End of training
Browse files- README.md +7 -37
- config.json +1 -1
- model.safetensors +1 -1
- runs/Jan07_19-50-54_2c2be611b99b/events.out.tfevents.1704657723.2c2be611b99b.440.2 +3 -0
- training_args.bin +1 -1
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 [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,47 +40,17 @@ The following hyperparameters were used during training:
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
|
|
50 |
-
|
|
51 |
-
|
|
52 |
-
|
|
53 |
-
| 1.
|
54 |
-
| 1.729 | 6.0 | 1422 | 1.5996 |
|
55 |
-
| 1.4949 | 7.0 | 1659 | 1.5250 |
|
56 |
-
| 1.4949 | 8.0 | 1896 | 1.4521 |
|
57 |
-
| 1.3437 | 9.0 | 2133 | 1.4227 |
|
58 |
-
| 1.3437 | 10.0 | 2370 | 1.4164 |
|
59 |
-
| 1.1716 | 11.0 | 2607 | 1.3883 |
|
60 |
-
| 1.1716 | 12.0 | 2844 | 1.3573 |
|
61 |
-
| 1.0851 | 13.0 | 3081 | 1.3602 |
|
62 |
-
| 1.0851 | 14.0 | 3318 | 1.2873 |
|
63 |
-
| 0.9756 | 15.0 | 3555 | 1.2825 |
|
64 |
-
| 0.9756 | 16.0 | 3792 | 1.2744 |
|
65 |
-
| 0.9178 | 17.0 | 4029 | 1.2702 |
|
66 |
-
| 0.9178 | 18.0 | 4266 | 1.2629 |
|
67 |
-
| 0.8283 | 19.0 | 4503 | 1.2731 |
|
68 |
-
| 0.8283 | 20.0 | 4740 | 1.1455 |
|
69 |
-
| 0.8283 | 21.0 | 4977 | 1.2067 |
|
70 |
-
| 0.7733 | 22.0 | 5214 | 1.1868 |
|
71 |
-
| 0.7733 | 23.0 | 5451 | 1.1915 |
|
72 |
-
| 0.7167 | 24.0 | 5688 | 1.1226 |
|
73 |
-
| 0.7167 | 25.0 | 5925 | 1.1329 |
|
74 |
-
| 0.681 | 26.0 | 6162 | 1.1684 |
|
75 |
-
| 0.681 | 27.0 | 6399 | 1.1707 |
|
76 |
-
| 0.6346 | 28.0 | 6636 | 1.0747 |
|
77 |
-
| 0.6346 | 29.0 | 6873 | 1.1317 |
|
78 |
-
| 0.6035 | 30.0 | 7110 | 1.1026 |
|
79 |
-
| 0.6035 | 31.0 | 7347 | 1.1029 |
|
80 |
-
| 0.5947 | 32.0 | 7584 | 1.0896 |
|
81 |
-
| 0.5947 | 33.0 | 7821 | 1.1341 |
|
82 |
-
| 0.5426 | 34.0 | 8058 | 1.0862 |
|
83 |
-
| 0.5426 | 35.0 | 8295 | 1.0757 |
|
84 |
|
85 |
|
86 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.4194
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 5
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 2.0236 | 1.0 | 581 | 1.7083 |
|
50 |
+
| 1.8282 | 2.0 | 1162 | 1.6452 |
|
51 |
+
| 1.6842 | 3.0 | 1743 | 1.5066 |
|
52 |
+
| 1.5534 | 4.0 | 2324 | 1.4436 |
|
53 |
+
| 1.4659 | 5.0 | 2905 | 1.4194 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_name_or_path": "distilroberta-base",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
1 |
{
|
2 |
"_name_or_path": "distilroberta-base",
|
3 |
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328693404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04b25b0366b3bc3d710c21a91ae306f7356c869bdad69b9af19c7a29603599d1
|
3 |
size 328693404
|
runs/Jan07_19-50-54_2c2be611b99b/events.out.tfevents.1704657723.2c2be611b99b.440.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e405d1a781eb01a655adbe9b6c0d50903209664af133d0396e8900e5607cddf
|
3 |
+
size 6806
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93dae5ddfa779b92041dd39d1ca38396e150b8ab604fb70573ff814013786b19
|
3 |
size 4600
|