DouglasPontes
commited on
Commit
•
0f15cef
1
Parent(s):
c7ea2ef
End of training
Browse files- README.md +1 -1
- all_results.json +10 -10
- eval_results.json +5 -5
- train_results.json +5 -5
- 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: 1.
|
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: 1.9012
|
19 |
|
20 |
## Model description
|
21 |
|
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"epoch": 49.17,
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 41102,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"perplexity":
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples":
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second":
|
14 |
}
|
|
|
1 |
{
|
2 |
"epoch": 49.17,
|
3 |
+
"eval_loss": 1.9011980295181274,
|
4 |
+
"eval_runtime": 46.9736,
|
5 |
"eval_samples": 41102,
|
6 |
+
"eval_samples_per_second": 875.002,
|
7 |
+
"eval_steps_per_second": 54.69,
|
8 |
+
"perplexity": 6.693909141140503,
|
9 |
+
"train_loss": 2.0531104736328123,
|
10 |
+
"train_runtime": 167230.1572,
|
11 |
+
"train_samples": 780940,
|
12 |
+
"train_samples_per_second": 229.624,
|
13 |
+
"train_steps_per_second": 14.351
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 49.17,
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 41102,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"perplexity":
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 49.17,
|
3 |
+
"eval_loss": 1.9011980295181274,
|
4 |
+
"eval_runtime": 46.9736,
|
5 |
"eval_samples": 41102,
|
6 |
+
"eval_samples_per_second": 875.002,
|
7 |
+
"eval_steps_per_second": 54.69,
|
8 |
+
"perplexity": 6.693909141140503
|
9 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 49.17,
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 49.17,
|
3 |
+
"train_loss": 2.0531104736328123,
|
4 |
+
"train_runtime": 167230.1572,
|
5 |
+
"train_samples": 780940,
|
6 |
+
"train_samples_per_second": 229.624,
|
7 |
+
"train_steps_per_second": 14.351
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|