
"step": 90018
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 27.02,
|
| 823 |
+
"learning_rate": 0.0006107111910951143,
|
| 824 |
"loss": 0.0043,
|
| 825 |
+
"step": 90090
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 27.32,
|
| 829 |
+
"learning_rate": 0.0006051511919838255,
|
| 830 |
+
"loss": 0.0038,
|
| 831 |
+
"step": 91091
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 27.62,
|
| 835 |
+
"learning_rate": 0.0005995911928725366,
|
| 836 |
+
"loss": 0.0038,
|
| 837 |
+
"step": 92092
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 27.92,
|
| 841 |
+
"learning_rate": 0.0005940311937612478,
|
| 842 |
+
"loss": 0.0041,
|
| 843 |
+
"step": 93093
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 28.0,
|
| 847 |
+
"eval_loss": 0.029230400919914246,
|
| 848 |
+
"eval_max_distance": 11,
|
| 849 |
+
"eval_mean_distance": 0,
|
| 850 |
+
"eval_runtime": 0.2482,
|
| 851 |
+
"eval_samples_per_second": 201.481,
|
| 852 |
+
"eval_steps_per_second": 8.059,
|
| 853 |
+
"step": 93352
|
| 854 |
},
|
| 855 |
{
|
| 856 |
"epoch": 28.22,
|
| 857 |
+
"learning_rate": 0.0005884711946499589,
|
| 858 |
"loss": 0.0037,
|
| 859 |
+
"step": 94094
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 28.52,
|
| 863 |
+
"learning_rate": 0.00058291119553867,
|
| 864 |
+
"loss": 0.0033,
|
| 865 |
+
"step": 95095
|
| 866 |
},
|
| 867 |
{
|
| 868 |
"epoch": 28.82,
|
| 869 |
+
"learning_rate": 0.0005773511964273812,
|
| 870 |
+
"loss": 0.0037,
|
| 871 |
+
"step": 96096
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 29.0,
|
| 875 |
+
"eval_loss": 0.030607566237449646,
|
| 876 |
+
"eval_max_distance": 11,
|
| 877 |
+
"eval_mean_distance": 0,
|
| 878 |
+
"eval_runtime": 0.2429,
|
| 879 |
+
"eval_samples_per_second": 205.838,
|
| 880 |
+
"eval_steps_per_second": 8.234,
|
| 881 |
+
"step": 96686
|
| 882 |
},
|
| 883 |
{
|
| 884 |
"epoch": 29.12,
|
| 885 |
+
"learning_rate": 0.0005717911973160923,
|
| 886 |
+
"loss": 0.0036,
|
| 887 |
+
"step": 97097
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 29.42,
|
| 891 |
+
"learning_rate": 0.0005662311982048035,
|
| 892 |
"loss": 0.0033,
|
| 893 |
+
"step": 98098
|
| 894 |
},
|
| 895 |
{
|
| 896 |
"epoch": 29.72,
|
| 897 |
+
"learning_rate": 0.0005606711990935146,
|
| 898 |
+
"loss": 0.0035,
|
| 899 |
+
"step": 99099
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 30.0,
|
| 903 |
+
"eval_loss": 0.027241094037890434,
|
| 904 |
+
"eval_max_distance": 12,
|
| 905 |
+
"eval_mean_distance": 0,
|
| 906 |
+
"eval_runtime": 0.2466,
|
| 907 |
+
"eval_samples_per_second": 202.757,
|
| 908 |
+
"eval_steps_per_second": 8.11,
|
| 909 |
+
"step": 100020
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 30.02,
|
| 913 |
+
"learning_rate": 0.0005551111999822258,
|
| 914 |
+
"loss": 0.0033,
|
| 915 |
+
"step": 100100
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 30.32,
|
| 919 |
+
"learning_rate": 0.0005495512008709369,
|
| 920 |
"loss": 0.003,
|
| 921 |
+
"step": 101101
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 30.62,
|
| 925 |
+
"learning_rate": 0.0005439912017596481,
|
| 926 |
+
"loss": 0.0031,
|
| 927 |
+
"step": 102102
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 30.92,
|
| 931 |
+
"learning_rate": 0.0005384312026483592,
|
| 932 |
+
"loss": 0.0032,
|
| 933 |
+
"step": 103103
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 31.0,
|
| 937 |
+
"eval_loss": 0.0254651065915823,
|
| 938 |
+
"eval_max_distance": 9,
|
| 939 |
+
"eval_mean_distance": 0,
|
| 940 |
+
"eval_runtime": 0.2446,
|
| 941 |
+
"eval_samples_per_second": 204.388,
|
| 942 |
+
"eval_steps_per_second": 8.176,
|
| 943 |
+
"step": 103354
|
| 944 |
},
|
| 945 |
{
|
| 946 |
"epoch": 31.22,
|
| 947 |
+
"learning_rate": 0.0005328712035370704,
|
| 948 |
+
"loss": 0.0028,
|
| 949 |
+
"step": 104104
|
| 950 |
},
|
| 951 |
{
|
| 952 |
+
"epoch": 31.53,
