Plurczynsky
commited on
End of training
Browse files
README.md
CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# modernbert-llm-router
|
18 |
|
19 |
-
This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- F1: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
16 |
|
17 |
# modernbert-llm-router
|
18 |
|
19 |
+
This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0729
|
22 |
+
- F1: 0.7793
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
+
| 0.8558 | 1.0 | 394 | 0.7758 | 0.7761 |
|
54 |
+
| 0.5148 | 2.0 | 788 | 0.7445 | 0.7702 |
|
55 |
+
| 0.2466 | 3.0 | 1182 | 0.8782 | 0.7809 |
|
56 |
+
| 0.1071 | 4.0 | 1576 | 1.0124 | 0.7789 |
|
57 |
+
| 0.0579 | 5.0 | 1970 | 1.0729 | 0.7793 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 598476704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f1ce5a59604db282913163fabe015f5834ea8656e358fc22153a1f5233923a9
|
3 |
size 598476704
|
runs/Jan13_12-14-09_5c2d25ea5850/events.out.tfevents.1736770450.5c2d25ea5850.441003.0
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 sha256:9ea019442ef268d3335ed16f916a93391eabebc9f1ed8739693ee668dd1ccacf
|
3 |
+
size 12093
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 512
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 50283,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "[PAD]"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|