jenslemmens
commited on
Commit
•
aaea1f5
1
Parent(s):
f451d11
End of training
Browse files- README.md +8 -0
- all_results.json +6 -6
- eval_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +3 -3
README.md
CHANGED
@@ -3,6 +3,9 @@ license: mit
|
|
3 |
base_model: xlm-roberta-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: dutch_genre_classifier
|
8 |
results: []
|
@@ -14,6 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# dutch_genre_classifier
|
15 |
|
16 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: xlm-roberta-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
model-index:
|
10 |
- name: dutch_genre_classifier
|
11 |
results: []
|
|
|
17 |
# dutch_genre_classifier
|
18 |
|
19 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1404
|
22 |
+
- Precision: 0.9713
|
23 |
+
- Recall: 0.9707
|
24 |
+
- Fscore: 0.9707
|
25 |
|
26 |
## Model description
|
27 |
|
all_results.json
CHANGED
@@ -4,13 +4,13 @@
|
|
4 |
"eval_loss": 0.14040668308734894,
|
5 |
"eval_precision": 0.971255206348869,
|
6 |
"eval_recall": 0.9707142857142858,
|
7 |
-
"eval_runtime": 9.
|
8 |
"eval_samples": 1400,
|
9 |
-
"eval_samples_per_second": 154.
|
10 |
-
"eval_steps_per_second": 19.
|
11 |
"train_loss": 0.23042542536496113,
|
12 |
-
"train_runtime":
|
13 |
"train_samples": 11415,
|
14 |
-
"train_samples_per_second": 40.
|
15 |
-
"train_steps_per_second": 2.
|
16 |
}
|
|
|
4 |
"eval_loss": 0.14040668308734894,
|
5 |
"eval_precision": 0.971255206348869,
|
6 |
"eval_recall": 0.9707142857142858,
|
7 |
+
"eval_runtime": 9.0796,
|
8 |
"eval_samples": 1400,
|
9 |
+
"eval_samples_per_second": 154.192,
|
10 |
+
"eval_steps_per_second": 19.274,
|
11 |
"train_loss": 0.23042542536496113,
|
12 |
+
"train_runtime": 560.0994,
|
13 |
"train_samples": 11415,
|
14 |
+
"train_samples_per_second": 40.761,
|
15 |
+
"train_steps_per_second": 2.546
|
16 |
}
|
eval_results.json
CHANGED
@@ -4,8 +4,8 @@
|
|
4 |
"eval_loss": 0.14040668308734894,
|
5 |
"eval_precision": 0.971255206348869,
|
6 |
"eval_recall": 0.9707142857142858,
|
7 |
-
"eval_runtime": 9.
|
8 |
"eval_samples": 1400,
|
9 |
-
"eval_samples_per_second": 154.
|
10 |
-
"eval_steps_per_second": 19.
|
11 |
}
|
|
|
4 |
"eval_loss": 0.14040668308734894,
|
5 |
"eval_precision": 0.971255206348869,
|
6 |
"eval_recall": 0.9707142857142858,
|
7 |
+
"eval_runtime": 9.0796,
|
8 |
"eval_samples": 1400,
|
9 |
+
"eval_samples_per_second": 154.192,
|
10 |
+
"eval_steps_per_second": 19.274
|
11 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"train_loss": 0.23042542536496113,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 11415,
|
6 |
-
"train_samples_per_second": 40.
|
7 |
-
"train_steps_per_second": 2.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"train_loss": 0.23042542536496113,
|
4 |
+
"train_runtime": 560.0994,
|
5 |
"train_samples": 11415,
|
6 |
+
"train_samples_per_second": 40.761,
|
7 |
+
"train_steps_per_second": 2.546
|
8 |
}
|
trainer_state.json
CHANGED
@@ -25,9 +25,9 @@
|
|
25 |
"step": 1426,
|
26 |
"total_flos": 6003148215168000.0,
|
27 |
"train_loss": 0.23042542536496113,
|
28 |
-
"train_runtime":
|
29 |
-
"train_samples_per_second": 40.
|
30 |
-
"train_steps_per_second": 2.
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 500,
|
|
|
25 |
"step": 1426,
|
26 |
"total_flos": 6003148215168000.0,
|
27 |
"train_loss": 0.23042542536496113,
|
28 |
+
"train_runtime": 560.0994,
|
29 |
+
"train_samples_per_second": 40.761,
|
30 |
+
"train_steps_per_second": 2.546
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 500,
|