|
| 953 |
+
"learning_rate": 0.0005273112044257815,
|
| 954 |
+
"loss": 0.0029,
|
| 955 |
+
"step": 105105
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 31.83,
|
| 959 |
+
"learning_rate": 0.0005217512053144927,
|
| 960 |
+
"loss": 0.0031,
|
| 961 |
+
"step": 106106
|
| 962 |
},
|
| 963 |
{
|
| 964 |
"epoch": 32.0,
|
| 965 |
+
"eval_loss": 0.02928677573800087,
|
| 966 |
+
"eval_max_distance": 10,
|
| 967 |
+
"eval_mean_distance": 0,
|
| 968 |
+
"eval_runtime": 0.2518,
|
| 969 |
+
"eval_samples_per_second": 198.594,
|
| 970 |
+
"eval_steps_per_second": 7.944,
|
| 971 |
+
"step": 106688
|
| 972 |
},
|
| 973 |
{
|
| 974 |
+
"epoch": 32.13,
|
| 975 |
+
"learning_rate": 0.0005161912062032039,
|
| 976 |
"loss": 0.0028,
|
| 977 |
+
"step": 107107
|
| 978 |
},
|
| 979 |
{
|
| 980 |
+
"epoch": 32.43,
|
| 981 |
+
"learning_rate": 0.0005106312070919149,
|
| 982 |
+
"loss": 0.0026,
|
| 983 |
+
"step": 108108
|
| 984 |
},
|
| 985 |
{
|
| 986 |
+
"epoch": 32.73,
|
| 987 |
+
"learning_rate": 0.0005050712079806262,
|
| 988 |
+
"loss": 0.0029,
|
| 989 |
+
"step": 109109
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 33.0,
|
| 993 |
+
"eval_loss": 0.029988963156938553,
|
| 994 |
+
"eval_max_distance": 13,
|
| 995 |
"eval_mean_distance": 0,
|
| 996 |
+
"eval_runtime": 0.2465,
|
| 997 |
+
"eval_samples_per_second": 202.802,
|
| 998 |
+
"eval_steps_per_second": 8.112,
|
| 999 |
+
"step": 110022
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 33.03,
|
| 1003 |
+
"learning_rate": 0.0004995112088693373,
|
| 1004 |
+
"loss": 0.0027,
|
| 1005 |
+
"step": 110110
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
+
"epoch": 33.33,
|
| 1009 |
+
"learning_rate": 0.0004939512097580485,
|
| 1010 |
+
"loss": 0.0025,
|
| 1011 |
+
"step": 111111
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
+
"epoch": 33.63,
|
| 1015 |
+
"learning_rate": 0.0004883912106467596,
|
| 1016 |
"loss": 0.0026,
|
| 1017 |
+
"step": 112112
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
+
"epoch": 33.93,
|
| 1021 |
+
"learning_rate": 0.0004828312115354707,
|
| 1022 |
+
"loss": 0.0026,
|
| 1023 |
+
"step": 113113
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 34.0,
|
| 1027 |
+
"eval_loss": 0.03050011210143566,
|
| 1028 |
+
"eval_max_distance": 11,
|
| 1029 |
+
"eval_mean_distance": 0,
|
| 1030 |
+
"eval_runtime": 0.2507,
|
| 1031 |
+
"eval_samples_per_second": 199.458,
|
| 1032 |
+
"eval_steps_per_second": 7.978,
|
| 1033 |
+
"step": 113356
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
+
"epoch": 34.23,
|
| 1037 |
+
"learning_rate": 0.00047727121242418185,
|
| 1038 |
+
"loss": 0.0025,
|
| 1039 |
+
"step": 114114
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
+
"epoch": 34.53,
|
| 1043 |
+
"learning_rate": 0.00047171121331289294,
|
| 1044 |
"loss": 0.0023,
|
| 1045 |
+
"step": 115115
|
| 1046 |
},
|
| 1047 |
{
|
| 1048 |
+
"epoch": 34.83,
|
| 1049 |
+
"learning_rate": 0.0004661512142016041,
|
| 1050 |
+
"loss": 0.0024,
|
| 1051 |
+
"step": 116116
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
"epoch": 35.0,
|
| 1055 |
+
"eval_loss": 0.027280788868665695,
|
| 1056 |
+
"eval_max_distance": 9,
|
| 1057 |
"eval_mean_distance": 0,
|
| 1058 |
+
"eval_runtime": 0.2447,
|
| 1059 |
+
"eval_samples_per_second": 204.372,
|
| 1060 |
+
"eval_steps_per_second": 8.175,
|
| 1061 |
+
"step": 116690
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
+
"epoch": 35.13,
|
| 1065 |
+
"learning_rate": 0.00046059121509031524,
|
| 1066 |
+
"loss": 0.0024,
|
| 1067 |
+
"step": 117117
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
+
"epoch": 35.43,
|
| 1071 |
+
"learning_rate": 0.00045503121597902644,
|
| 1072 |
+
"loss": 0.0022,
|
| 1073 |
+
"step": 118118
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
+
"epoch": 35.73,
|
| 1077 |
+
"learning_rate": 0.0004494712168677376,
|
| 1078 |
