dpravinv commited on
Commit
67d5ebb
·
verified ·
1 Parent(s): 12066e9

Model save

Browse files
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 [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: 1.2870
22
- - F1: 0.7538
23
 
24
  ## Model description
25
 
@@ -50,21 +50,21 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | No log | 1.0 | 20 | 1.0667 | 0.4175 |
54
- | No log | 2.0 | 40 | 0.8725 | 0.6812 |
55
- | No log | 3.0 | 60 | 0.6462 | 0.7165 |
56
- | No log | 4.0 | 80 | 0.6401 | 0.7590 |
57
- | 0.6701 | 5.0 | 100 | 1.1543 | 0.7228 |
58
- | 0.6701 | 6.0 | 120 | 1.2284 | 0.7242 |
59
- | 0.6701 | 7.0 | 140 | 1.2582 | 0.7567 |
60
- | 0.6701 | 8.0 | 160 | 1.3976 | 0.7468 |
61
- | 0.6701 | 9.0 | 180 | 1.2946 | 0.7321 |
62
- | 0.0083 | 10.0 | 200 | 1.2870 | 0.7538 |
63
 
64
 
65
  ### Framework versions
66
 
67
- - Transformers 4.48.0
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 [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: 1.1954
22
+ - F1: 0.8447
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | F1 |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.425 | 1.0 | 300 | 0.4228 | 0.8290 |
54
+ | 0.265 | 2.0 | 600 | 0.4118 | 0.8407 |
55
+ | 0.1577 | 3.0 | 900 | 0.4843 | 0.8540 |
56
+ | 0.0773 | 4.0 | 1200 | 0.7007 | 0.8394 |
57
+ | 0.0406 | 5.0 | 1500 | 0.8548 | 0.8487 |
58
+ | 0.0192 | 6.0 | 1800 | 1.0277 | 0.8444 |
59
+ | 0.0184 | 7.0 | 2100 | 0.9923 | 0.8469 |
60
+ | 0.0068 | 8.0 | 2400 | 1.1065 | 0.8461 |
61
+ | 0.0049 | 9.0 | 2700 | 1.1675 | 0.8448 |
62
+ | 0.0014 | 10.0 | 3000 | 1.1954 | 0.8447 |
63
 
64
 
65
  ### Framework versions
66
 
67
+ - Transformers 4.48.0.dev0
68
+ - Pytorch 2.6.0+cu124
69
+ - Datasets 3.1.0
70
  - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e0386449807f132fbee911ab13d9095f7915760989e475b1a1a3b23533618b6
3
  size 598445936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f08180ba1dd750faecbc0f8a061dcfc0ab7f38cba6a2b9af17c48ed6049a0e2
3
  size 598445936
runs/Feb24_13-12-51_vapratux/events.out.tfevents.1740399172.vapratux.103021.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbdedbd52d545f0f4fc5dde56093bbb9ceaa0a578697a397667f5d9d7faf0ae9
3
- size 15207
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56762dd582eadf0b21b28b8628198ccd5ac545b5e8497efbc932440d8b7bccfb
3
+ size 15878