End of training
Browse files- README.md +1 -1
- all_results.json +12 -12
- eval_results.json +7 -7
- train_results.json +6 -6
- 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: 2.5608
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 2.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 55.
|
| 8 |
-
"perplexity":
|
| 9 |
-
"train_loss": 2.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples":
|
| 12 |
-
"train_samples_per_second": 173.
|
| 13 |
-
"train_steps_per_second": 10.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.11,
|
| 3 |
+
"eval_loss": 2.560811996459961,
|
| 4 |
+
"eval_runtime": 225.5262,
|
| 5 |
+
"eval_samples": 200000,
|
| 6 |
+
"eval_samples_per_second": 886.815,
|
| 7 |
+
"eval_steps_per_second": 55.426,
|
| 8 |
+
"perplexity": 12.94632541910408,
|
| 9 |
+
"train_loss": 2.9681437548828127,
|
| 10 |
+
"train_runtime": 221059.9809,
|
| 11 |
+
"train_samples": 3799999,
|
| 12 |
+
"train_samples_per_second": 173.709,
|
| 13 |
+
"train_steps_per_second": 10.857
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 2.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 55.
|
| 8 |
-
"perplexity":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.11,
|
| 3 |
+
"eval_loss": 2.560811996459961,
|
| 4 |
+
"eval_runtime": 225.5262,
|
| 5 |
+
"eval_samples": 200000,
|
| 6 |
+
"eval_samples_per_second": 886.815,
|
| 7 |
+
"eval_steps_per_second": 55.426,
|
| 8 |
+
"perplexity": 12.94632541910408
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 2.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second": 173.
|
| 7 |
-
"train_steps_per_second": 10.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.11,
|
| 3 |
+
"train_loss": 2.9681437548828127,
|
| 4 |
+
"train_runtime": 221059.9809,
|
| 5 |
+
"train_samples": 3799999,
|
| 6 |
+
"train_samples_per_second": 173.709,
|
| 7 |
+
"train_steps_per_second": 10.857
|
| 8 |
}
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|