"loss": 0.0023,
|
| 1079 |
+
"step": 119119
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
"epoch": 36.0,
|
| 1083 |
+
"eval_loss": 0.028403306379914284,
|
| 1084 |
+
"eval_max_distance": 10,
|
| 1085 |
"eval_mean_distance": 0,
|
| 1086 |
+
"eval_runtime": 0.2435,
|
| 1087 |
+
"eval_samples_per_second": 205.364,
|
| 1088 |
+
"eval_steps_per_second": 8.215,
|
| 1089 |
+
"step": 120024
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
+
"epoch": 36.03,
|
| 1093 |
+
"learning_rate": 0.00044391121775644874,
|
| 1094 |
+
"loss": 0.0022,
|
| 1095 |
+
"step": 120120
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"epoch": 36.33,
|
| 1099 |
+
"learning_rate": 0.0004383512186451599,
|
| 1100 |
+
"loss": 0.002,
|
| 1101 |
+
"step": 121121
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
+
"epoch": 36.63,
|
| 1105 |
+
"learning_rate": 0.00043279121953387103,
|
| 1106 |
+
"loss": 0.0022,
|
| 1107 |
+
"step": 122122
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 36.93,
|
| 1111 |
+
"learning_rate": 0.0004272312204225822,
|
| 1112 |
+
"loss": 0.0022,
|
| 1113 |
+
"step": 123123
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 37.0,
|
| 1117 |
+
"eval_loss": 0.03133893013000488,
|
| 1118 |
+
"eval_max_distance": 13,
|
| 1119 |
+
"eval_mean_distance": 0,
|
| 1120 |
+
"eval_runtime": 0.2436,
|
| 1121 |
+
"eval_samples_per_second": 205.289,
|
| 1122 |
+
"eval_steps_per_second": 8.212,
|
| 1123 |
+
"step": 123358
|
| 1124 |
},
|
| 1125 |
{
|
| 1126 |
+
"epoch": 37.23,
|
| 1127 |
+
"learning_rate": 0.00042167122131129333,
|
| 1128 |
+
"loss": 0.0019,
|
| 1129 |
+
"step": 124124
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 37.53,
|
| 1133 |
+
"learning_rate": 0.0004161112222000045,
|
| 1134 |
"loss": 0.0019,
|
| 1135 |
+
"step": 125125
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 37.83,
|
| 1139 |
+
"learning_rate": 0.0004105512230887156,
|
| 1140 |
+
"loss": 0.002,
|
| 1141 |
+
"step": 126126
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 38.0,
|
| 1145 |
+
"eval_loss": 0.034086938947439194,
|
| 1146 |
+
"eval_max_distance": 13,
|
| 1147 |
+
"eval_mean_distance": 0,
|
| 1148 |
+
"eval_runtime": 0.242,
|
| 1149 |
+
"eval_samples_per_second": 206.579,
|
| 1150 |
+
"eval_steps_per_second": 8.263,
|
| 1151 |
+
"step": 126692
|
| 1152 |
},
|
| 1153 |
{
|
| 1154 |
+
"epoch": 38.13,
|
| 1155 |
+
"learning_rate": 0.0004049912239774268,
|
| 1156 |
+
"loss": 0.002,
|
| 1157 |
+
"step": 127127
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
+
"epoch": 38.43,
|
| 1161 |
+
"learning_rate": 0.00039943122486613787,
|
| 1162 |
"loss": 0.0018,
|
| 1163 |
+
"step": 128128
|
| 1164 |
},
|
| 1165 |
{
|
| 1166 |
+
"epoch": 38.73,
|
| 1167 |
+
"learning_rate": 0.000393871225754849,
|
| 1168 |
"loss": 0.0017,
|
| 1169 |
+
"step": 129129
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
"epoch": 39.0,
|
| 1173 |
+
"eval_loss": 0.03005034476518631,
|
| 1174 |
+
"eval_max_distance": 13,
|
| 1175 |
"eval_mean_distance": 0,
|
| 1176 |
+
"eval_runtime": 0.2407,
|
| 1177 |
+
"eval_samples_per_second": 207.711,
|
| 1178 |
+
"eval_steps_per_second": 8.308,
|
| 1179 |
+
"step": 130026
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
+
"epoch": 39.03,
|
| 1183 |
+
"learning_rate": 0.00038831122664356016,
|
| 1184 |
+
"loss": 0.0018,
|
| 1185 |
+
"step": 130130
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
+
"epoch": 39.33,
|
| 1189 |
+
"learning_rate": 0.0003827512275322713,
|
| 1190 |
"loss": 0.0016,
|
| 1191 |
+
"step": 131131
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
+
"epoch": 39.63,
|
| 1195 |
+
"learning_rate": 0.00037719122842098246,
|
| 1196 |
"loss": 0.0017,
|
| 1197 |
+
"step": 132132
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
+
"epoch": 39.93,
|
| 1201 |
+
"learning_rate": 0.0003716312293096936,
|
| 1202 |
"loss": 0.0017,
