Commit
•
8713311
1
Parent(s):
cdd263f
End of training
Browse files- README.md +1 -1
- all_results.json +9 -9
- eval_results.json +5 -5
- train_results.json +4 -4
- trainer_state.json +0 -0
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-2019-90m](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 2.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-2019-90m](https://huggingface.co/cardiffnlp/twitter-roberta-base-2019-90m) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.4514
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.83,
|
| 3 |
-
"eval_loss": 2.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 205510,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 55.
|
| 8 |
-
"perplexity":
|
| 9 |
-
"train_loss": 2.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 3904699,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 10.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.83,
|
| 3 |
+
"eval_loss": 2.4514307975769043,
|
| 4 |
+
"eval_runtime": 229.7941,
|
| 5 |
"eval_samples": 205510,
|
| 6 |
+
"eval_samples_per_second": 894.323,
|
| 7 |
+
"eval_steps_per_second": 55.898,
|
| 8 |
+
"perplexity": 11.604939165014551,
|
| 9 |
+
"train_loss": 2.5438934391276042,
|
| 10 |
+
"train_runtime": 220778.1092,
|
| 11 |
"train_samples": 3904699,
|
| 12 |
+
"train_samples_per_second": 173.93,
|
| 13 |
+
"train_steps_per_second": 10.871
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.83,
|
| 3 |
-
"eval_loss": 2.
|
| 4 |
-
"eval_runtime":
|
| 5 |
"eval_samples": 205510,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 55.
|
| 8 |
-
"perplexity":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.83,
|
| 3 |
+
"eval_loss": 2.4514307975769043,
|
| 4 |
+
"eval_runtime": 229.7941,
|
| 5 |
"eval_samples": 205510,
|
| 6 |
+
"eval_samples_per_second": 894.323,
|
| 7 |
+
"eval_steps_per_second": 55.898,
|
| 8 |
+
"perplexity": 11.604939165014551
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 9.83,
|
| 3 |
-
"train_loss": 2.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 3904699,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 10.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 9.83,
|
| 3 |
+
"train_loss": 2.5438934391276042,
|
| 4 |
+
"train_runtime": 220778.1092,
|
| 5 |
"train_samples": 3904699,
|
| 6 |
+
"train_samples_per_second": 173.93,
|
| 7 |
+
"train_steps_per_second": 10.871
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|