Hugging Face's logo

ferrazzipietro
/
ULS-MultiClinNERit-Qwen2.5-14B-symptom-MASKED

PEFT
Safetensors
Transformers
lora
Model card Files
xet
 Community
ferrazzipietro commited on
Commit
f5c2fd7
·
verified ·
1 Parent(s): 5167de6

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. README.md +17 -17
  2. adapter_model.safetensors +1 -1
  3. tokenizer.json +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -12,22 +12,22 @@ metrics:
12
  - f1
13
  - accuracy
14
  model-index:
15
- - name: ULS-MultiClinNERit-Qwen2.5-14B-symptom
16
  results: []
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
  should probably proofread and complete it, then remove this comment. -->
21
 
22
- # ULS-MultiClinNERit-Qwen2.5-14B-symptom
23
 
24
  This model is a fine-tuned version of [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) on an unknown dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.3812
27
- - Precision: 0.4376
28
- - Recall: 0.5496
29
- - F1: 0.4873
30
- - Accuracy: 0.9458
31
 
32
  ## Model description
33
 
@@ -58,16 +58,16 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
- | No log | 1.0 | 168 | 0.2069 | 0.2694 | 0.2529 | 0.2609 | 0.9208 |
62
- | No log | 2.0 | 336 | 0.1667 | 0.3549 | 0.5019 | 0.4158 | 0.9364 |
63
- | 0.2569 | 3.0 | 504 | 0.1586 | 0.3736 | 0.5389 | 0.4413 | 0.9382 |
64
- | 0.2569 | 4.0 | 672 | 0.1765 | 0.4043 | 0.5486 | 0.4655 | 0.9412 |
65
- | 0.2569 | 5.0 | 840 | 0.2056 | 0.4261 | 0.5272 | 0.4713 | 0.9440 |
66
- | 0.04 | 6.0 | 1008 | 0.2491 | 0.4209 | 0.5593 | 0.4804 | 0.9459 |
67
- | 0.04 | 7.0 | 1176 | 0.2821 | 0.4333 | 0.5399 | 0.4807 | 0.9463 |
68
- | 0.04 | 8.0 | 1344 | 0.3583 | 0.4479 | 0.5438 | 0.4912 | 0.9467 |
69
- | 0.0047 | 9.0 | 1512 | 0.3684 | 0.4477 | 0.5574 | 0.4965 | 0.9464 |
70
- | 0.0047 | 10.0 | 1680 | 0.3812 | 0.4376 | 0.5496 | 0.4873 | 0.9458 |
71
 
72
 
73
  ### Framework versions
 
12
  - f1
13
  - accuracy
14
  model-index:
15
+ - name: ULS-MultiClinNERit-Qwen2.5-14B-procedure
16
  results: []
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
  should probably proofread and complete it, then remove this comment. -->
21
 
22
+ # ULS-MultiClinNERit-Qwen2.5-14B-procedure
23
 
24
  This model is a fine-tuned version of [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) on an unknown dataset.
25
  It achieves the following results on the evaluation set:
26
+ - Loss: 0.3646
27
+ - Precision: 0.5186
28
+ - Recall: 0.5971
29
+ - F1: 0.5551
30
+ - Accuracy: 0.9624
31
 
32
  ## Model description
33
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | No log | 1.0 | 168 | 0.1425 | 0.5245 | 0.4468 | 0.4825 | 0.9571 |
62
+ | No log | 2.0 | 336 | 0.1102 | 0.5249 | 0.5554 | 0.5397 | 0.9631 |
63
+ | 0.1287 | 3.0 | 504 | 0.1145 | 0.5512 | 0.6081 | 0.5783 | 0.9649 |
64
+ | 0.1287 | 4.0 | 672 | 0.1418 | 0.4819 | 0.6125 | 0.5394 | 0.9595 |
65
+ | 0.1287 | 5.0 | 840 | 0.1664 | 0.5335 | 0.5939 | 0.5621 | 0.9628 |
66
+ | 0.0284 | 6.0 | 1008 | 0.1978 | 0.5133 | 0.6158 | 0.5599 | 0.9621 |
67
+ | 0.0284 | 7.0 | 1176 | 0.2861 | 0.5439 | 0.5982 | 0.5698 | 0.9628 |
68
+ | 0.0284 | 8.0 | 1344 | 0.3077 | 0.5289 | 0.6125 | 0.5677 | 0.9631 |
69
+ | 0.0036 | 9.0 | 1512 | 0.3561 | 0.5151 | 0.6004 | 0.5545 | 0.9624 |
70
+ | 0.0036 | 10.0 | 1680 | 0.3646 | 0.5186 | 0.5971 | 0.5551 | 0.9624 |
71
 
72
 
73
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:614f3622d62bbafbc20ccd192efd6172f2859ba46988c11abdecbd2a5cde606e
3
  size 100761070
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60c059078f2d791a30f55eda4b7099fd4743b0cf9c653de11510f2940a04890
3
  size 100761070
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:540b7fbf60b80e8293593a86960df91d2263723d69107ffc1afc89a7c08cda12
3
- size 11422162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:796f3aee7dcab5a73f03f09cdd6020fd3ac201d1567b10c3608318df068d066f
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04af9b5cdc3ebeb288393b4fbd1a746ad8f1f9f7111cc74ca49272edf582cabb
3
  size 5905