|
| 1203 |
+
"step": 133133
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 40.0,
|
| 1207 |
+
"eval_loss": 0.03297489508986473,
|
| 1208 |
+
"eval_max_distance": 11,
|
| 1209 |
"eval_mean_distance": 0,
|
| 1210 |
+
"eval_runtime": 0.2478,
|
| 1211 |
+
"eval_samples_per_second": 201.796,
|
| 1212 |
+
"eval_steps_per_second": 8.072,
|
| 1213 |
+
"step": 133360
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
+
"epoch": 40.23,
|
| 1217 |
+
"learning_rate": 0.00036607123019840476,
|
| 1218 |
"loss": 0.0015,
|
| 1219 |
+
"step": 134134
|
| 1220 |
},
|
| 1221 |
{
|
| 1222 |
+
"epoch": 40.53,
|
| 1223 |
+
"learning_rate": 0.0003605112310871159,
|
| 1224 |
+
"loss": 0.0015,
|
| 1225 |
+
"step": 135135
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
+
"epoch": 40.83,
|
| 1229 |
+
"learning_rate": 0.00035495123197582705,
|
| 1230 |
"loss": 0.0016,
|
| 1231 |
+
"step": 136136
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
"epoch": 41.0,
|
| 1235 |
+
"eval_loss": 0.03444751352071762,
|
| 1236 |
+
"eval_max_distance": 11,
|
| 1237 |
"eval_mean_distance": 0,
|
| 1238 |
+
"eval_runtime": 0.2543,
|
| 1239 |
+
"eval_samples_per_second": 196.583,
|
| 1240 |
+
"eval_steps_per_second": 7.863,
|
| 1241 |
+
"step": 136694
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
+
"epoch": 41.13,
|
| 1245 |
+
"learning_rate": 0.0003493912328645382,
|
| 1246 |
"loss": 0.0015,
|
| 1247 |
+
"step": 137137
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
"epoch": 41.43,
|
| 1251 |
+
"learning_rate": 0.00034383123375324935,
|
| 1252 |
"loss": 0.0014,
|
| 1253 |
+
"step": 138138
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 41.73,
|
| 1257 |
+
"learning_rate": 0.0003382712346419605,
|
| 1258 |
+
"loss": 0.0014,
|
| 1259 |
+
"step": 139139
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 42.0,
|
| 1263 |
+
"eval_loss": 0.033661480993032455,
|
| 1264 |
+
"eval_max_distance": 10,
|
| 1265 |
+
"eval_mean_distance": 0,
|
| 1266 |
+
"eval_runtime": 0.251,
|
| 1267 |
+
"eval_samples_per_second": 199.199,
|
| 1268 |
+
"eval_steps_per_second": 7.968,
|
| 1269 |
+
"step": 140028
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 42.03,
|
| 1273 |
+
"learning_rate": 0.0003327112355306717,
|
| 1274 |
+
"loss": 0.0015,
|
| 1275 |
+
"step": 140140
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 42.33,
|
| 1279 |
+
"learning_rate": 0.0003271512364193828,
|
| 1280 |
+
"loss": 0.0014,
|
| 1281 |
+
"step": 141141
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 42.63,
|
| 1285 |
+
"learning_rate": 0.00032159123730809394,
|
| 1286 |
+
"loss": 0.0014,
|
| 1287 |
+
"step": 142142
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 42.93,
|
| 1291 |
+
"learning_rate": 0.0003160312381968051,
|
| 1292 |
+
"loss": 0.0013,
|
| 1293 |
+
"step": 143143
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 43.0,
|
| 1297 |
+
"eval_loss": 0.029230637475848198,
|
| 1298 |
+
"eval_max_distance": 12,
|
| 1299 |
"eval_mean_distance": 0,
|
| 1300 |
+
"eval_runtime": 0.2458,
|
| 1301 |
+
"eval_samples_per_second": 203.394,
|
| 1302 |
+
"eval_steps_per_second": 8.136,
|
| 1303 |
+
"step": 143362
|
| 1304 |
},
|
| 1305 |
{
|
| 1306 |
"epoch": 43.23,
|
| 1307 |
+
"learning_rate": 0.00031047123908551624,
|
| 1308 |
+
"loss": 0.0012,
|
| 1309 |
+
"step": 144144
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 43.53,
|
| 1313 |
+
"learning_rate": 0.0003049112399742274,
|
| 1314 |
+
"loss": 0.0012,
|
| 1315 |
+
"step": 145145
|
| 1316 |
},
|
| 1317 |
{
|
| 1318 |
+
"epoch": 43.84,
|
| 1319 |
+
"learning_rate": 0.00029935124086293854,
|
| 1320 |
+
"loss": 0.0012,
|
| 1321 |
+
"step": 146146
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"epoch": 44.0,
|
| 1325 |
+
"eval_loss": 0.03386835753917694,
|
| 1326 |
+
"eval_max_distance": 11,
|
| 1327 |
+
"eval_mean_distance": 0,
|
| 1328 |
+
