Hugging Face's logo

gimarchetti
/
gm-lora-bfloat16-idefics2-8b-xrayvqa-finetuned-mimic-short

Safetensors
Generated from Trainer
Model card Files Community
gimarchetti commited on
Commit
94680aa
•
1 Parent(s): 51c6544

End of training

Browse files
Files changed (3) hide show
  1. README.md +36 -9
  2. adapter_model.safetensors +1 -1
  3. 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 [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1519
19
 
20
  ## Model description
21
 
@@ -48,14 +48,41 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
- | 0.1674 | 0.4472 | 50 | 0.1424 |
52
- | 0.1437 | 0.8945 | 100 | 0.1422 |
53
- | 0.1396 | 1.3417 | 150 | 0.1446 |
54
- | 0.1403 | 1.7889 | 200 | 0.1428 |
55
- | 0.135 | 2.2361 | 250 | 0.1444 |
56
- | 0.1316 | 2.6834 | 300 | 0.1450 |
57
- | 0.1278 | 3.1306 | 350 | 0.1521 |
58
- | 0.1165 | 3.5778 | 400 | 0.1519 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.0730
19
 
20
  ## Model description
21
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
+ | 1.171 | 0.1119 | 50 | 1.2339 |
52
+ | 1.2051 | 0.2237 | 100 | 1.1744 |
53
+ | 1.1372 | 0.3356 | 150 | 1.1323 |
54
+ | 1.1046 | 0.4474 | 200 | 1.1095 |
55
+ | 1.0673 | 0.5593 | 250 | 1.0877 |
56
+ | 1.0713 | 0.6711 | 300 | 1.0761 |
57
+ | 1.0824 | 0.7830 | 350 | 1.0611 |
58
+ | 1.0358 | 0.8949 | 400 | 1.0511 |
59
+ | 1.0288 | 1.0067 | 450 | 1.0389 |
60
+ | 0.9158 | 1.1186 | 500 | 1.0443 |
61
+ | 0.9199 | 1.2304 | 550 | 1.0382 |
62
+ | 0.9032 | 1.3423 | 600 | 1.0339 |
63
+ | 0.8834 | 1.4541 | 650 | 1.0292 |
64
+ | 0.9048 | 1.5660 | 700 | 1.0271 |
65
+ | 0.9101 | 1.6779 | 750 | 1.0193 |
66
+ | 0.8928 | 1.7897 | 800 | 1.0164 |
67
+ | 0.9032 | 1.9016 | 850 | 1.0124 |
68
+ | 0.8649 | 2.0134 | 900 | 1.0234 |
69
+ | 0.7615 | 2.1253 | 950 | 1.0433 |
70
+ | 0.7588 | 2.2371 | 1000 | 1.0366 |
71
+ | 0.7759 | 2.3490 | 1050 | 1.0331 |
72
+ | 0.7696 | 2.4609 | 1100 | 1.0349 |
73
+ | 0.7587 | 2.5727 | 1150 | 1.0324 |
74
+ | 0.7532 | 2.6846 | 1200 | 1.0309 |
75
+ | 0.7702 | 2.7964 | 1250 | 1.0287 |
76
+ | 0.7648 | 2.9083 | 1300 | 1.0275 |
77
+ | 0.7452 | 3.0201 | 1350 | 1.0529 |
78
+ | 0.6471 | 3.1320 | 1400 | 1.0683 |
79
+ | 0.665 | 3.2438 | 1450 | 1.0727 |
80
+ | 0.6563 | 3.3557 | 1500 | 1.0713 |
81
+ | 0.6499 | 3.4676 | 1550 | 1.0721 |
82
+ | 0.6538 | 3.5794 | 1600 | 1.0741 |
83
+ | 0.6437 | 3.6913 | 1650 | 1.0740 |
84
+ | 0.6486 | 3.8031 | 1700 | 1.0734 |
85
+ | 0.66 | 3.9150 | 1750 | 1.0730 |
86
 
87
 
88
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4797aeaabbbeb8e142c6c9af8110d26c9d749582609b54b9f800085135b2379
3
  size 49840864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a63f88b2acc148c996eef08f46737a9d2ca8aa1f45e81959b9a18bef2f4875
3
  size 49840864
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c5654e1b8b90b658dd07b6b0f8e4c4101c4e4d1deb1e994e1745ec3e705fbc1
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3753b9e546393443fef3acda8f283af4324b924a54b9eb93f0c92eb840832683
3
  size 5240