SimoneJLaudani
commited on
Commit
•
7d1777b
1
Parent(s):
c2aa982
End of training
Browse files- README.md +15 -15
- config.json +2 -3
- model.safetensors +2 -2
- runs/Mar19_18-00-21_f2dbfe237d11/events.out.tfevents.1710871228.f2dbfe237d11.373.0 +3 -0
- runs/Mar19_18-00-21_f2dbfe237d11/events.out.tfevents.1710872573.f2dbfe237d11.373.1 +3 -0
- runs/Mar19_18-00-21_f2dbfe237d11/events.out.tfevents.1710874676.f2dbfe237d11.373.2 +3 -0
- runs/Mar19_19-02-58_f2dbfe237d11/events.out.tfevents.1710874990.f2dbfe237d11.373.3 +3 -0
- runs/Mar19_19-09-41_f2dbfe237d11/events.out.tfevents.1710875388.f2dbfe237d11.373.4 +3 -0
- runs/Mar19_19-24-05_f2dbfe237d11/events.out.tfevents.1710876253.f2dbfe237d11.373.5 +3 -0
- runs/Mar19_19-40-19_f2dbfe237d11/events.out.tfevents.1710877228.f2dbfe237d11.373.6 +3 -0
- runs/Mar19_19-43-03_f2dbfe237d11/events.out.tfevents.1710877389.f2dbfe237d11.373.7 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert-base-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# trainer
|
20 |
|
21 |
-
This model is a fine-tuned version of [distilbert-base-
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 4.
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.0 | 2.83 | 150 | 4.
|
63 |
-
| 0.0 | 3.4 | 180 | 4.
|
64 |
-
| 0.0 | 3.96 | 210 | 4.
|
65 |
-
| 0.0 | 4.53 | 240 | 4.
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
18 |
|
19 |
# trainer
|
20 |
|
21 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 4.5429
|
24 |
+
- Precision: 0.6049
|
25 |
+
- Recall: 0.5714
|
26 |
+
- F1: 0.5559
|
27 |
+
- Accuracy: 0.5714
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.0126 | 0.57 | 30 | 3.5750 | 0.6388 | 0.6190 | 0.6167 | 0.6190 |
|
59 |
+
| 0.0144 | 1.13 | 60 | 3.7088 | 0.6787 | 0.6548 | 0.6479 | 0.6548 |
|
60 |
+
| 0.0364 | 1.7 | 90 | 3.5580 | 0.6614 | 0.6548 | 0.6488 | 0.6548 |
|
61 |
+
| 0.0991 | 2.26 | 120 | 3.8208 | 0.6775 | 0.6429 | 0.6407 | 0.6429 |
|
62 |
+
| 0.0 | 2.83 | 150 | 4.5110 | 0.6127 | 0.5833 | 0.5646 | 0.5833 |
|
63 |
+
| 0.0 | 3.4 | 180 | 4.5298 | 0.6127 | 0.5833 | 0.5646 | 0.5833 |
|
64 |
+
| 0.0 | 3.96 | 210 | 4.5318 | 0.6127 | 0.5833 | 0.5646 | 0.5833 |
|
65 |
+
| 0.0 | 4.53 | 240 | 4.5429 | 0.6049 | 0.5714 | 0.5559 | 0.5714 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
@@ -31,7 +31,6 @@
|
|
31 |
"model_type": "distilbert",
|
32 |
"n_heads": 12,
|
33 |
"n_layers": 6,
|
34 |
-
"output_past": true,
|
35 |
"pad_token_id": 0,
|
36 |
"problem_type": "single_label_classification",
|
37 |
"qa_dropout": 0.1,
|
@@ -40,5 +39,5 @@
|
|
40 |
"tie_weights_": true,
|
41 |
"torch_dtype": "float32",
|
42 |
"transformers_version": "4.38.2",
|
43 |
-
"vocab_size":
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
31 |
"model_type": "distilbert",
|
32 |
"n_heads": 12,
|
33 |
"n_layers": 6,
|
|
|
34 |
"pad_token_id": 0,
|
35 |
"problem_type": "single_label_classification",
|
36 |
"qa_dropout": 0.1,
|
|
|
39 |
"tie_weights_": true,
|
40 |
"torch_dtype": "float32",
|
41 |
"transformers_version": "4.38.2",
|
42 |
+
"vocab_size": 30522
|
43 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e26700f82c8e469c99655b2ce484621837d170b68067f2313596e36af97eb889
|
3 |
+
size 267847948
|
runs/Mar19_18-00-21_f2dbfe237d11/events.out.tfevents.1710871228.f2dbfe237d11.373.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bd954040ba4c9efb68182b05c78fcc14d7e2a60a8498c343b9417564263db5a
|
3 |
+
size 10486
|
runs/Mar19_18-00-21_f2dbfe237d11/events.out.tfevents.1710872573.f2dbfe237d11.373.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42676bb6cdf8282830a9d6c4e7b6a2ba76eda162811f391f9015d3e354c60d03
|
3 |
+
size 10535
|
runs/Mar19_18-00-21_f2dbfe237d11/events.out.tfevents.1710874676.f2dbfe237d11.373.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b1e63b4a4ea590bc12252e2665b037e243b915906542e58cf582d06b5502769
|
3 |
+
size 6109
|
runs/Mar19_19-02-58_f2dbfe237d11/events.out.tfevents.1710874990.f2dbfe237d11.373.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bda49810f01f0242bd652b6ebd5421cc09216b9bb8ebef119433b540e8a42d7
|
3 |
+
size 6779
|
runs/Mar19_19-09-41_f2dbfe237d11/events.out.tfevents.1710875388.f2dbfe237d11.373.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c82f3aec37f23aef28aa148e611bb3c44e7dcf0cd3b75b78b5a397a50ea0b00
|
3 |
+
size 9498
|
runs/Mar19_19-24-05_f2dbfe237d11/events.out.tfevents.1710876253.f2dbfe237d11.373.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c381847a8a0cfc7db60dce8a00a41aece6297191bec2303cf93367dff86c1c2
|
3 |
+
size 10535
|
runs/Mar19_19-40-19_f2dbfe237d11/events.out.tfevents.1710877228.f2dbfe237d11.373.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24c751ad751e97dae27d3ddb450acfbf818c392e13b330488febfd2c2ece647f
|
3 |
+
size 5439
|
runs/Mar19_19-43-03_f2dbfe237d11/events.out.tfevents.1710877389.f2dbfe237d11.373.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb22fdcb29b880a8295fa5eee26ce7eea385fddd4dcd930ac45de647e3b3f323
|
3 |
+
size 10535
|
tokenizer_config.json
CHANGED
@@ -44,7 +44,7 @@
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
-
"do_lower_case":
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
"never_split": null,
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
"never_split": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce3382def35726fe9f8dd02e330d086b6ee5535ebde116b86c24b332099b1bd5
|
3 |
size 4856
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|