"eval_runtime": 0.248,
|
| 1329 |
+
"eval_samples_per_second": 201.602,
|
| 1330 |
+
"eval_steps_per_second": 8.064,
|
| 1331 |
+
"step": 146696
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
+
"epoch": 44.14,
|
| 1335 |
+
"learning_rate": 0.0002937912417516497,
|
| 1336 |
"loss": 0.0012,
|
| 1337 |
+
"step": 147147
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
+
"epoch": 44.44,
|
| 1341 |
+
"learning_rate": 0.00028823124264036083,
|
| 1342 |
"loss": 0.0011,
|
| 1343 |
+
"step": 148148
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
+
"epoch": 44.74,
|
| 1347 |
+
"learning_rate": 0.000282671243529072,
|
| 1348 |
+
"loss": 0.0012,
|
| 1349 |
+
"step": 149149
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 45.0,
|
| 1353 |
+
"eval_loss": 0.03299795091152191,
|
| 1354 |
+
"eval_max_distance": 11,
|
| 1355 |
+
"eval_mean_distance": 0,
|
| 1356 |
+
"eval_runtime": 0.2516,
|
| 1357 |
+
"eval_samples_per_second": 198.692,
|
| 1358 |
+
"eval_steps_per_second": 7.948,
|
| 1359 |
+
"step": 150030
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
+
"epoch": 45.04,
|
| 1363 |
+
"learning_rate": 0.00027711124441778313,
|
| 1364 |
+
"loss": 0.0012,
|
| 1365 |
+
"step": 150150
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
+
"epoch": 45.34,
|
| 1369 |
+
"learning_rate": 0.0002715512453064943,
|
| 1370 |
"loss": 0.001,
|
| 1371 |
+
"step": 151151
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
+
"epoch": 45.64,
|
| 1375 |
+
"learning_rate": 0.0002659912461952054,
|
| 1376 |
"loss": 0.0011,
|
| 1377 |
+
"step": 152152
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 45.94,
|
| 1381 |
+
"learning_rate": 0.0002604312470839166,
|
| 1382 |
+
"loss": 0.001,
|
| 1383 |
+
"step": 153153
|
| 1384 |
},
|
| 1385 |
{
|
| 1386 |
"epoch": 46.0,
|
| 1387 |
+
"eval_loss": 0.030699940398335457,
|
| 1388 |
+
"eval_max_distance": 11,
|
| 1389 |
"eval_mean_distance": 0,
|
| 1390 |
+
"eval_runtime": 0.2486,
|
| 1391 |
+
"eval_samples_per_second": 201.091,
|
| 1392 |
+
"eval_steps_per_second": 8.044,
|
| 1393 |
+
"step": 153364
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 46.24,
|
| 1397 |
+
"learning_rate": 0.0002548712479726277,
|
| 1398 |
"loss": 0.001,
|
| 1399 |
+
"step": 154154
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
+
"epoch": 46.54,
|
| 1403 |
+
"learning_rate": 0.00024931124886133887,
|
| 1404 |
+
"loss": 0.0009,
|
| 1405 |
+
"step": 155155
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
+
"epoch": 46.84,
|
| 1409 |
+
"learning_rate": 0.00024375124975005,
|
| 1410 |
"loss": 0.001,
|
| 1411 |
+
"step": 156156
|
| 1412 |
},
|
| 1413 |
{
|
| 1414 |
"epoch": 47.0,
|
| 1415 |
+
"eval_loss": 0.032952647656202316,
|
| 1416 |
+
"eval_max_distance": 10,
|
| 1417 |
"eval_mean_distance": 0,
|
| 1418 |
+
"eval_runtime": 0.2471,
|
| 1419 |
+
"eval_samples_per_second": 202.373,
|
| 1420 |
+
"eval_steps_per_second": 8.095,
|
| 1421 |
+
"step": 156698
|
| 1422 |
},
|
| 1423 |
{
|
| 1424 |
+
"epoch": 47.14,
|
| 1425 |
+
"learning_rate": 0.00023819125063876117,
|
| 1426 |
+
"loss": 0.0013,
|
| 1427 |
+
"step": 157157
|
| 1428 |
},
|
| 1429 |
{
|
| 1430 |
+
"epoch": 47.44,
|
| 1431 |
+
"learning_rate": 0.0002326312515274723,
|
| 1432 |
"loss": 0.0009,
|
| 1433 |
+
"step": 158158
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
+
"epoch": 47.74,
|
| 1437 |
+
"learning_rate": 0.00022707125241618344,
|
| 1438 |
"loss": 0.0009,
|
| 1439 |
+
"step": 159159
|
| 1440 |
},
|
| 1441 |
{
|
| 1442 |
"epoch": 48.0,
|
| 1443 |
+
"eval_loss": 0.03382818400859833,
|
| 1444 |
+
"eval_max_distance": 11,
|
| 1445 |
"eval_mean_distance": 0,
|
| 1446 |
+
"eval_runtime": 0.2551,
|
| 1447 |
+
"eval_samples_per_second": 195.998,
|
| 1448 |
+
"eval_steps_per_second": 7.84,
|
| 1449 |
+
"step": 160032
|
| 1450 |
},
|
| 1451 |
{
|
| 1452 |
+
"epoch": 48.04,
|
| 1453 |
+
