Model save
Browse files- README.md +53 -53
- all_results.json +5 -5
- train_results.json +5 -5
README.md
CHANGED
|
@@ -5,18 +5,18 @@ base_model: gpt2
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -48,56 +48,56 @@ The following hyperparameters were used during training:
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:------:|:---------------:|
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
|
| 102 |
|
| 103 |
### Framework versions
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
+
- name: Se124M100KInfKeyValue
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# Se124M100KInfKeyValue
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4826
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:------:|:---------------:|
|
| 51 |
+
| 0.1533 | 1.0 | 2090 | 0.5677 |
|
| 52 |
+
| 0.141 | 2.0 | 4180 | 0.5401 |
|
| 53 |
+
| 0.1401 | 3.0 | 6270 | 0.5321 |
|
| 54 |
+
| 0.1351 | 4.0 | 8360 | 0.5224 |
|
| 55 |
+
| 0.1361 | 5.0 | 10450 | 0.5209 |
|
| 56 |
+
| 0.134 | 6.0 | 12540 | 0.5155 |
|
| 57 |
+
| 0.1315 | 7.0 | 14630 | 0.5118 |
|
| 58 |
+
| 0.1304 | 8.0 | 16720 | 0.5085 |
|
| 59 |
+
| 0.1299 | 9.0 | 18810 | 0.5067 |
|
| 60 |
+
| 0.1294 | 10.0 | 20900 | 0.5066 |
|
| 61 |
+
| 0.1309 | 11.0 | 22990 | 0.5030 |
|
| 62 |
+
| 0.129 | 12.0 | 25080 | 0.5004 |
|
| 63 |
+
| 0.1292 | 13.0 | 27170 | 0.4999 |
|
| 64 |
+
| 0.1309 | 14.0 | 29260 | 0.4985 |
|
| 65 |
+
| 0.1312 | 15.0 | 31350 | 0.4974 |
|
| 66 |
+
| 0.1275 | 16.0 | 33440 | 0.4963 |
|
| 67 |
+
| 0.1265 | 17.0 | 35530 | 0.4950 |
|
| 68 |
+
| 0.1276 | 18.0 | 37620 | 0.4936 |
|
| 69 |
+
| 0.1247 | 19.0 | 39710 | 0.4931 |
|
| 70 |
+
| 0.1268 | 20.0 | 41800 | 0.4919 |
|
| 71 |
+
| 0.1273 | 21.0 | 43890 | 0.4914 |
|
| 72 |
+
| 0.1284 | 22.0 | 45980 | 0.4907 |
|
| 73 |
+
| 0.1276 | 23.0 | 48070 | 0.4898 |
|
| 74 |
+
| 0.1284 | 24.0 | 50160 | 0.4894 |
|
| 75 |
+
| 0.1263 | 25.0 | 52250 | 0.4894 |
|
| 76 |
+
| 0.1264 | 26.0 | 54340 | 0.4888 |
|
| 77 |
+
| 0.1257 | 27.0 | 56430 | 0.4881 |
|
| 78 |
+
| 0.1292 | 28.0 | 58520 | 0.4875 |
|
| 79 |
+
| 0.1262 | 29.0 | 60610 | 0.4874 |
|
| 80 |
+
| 0.1272 | 30.0 | 62700 | 0.4867 |
|
| 81 |
+
| 0.1252 | 31.0 | 64790 | 0.4864 |
|
| 82 |
+
| 0.1261 | 32.0 | 66880 | 0.4859 |
|
| 83 |
+
| 0.1262 | 33.0 | 68970 | 0.4858 |
|
| 84 |
+
| 0.1256 | 34.0 | 71060 | 0.4849 |
|
| 85 |
+
| 0.1251 | 35.0 | 73150 | 0.4847 |
|
| 86 |
+
| 0.1263 | 36.0 | 75240 | 0.4843 |
|
| 87 |
+
| 0.1266 | 37.0 | 77330 | 0.4843 |
|
| 88 |
+
| 0.125 | 38.0 | 79420 | 0.4842 |
|
| 89 |
+
| 0.1248 | 39.0 | 81510 | 0.4840 |
|
| 90 |
+
| 0.126 | 40.0 | 83600 | 0.4837 |
|
| 91 |
+
| 0.1239 | 41.0 | 85690 | 0.4831 |
|
| 92 |
+
| 0.1246 | 42.0 | 87780 | 0.4837 |
|
| 93 |
+
| 0.1241 | 43.0 | 89870 | 0.4830 |
|
| 94 |
+
| 0.1259 | 44.0 | 91960 | 0.4829 |
|
| 95 |
+
| 0.1275 | 45.0 | 94050 | 0.4828 |
|
| 96 |
+
| 0.1258 | 46.0 | 96140 | 0.4826 |
|
| 97 |
+
| 0.1265 | 47.0 | 98230 | 0.4828 |
|
| 98 |
+
| 0.1235 | 48.0 | 100320 | 0.4827 |
|
| 99 |
+
| 0.1255 | 49.0 | 102410 | 0.4827 |
|
| 100 |
+
| 0.1245 | 50.0 | 104500 | 0.4826 |
|
| 101 |
|
| 102 |
|
| 103 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -5,9 +5,9 @@
|
|
| 5 |
"eval_samples_per_second": 158.911,
|
| 6 |
"eval_steps_per_second": 4.972,
|
| 7 |
"perplexity": 1.5811901214941453,
|
| 8 |
-
"total_flos": 2.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 9.
|
| 13 |
}
|
|
|
|
| 5 |
"eval_samples_per_second": 158.911,
|
| 6 |
"eval_steps_per_second": 4.972,
|
| 7 |
"perplexity": 1.5811901214941453,
|
| 8 |
+
"total_flos": 2.191516447408128e+17,
|
| 9 |
+
"train_loss": 0.12956011656254673,
|
| 10 |
+
"train_runtime": 10667.5849,
|
| 11 |
+
"train_samples_per_second": 313.407,
|
| 12 |
+
"train_steps_per_second": 9.796
|
| 13 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 50.0,
|
| 3 |
-
"total_flos": 2.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 9.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 50.0,
|
| 3 |
+
"total_flos": 2.191516447408128e+17,
|
| 4 |
+
"train_loss": 0.12956011656254673,
|
| 5 |
+
"train_runtime": 10667.5849,
|
| 6 |
+
"train_samples_per_second": 313.407,
|
| 7 |
+
"train_steps_per_second": 9.796
|
| 8 |
}
|