cotysong113
commited on
Commit
•
7686fe1
1
Parent(s):
557d482
Training in progress, step 2862
Browse files- README.md +14 -14
- config.json +1 -1
- model.safetensors +1 -1
- tokenizer.json +1 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -50,21 +50,21 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
-
- Transformers 4.47.
|
68 |
-
- Pytorch 2.5.1
|
69 |
- Datasets 3.2.0
|
70 |
- Tokenizers 0.21.0
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3223
|
22 |
+
- Accuracy: 0.9461
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| 2.8424 | 1.0 | 318 | 2.0795 | 0.7271 |
|
54 |
+
| 1.6103 | 2.0 | 636 | 1.0650 | 0.8577 |
|
55 |
+
| 0.8466 | 3.0 | 954 | 0.6074 | 0.9135 |
|
56 |
+
| 0.4999 | 4.0 | 1272 | 0.4376 | 0.9310 |
|
57 |
+
| 0.3539 | 5.0 | 1590 | 0.3770 | 0.9397 |
|
58 |
+
| 0.2899 | 6.0 | 1908 | 0.3515 | 0.9419 |
|
59 |
+
| 0.2589 | 7.0 | 2226 | 0.3353 | 0.9448 |
|
60 |
+
| 0.2418 | 8.0 | 2544 | 0.3276 | 0.9458 |
|
61 |
+
| 0.2319 | 9.0 | 2862 | 0.3234 | 0.9458 |
|
62 |
+
| 0.2284 | 10.0 | 3180 | 0.3223 | 0.9461 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
+
- Transformers 4.47.1
|
68 |
+
- Pytorch 2.5.1+cu124
|
69 |
- Datasets 3.2.0
|
70 |
- Tokenizers 0.21.0
|
config.json
CHANGED
@@ -326,6 +326,6 @@
|
|
326 |
"sinusoidal_pos_embds": false,
|
327 |
"tie_weights_": true,
|
328 |
"torch_dtype": "float32",
|
329 |
-
"transformers_version": "4.47.
|
330 |
"vocab_size": 30522
|
331 |
}
|
|
|
326 |
"sinusoidal_pos_embds": false,
|
327 |
"tie_weights_": true,
|
328 |
"torch_dtype": "float32",
|
329 |
+
"transformers_version": "4.47.1",
|
330 |
"vocab_size": 30522
|
331 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268290900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:794fad7b47b0fe92673e092e17f8aea9beceeccdfe377212201cac5f6df3aeac
|
3 |
size 268290900
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a726f8484aefbc7550edb1167a34362de730f8d4644e045d57fe4d3ea85e937
|
3 |
size 5432
|