"learning_rate": 0.00022151125330489458,
|
| 1454 |
"loss": 0.0009,
|
| 1455 |
+
"step": 160160
|
| 1456 |
},
|
| 1457 |
{
|
| 1458 |
+
"epoch": 48.34,
|
| 1459 |
+
"learning_rate": 0.00021595125419360573,
|
| 1460 |
"loss": 0.0008,
|
| 1461 |
+
"step": 161161
|
| 1462 |
},
|
| 1463 |
{
|
| 1464 |
+
"epoch": 48.64,
|
| 1465 |
+
"learning_rate": 0.00021039125508231688,
|
| 1466 |
+
"loss": 0.0009,
|
| 1467 |
+
"step": 162162
|
| 1468 |
},
|
| 1469 |
{
|
| 1470 |
+
"epoch": 48.94,
|
| 1471 |
+
"learning_rate": 0.00020483125597102803,
|
| 1472 |
+
"loss": 0.0009,
|
| 1473 |
+
"step": 163163
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 49.0,
|
| 1477 |
+
"eval_loss": 0.02877364680171013,
|
| 1478 |
+
"eval_max_distance": 10,
|
| 1479 |
+
"eval_mean_distance": 0,
|
| 1480 |
+
"eval_runtime": 0.2518,
|
| 1481 |
+
"eval_samples_per_second": 198.574,
|
| 1482 |
+
"eval_steps_per_second": 7.943,
|
| 1483 |
+
"step": 163366
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
+
"epoch": 49.24,
|
| 1487 |
+
"learning_rate": 0.00019927125685973918,
|
| 1488 |
"loss": 0.0008,
|
| 1489 |
+
"step": 164164
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
+
"epoch": 49.54,
|
| 1493 |
+
"learning_rate": 0.0001937112577484503,
|
| 1494 |
"loss": 0.0008,
|
| 1495 |
+
"step": 165165
|
| 1496 |
},
|
| 1497 |
{
|
| 1498 |
+
"epoch": 49.84,
|
| 1499 |
+
"learning_rate": 0.00018815125863716145,
|
| 1500 |
"loss": 0.0008,
|
| 1501 |
+
"step": 166166
|
| 1502 |
},
|
| 1503 |
{
|
| 1504 |
"epoch": 50.0,
|
| 1505 |
+
"eval_loss": 0.02558927983045578,
|
| 1506 |
+
"eval_max_distance": 10,
|
| 1507 |
"eval_mean_distance": 0,
|
| 1508 |
+
"eval_runtime": 0.2461,
|
| 1509 |
+
"eval_samples_per_second": 203.155,
|
| 1510 |
+
"eval_steps_per_second": 8.126,
|
| 1511 |
+
"step": 166700
|
| 1512 |
},
|
| 1513 |
{
|
| 1514 |
+
"epoch": 50.14,
|
| 1515 |
+
"learning_rate": 0.0001825912595258726,
|
| 1516 |
+
"loss": 0.0007,
|
| 1517 |
+
"step": 167167
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
+
"epoch": 50.44,
|
| 1521 |
+
"learning_rate": 0.00017703126041458374,
|
| 1522 |
"loss": 0.0007,
|
| 1523 |
+
"step": 168168
|
| 1524 |
},
|
| 1525 |
{
|
| 1526 |
+
"epoch": 50.74,
|
| 1527 |
+
"learning_rate": 0.00017147126130329492,
|
| 1528 |
+
"loss": 0.0007,
|
| 1529 |
+
"step": 169169
|
| 1530 |
},
|
| 1531 |
{
|
| 1532 |
"epoch": 51.0,
|
| 1533 |
+
"eval_loss": 0.02841602824628353,
|
| 1534 |
+
"eval_max_distance": 11,
|
| 1535 |
"eval_mean_distance": 0,
|
| 1536 |
+
"eval_runtime": 0.2394,
|
| 1537 |
+
"eval_samples_per_second": 208.815,
|
| 1538 |
+
"eval_steps_per_second": 8.353,
|
| 1539 |
+
"step": 170034
|
| 1540 |
},
|
| 1541 |
{
|
| 1542 |
+
"epoch": 51.04,
|
| 1543 |
+
"learning_rate": 0.00016591126219200607,
|
| 1544 |
"loss": 0.0007,
|
| 1545 |
+
"step": 170170
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
+
"epoch": 51.34,
|
| 1549 |
+
"learning_rate": 0.0001603512630807172,
|
| 1550 |
"loss": 0.0007,
|
| 1551 |
+
"step": 171171
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
+
"epoch": 51.64,
|
| 1555 |
+
"learning_rate": 0.00015479126396942834,
|
| 1556 |
+
"loss": 0.0006,
|
| 1557 |
+
"step": 172172
|
| 1558 |
},
|
| 1559 |
{
|
| 1560 |
+
"epoch": 51.94,
|
| 1561 |
+
"learning_rate": 0.00014923126485813948,
|
| 1562 |
+
"loss": 0.0006,
|
| 1563 |
+
"step": 173173
|
| 1564 |
},
|
| 1565 |
{
|
| 1566 |
"epoch": 52.0,
|
| 1567 |
+
"eval_loss": 0.03416401892900467,
|
| 1568 |
+
"eval_max_distance": 10,
|
| 1569 |
"eval_mean_distance": 0,
|
| 1570 |
+
"eval_runtime": 0.2536,
|
| 1571 |
+
"eval_samples_per_second": 197.147,
|
| 1572 |
+
"eval_steps_per_second": 7.886,
|
| 1573 |
+
"step": 173368
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
+
"epoch": 52.24,
|
| 1577 |
+
"learning_rate": 0.00014367126574685063,
|
| 1578 |
"loss": 0.0006,
|
| 1579 |
+
"step": 174174
