Hugging Face's logo

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

Safetensors
Generated from Trainer
Model card Files Community
gimarchetti commited on
Commit
16bf758
•
1 Parent(s): 26c0502

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -12
  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: 0.6872
19
 
20
  ## Model description
21
 
@@ -35,11 +35,11 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0001
38
- - train_batch_size: 3
39
- - eval_batch_size: 3
40
  - seed: 42
41
  - gradient_accumulation_steps: 10
42
- - total_train_batch_size: 30
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 50
@@ -47,14 +47,18 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:------:|:----:|:---------------:|
52
- | 1.4399 | 0.2999 | 38 | 0.7745 |
53
- | 0.8072 | 0.5998 | 76 | 0.7329 |
54
- | 0.7577 | 0.8998 | 114 | 0.7067 |
55
- | 0.6603 | 1.1997 | 152 | 0.7081 |
56
- | 0.6099 | 1.4996 | 190 | 0.6960 |
57
- | 0.6045 | 1.7995 | 228 | 0.6872 |
 
 
 
 
58
 
59
 
60
  ### 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: 0.6749
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0001
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
  - seed: 42
41
  - gradient_accumulation_steps: 10
42
+ - total_train_batch_size: 20
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 50
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.4646 | 0.2 | 38 | 0.7746 |
53
+ | 0.7849 | 0.4 | 76 | 0.7351 |
54
+ | 0.797 | 0.6 | 114 | 0.7129 |
55
+ | 0.7429 | 0.8 | 152 | 0.6936 |
56
+ | 0.7361 | 1.0 | 190 | 0.6865 |
57
+ | 0.587 | 1.2 | 228 | 0.6933 |
58
+ | 0.5768 | 1.4 | 266 | 0.6863 |
59
+ | 0.5911 | 1.6 | 304 | 0.6815 |
60
+ | 0.5815 | 1.8 | 342 | 0.6772 |
61
+ | 0.5496 | 2.0 | 380 | 0.6749 |
62
 
63
 
64
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7da3396b30bb4afe2e4eb2206a34b4bebdde289c521757d8f98d916f74b527eb
3
  size 49840864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45b36bd20b00feeae9cfa69001f9104809aa611bd091d1448603777cc47c1a4
3
  size 49840864
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b65e69b9f16929f9153aeb81074223e10d976406a3610f8b175bcc5c85163483
3
  size 4731
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee54f2acc5ff802a0ddade6b36a8507991c35cf7d8e84c4ba1676f4a763b72a2
3
  size 4731