End of training
Browse files
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 an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 2.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -46,31 +46,31 @@ The following hyperparameters were used during training:
|
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| No log | 1.0 | 39 | 7.
|
50 |
-
| No log | 2.0 | 78 | 6.
|
51 |
-
| No log | 3.0 | 117 | 5.
|
52 |
-
| No log | 4.0 | 156 | 4.
|
53 |
-
| No log | 5.0 | 195 | 4.
|
54 |
-
| No log | 6.0 | 234 | 3.
|
55 |
-
| No log | 7.0 | 273 | 3.
|
56 |
-
| No log | 8.0 | 312 | 3.
|
57 |
-
| No log | 9.0 | 351 | 3.
|
58 |
-
| No log | 10.0 | 390 | 3.
|
59 |
-
| No log | 11.0 | 429 | 3.
|
60 |
-
| No log | 12.0 | 468 | 3.
|
61 |
-
| 4.
|
62 |
-
| 4.
|
63 |
-
| 4.
|
64 |
-
| 4.
|
65 |
-
| 4.
|
66 |
-
| 4.
|
67 |
-
| 4.
|
68 |
-
| 4.
|
69 |
-
| 4.
|
70 |
-
| 4.
|
71 |
-
| 4.
|
72 |
-
| 4.
|
73 |
-
| 4.
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.9920
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 39 | 7.8584 |
|
50 |
+
| No log | 2.0 | 78 | 6.4713 |
|
51 |
+
| No log | 3.0 | 117 | 5.4690 |
|
52 |
+
| No log | 4.0 | 156 | 4.7140 |
|
53 |
+
| No log | 5.0 | 195 | 4.1569 |
|
54 |
+
| No log | 6.0 | 234 | 3.7854 |
|
55 |
+
| No log | 7.0 | 273 | 3.5573 |
|
56 |
+
| No log | 8.0 | 312 | 3.4160 |
|
57 |
+
| No log | 9.0 | 351 | 3.3223 |
|
58 |
+
| No log | 10.0 | 390 | 3.2547 |
|
59 |
+
| No log | 11.0 | 429 | 3.2044 |
|
60 |
+
| No log | 12.0 | 468 | 3.1632 |
|
61 |
+
| 4.6041 | 13.0 | 507 | 3.1322 |
|
62 |
+
| 4.6041 | 14.0 | 546 | 3.1054 |
|
63 |
+
| 4.6041 | 15.0 | 585 | 3.0849 |
|
64 |
+
| 4.6041 | 16.0 | 624 | 3.0633 |
|
65 |
+
| 4.6041 | 17.0 | 663 | 3.0490 |
|
66 |
+
| 4.6041 | 18.0 | 702 | 3.0339 |
|
67 |
+
| 4.6041 | 19.0 | 741 | 3.0230 |
|
68 |
+
| 4.6041 | 20.0 | 780 | 3.0134 |
|
69 |
+
| 4.6041 | 21.0 | 819 | 3.0055 |
|
70 |
+
| 4.6041 | 22.0 | 858 | 2.9999 |
|
71 |
+
| 4.6041 | 23.0 | 897 | 2.9954 |
|
72 |
+
| 4.6041 | 24.0 | 936 | 2.9929 |
|
73 |
+
| 4.6041 | 25.0 | 975 | 2.9920 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
generation_config.json
CHANGED
@@ -2,7 +2,6 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 2,
|
5 |
-
"output_hidden_states": true,
|
6 |
"pad_token_id": 1,
|
7 |
"transformers_version": "4.35.2"
|
8 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 2,
|
|
|
5 |
"pad_token_id": 1,
|
6 |
"transformers_version": "4.35.2"
|
7 |
}
|
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 sha256:69455ecb1dcdc862b629342561d8d4f0cb21e45b3cb4983cb3ad7a98bc5c1230
|
3 |
size 328693404
|
runs/Feb19_09-36-16_b58b79c23f7e/events.out.tfevents.1708335383.b58b79c23f7e.2842.2
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:ef0e8b54c853048595b2fa382ff2f9d8f0357c63164c9a5eb0523ac3888acdb6
|
3 |
+
size 11549
|
runs/Feb19_09-36-16_b58b79c23f7e/events.out.tfevents.1708336148.b58b79c23f7e.2842.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e3e5de99611de34804c2be00be8f3294268652ad72e5717971483f8c641817c
|
3 |
+
size 359
|