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
+
"epoch": 52.54,
|
| 1583 |
+
"learning_rate": 0.00013811126663556178,
|
| 1584 |
"loss": 0.0006,
|
| 1585 |
+
"step": 175175
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
+
"epoch": 52.84,
|
| 1589 |
+
"learning_rate": 0.00013255126752427293,
|
| 1590 |
"loss": 0.0006,
|
| 1591 |
+
"step": 176176
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 53.0,
|
| 1595 |
+
"eval_loss": 0.031156664714217186,
|
| 1596 |
+
"eval_max_distance": 10,
|
| 1597 |
+
"eval_mean_distance": 0,
|
| 1598 |
+
"eval_runtime": 0.2541,
|
| 1599 |
+
"eval_samples_per_second": 196.804,
|
| 1600 |
+
"eval_steps_per_second": 7.872,
|
| 1601 |
+
"step": 176702
|
| 1602 |
},
|
| 1603 |
{
|
| 1604 |
+
"epoch": 53.14,
|
| 1605 |
+
"learning_rate": 0.00012699126841298408,
|
| 1606 |
"loss": 0.0006,
|
| 1607 |
+
"step": 177177
|
| 1608 |
},
|
| 1609 |
{
|
| 1610 |
+
"epoch": 53.44,
|
| 1611 |
+
"learning_rate": 0.00012143126930169523,
|
| 1612 |
+
"loss": 0.0005,
|
| 1613 |
+
"step": 178178
|
| 1614 |
},
|
| 1615 |
{
|
| 1616 |
+
"epoch": 53.74,
|
| 1617 |
+
"learning_rate": 0.00011587127019040637,
|
| 1618 |
"loss": 0.0005,
|
| 1619 |
+
"step": 179179
|
| 1620 |
},
|
| 1621 |
{
|
| 1622 |
"epoch": 54.0,
|
| 1623 |
+
"eval_loss": 0.03255148231983185,
|
| 1624 |
+
"eval_max_distance": 10,
|
| 1625 |
"eval_mean_distance": 0,
|
| 1626 |
+
"eval_runtime": 0.2469,
|
| 1627 |
+
"eval_samples_per_second": 202.55,
|
| 1628 |
+
"eval_steps_per_second": 8.102,
|
| 1629 |
+
"step": 180036
|
| 1630 |
},
|
| 1631 |
{
|
| 1632 |
+
"epoch": 54.04,
|
| 1633 |
+
"learning_rate": 0.00011031127107911751,
|
| 1634 |
"loss": 0.0005,
|
| 1635 |
+
"step": 180180
|
| 1636 |
},
|
| 1637 |
{
|
| 1638 |
+
"epoch": 54.34,
|
| 1639 |
+
"learning_rate": 0.00010475127196782866,
|
| 1640 |
+
"loss": 0.0006,
|
| 1641 |
+
"step": 181181
|
| 1642 |
},
|
| 1643 |
{
|
| 1644 |
+
"epoch": 54.64,
|
| 1645 |
+
"learning_rate": 9.91912728565398e-05,
|
| 1646 |
"loss": 0.0005,
|
| 1647 |
+
"step": 182182
|
| 1648 |
},
|
| 1649 |
{
|
| 1650 |
+
"epoch": 54.94,
|
| 1651 |
+
"learning_rate": 9.363127374525095e-05,
|
| 1652 |
+
"loss": 0.0005,
|
| 1653 |
+
"step": 183183
|
| 1654 |
},
|
| 1655 |
{
|
| 1656 |
"epoch": 55.0,
|
| 1657 |
+
"eval_loss": 0.030407395213842392,
|
| 1658 |
+
"eval_max_distance": 11,
|
| 1659 |
"eval_mean_distance": 0,
|
| 1660 |
+
"eval_runtime": 0.2417,
|
| 1661 |
+
"eval_samples_per_second": 206.906,
|
| 1662 |
+
"eval_steps_per_second": 8.276,
|
| 1663 |
+
"step": 183370
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
+
"epoch": 55.24,
|
| 1667 |
+
"learning_rate": 8.80712746339621e-05,
|
| 1668 |
"loss": 0.0005,
|
| 1669 |
+
"step": 184184
|
| 1670 |
},
|
| 1671 |
{
|
| 1672 |
+
"epoch": 55.54,
|
| 1673 |
+
"learning_rate": 8.251127552267325e-05,
|
| 1674 |
"loss": 0.0004,
|
| 1675 |
+
"step": 185185
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
+
"epoch": 55.84,
|
| 1679 |
+
"learning_rate": 7.695127641138438e-05,
|
| 1680 |
"loss": 0.0005,
|
| 1681 |
+
"step": 186186
|
| 1682 |
},
|
| 1683 |
{
|
| 1684 |
"epoch": 56.0,
|
| 1685 |
+
"eval_loss": 0.02997196838259697,
|
| 1686 |
+
"eval_max_distance": 11,
|
| 1687 |
"eval_mean_distance": 0,
|
| 1688 |
+
"eval_runtime": 0.2484,
|
| 1689 |
+
"eval_samples_per_second": 201.291,
|
| 1690 |
+
"eval_steps_per_second": 8.052,
|
| 1691 |
+
"step": 186704
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
+
"epoch": 56.14,
|
| 1695 |
+
"learning_rate": 7.139127730009553e-05,
|
| 1696 |
"loss": 0.0004,
|
| 1697 |
+
"step": 187187
|
| 1698 |
},
|
| 1699 |
{
|
| 1700 |
+
"epoch": 56.45,
|
| 1701 |
+
"learning_rate": 6.583127818880668e-05,
|
| 1702 |
"loss": 0.0004,
|
| 1703 |
+
"step": 188188
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
+
"epoch": 56.75,
|
| 1707 |
+
"learning_rate": 6.027127907751783e-05,
