Hugging Face's logo

gimarchetti
/
gm-qlora-float16-idefics2-8b-indiana

Safetensors
Generated from Trainer
Model card Files Community
gimarchetti commited on
Commit
6bd1166
·
verified ·
1 Parent(s): 5e4b237

End of training

Browse files
Files changed (3) hide show
  1. README.md +15 -15
  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: 0.2975
19
 
20
  ## Model description
21
 
@@ -50,20 +50,20 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 1.3388 | 0.1408 | 41 | 0.6993 |
54
- | 0.6303 | 0.2817 | 82 | 0.5937 |
55
- | 0.5577 | 0.4225 | 123 | 0.5322 |
56
- | 0.5287 | 0.5634 | 164 | 0.4970 |
57
- | 0.4962 | 0.7042 | 205 | 0.4599 |
58
- | 0.462 | 0.8451 | 246 | 0.4367 |
59
- | 0.4438 | 0.9859 | 287 | 0.4100 |
60
- | 0.3361 | 1.1268 | 328 | 0.3967 |
61
- | 0.3208 | 1.2676 | 369 | 0.3803 |
62
- | 0.3175 | 1.4085 | 410 | 0.3542 |
63
- | 0.2973 | 1.5493 | 451 | 0.3422 |
64
- | 0.2842 | 1.6901 | 492 | 0.3215 |
65
- | 0.2717 | 1.8310 | 533 | 0.3068 |
66
- | 0.2644 | 1.9718 | 574 | 0.2975 |
67
 
68
 
69
  ### 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: 0.3401
19
 
20
  ## Model description
21
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.4248 | 0.1408 | 41 | 0.7825 |
54
+ | 0.7397 | 0.2817 | 82 | 0.6691 |
55
+ | 0.6407 | 0.4225 | 123 | 0.6101 |
56
+ | 0.606 | 0.5634 | 164 | 0.5650 |
57
+ | 0.575 | 0.7042 | 205 | 0.5273 |
58
+ | 0.5301 | 0.8451 | 246 | 0.4916 |
59
+ | 0.4834 | 0.9859 | 287 | 0.4677 |
60
+ | 0.3982 | 1.1268 | 328 | 0.4448 |
61
+ | 0.366 | 1.2676 | 369 | 0.4266 |
62
+ | 0.3493 | 1.4085 | 410 | 0.4068 |
63
+ | 0.3478 | 1.5493 | 451 | 0.3865 |
64
+ | 0.3173 | 1.6901 | 492 | 0.3681 |
65
+ | 0.3036 | 1.8310 | 533 | 0.3515 |
66
+ | 0.2917 | 1.9718 | 574 | 0.3401 |
67
 
68
 
69
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e770a876373c5a896b482b7afacdaa5995121a2cfd06e8f3cf1d9d44f763300e
3
  size 93378688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90327832fe32e7c1ce90461c4c54c368e6dcfe26ec242da23e6d7b7fc4450e3a
3
  size 93378688
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad0cdd1e5ec13d08f019e0f489b44341e8b958f88ba1bb182d90aa11958e669f
3
  size 4731
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bf03727b21efbaf5e93bfb4ff744bc519abe012ceeae5c03978291b0e14c4c
3
  size 4731