|
| 1708 |
"loss": 0.0004,
|
| 1709 |
+
"step": 189189
|
| 1710 |
},
|
| 1711 |
{
|
| 1712 |
"epoch": 57.0,
|
| 1713 |
+
"eval_loss": 0.03127776086330414,
|
| 1714 |
+
"eval_max_distance": 11,
|
| 1715 |
"eval_mean_distance": 0,
|
| 1716 |
+
"eval_runtime": 0.2542,
|
| 1717 |
+
"eval_samples_per_second": 196.708,
|
| 1718 |
+
"eval_steps_per_second": 7.868,
|
| 1719 |
+
"step": 190038
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
+
"epoch": 57.05,
|
| 1723 |
+
"learning_rate": 5.471127996622898e-05,
|
| 1724 |
"loss": 0.0004,
|
| 1725 |
+
"step": 190190
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
+
"epoch": 57.35,
|
| 1729 |
+
"learning_rate": 4.9151280854940125e-05,
|
| 1730 |
"loss": 0.0004,
|
| 1731 |
+
"step": 191191
|
| 1732 |
},
|
| 1733 |
{
|
| 1734 |
+
"epoch": 57.65,
|
| 1735 |
+
"learning_rate": 4.359128174365127e-05,
|
| 1736 |
"loss": 0.0004,
|
| 1737 |
+
"step": 192192
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
+
"epoch": 57.95,
|
| 1741 |
+
"learning_rate": 3.803128263236242e-05,
|
| 1742 |
"loss": 0.0003,
|
| 1743 |
+
"step": 193193
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 58.0,
|
| 1747 |
+
"eval_loss": 0.03212800994515419,
|
| 1748 |
+
"eval_max_distance": 11,
|
| 1749 |
"eval_mean_distance": 0,
|
| 1750 |
+
"eval_runtime": 0.236,
|
| 1751 |
+
"eval_samples_per_second": 211.858,
|
| 1752 |
+
"eval_steps_per_second": 8.474,
|
| 1753 |
+
"step": 193372
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
+
"epoch": 58.25,
|
| 1757 |
+
"learning_rate": 3.247128352107356e-05,
|
| 1758 |
+
"loss": 0.0003,
|
| 1759 |
+
"step": 194194
|
| 1760 |
},
|
| 1761 |
{
|
| 1762 |
+
"epoch": 58.55,
|
| 1763 |
+
"learning_rate": 2.691128440978471e-05,
|
| 1764 |
"loss": 0.0004,
|
| 1765 |
+
"step": 195195
|
| 1766 |
},
|
| 1767 |
{
|
| 1768 |
+
"epoch": 58.85,
|
| 1769 |
+
"learning_rate": 2.135128529849586e-05,
|
| 1770 |
"loss": 0.0003,
|
| 1771 |
+
"step": 196196
|
| 1772 |
},
|
| 1773 |
{
|
| 1774 |
"epoch": 59.0,
|
| 1775 |
+
"eval_loss": 0.031559597700834274,
|
| 1776 |
+
"eval_max_distance": 10,
|
| 1777 |
"eval_mean_distance": 0,
|
| 1778 |
+
"eval_runtime": 0.2475,
|
| 1779 |
+
"eval_samples_per_second": 201.99,
|
| 1780 |
+
"eval_steps_per_second": 8.08,
|
| 1781 |
+
"step": 196706
|
| 1782 |
},
|
| 1783 |
{
|
| 1784 |
+
"epoch": 59.15,
|
| 1785 |
+
"learning_rate": 1.5791286187207e-05,
|
| 1786 |
+
"loss": 0.0003,
|
| 1787 |
+
"step": 197197
|
| 1788 |
},
|
| 1789 |
{
|
| 1790 |
+
"epoch": 59.45,
|
| 1791 |
+
"learning_rate": 1.023128707591815e-05,
|
| 1792 |
+
"loss": 0.0003,
|
| 1793 |
+
"step": 198198
|
| 1794 |
},
|
| 1795 |
{
|
| 1796 |
+
"epoch": 59.75,
|
| 1797 |
+
"learning_rate": 4.671287964629296e-06,
|
| 1798 |
"loss": 0.0004,
|
| 1799 |
+
"step": 199199
|
| 1800 |
},
|
| 1801 |
{
|
| 1802 |
"epoch": 60.0,
|
| 1803 |
+
"eval_loss": 0.03177854046225548,
|
| 1804 |
+
"eval_max_distance": 11,
|
| 1805 |
"eval_mean_distance": 0,
|
| 1806 |
+
"eval_runtime": 0.2438,
|
| 1807 |
+
"eval_samples_per_second": 205.126,
|
| 1808 |
+
"eval_steps_per_second": 8.205,
|
| 1809 |
+
"step": 200040
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 60.0,
|
| 1813 |
+
"step": 200040,
|
| 1814 |
+
"total_flos": 1.1617191885791232e+17,
|
| 1815 |
+
"train_loss": 0.03170474885008116,
|
| 1816 |
+
"train_runtime": 15592.8332,
|
| 1817 |
+
"train_samples_per_second": 384.846,
|
| 1818 |
+
"train_steps_per_second": 12.829
|
| 1819 |
}
|
| 1820 |
],
|
| 1821 |
+
"logging_steps": 1001,
|
| 1822 |
+
"max_steps": 200040,
|
| 1823 |
"num_train_epochs": 60,
|
| 1824 |
+
"save_steps": 2001,
|
| 1825 |
+
"total_flos": 1.1617191885791232e+17,
|
| 1826 |
"trial_name": null,
|
| 1827 |
"trial_params": null
|
| 1828 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:100e47428886cfceeb4983e829afe7caff9578529dd77c77ba43967c2229d9ca
|
| 3 |
size 4091
|