Hugging Face's logo

ospanbatyr
/
idefics-9b-instruct-ft-instruct-compact

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
ospanbatyr commited on
Commit
8472c4a
•
1 Parent(s): d68fe99

End of training

Browse files
Files changed (3) hide show
  1. README.md +20 -5
  2. adapter_model.safetensors +1 -1
  3. runs/Nov17_01-46-49_ai12.kuacc.ku.edu.tr/events.out.tfevents.1700174809.ai12.kuacc.ku.edu.tr.192886.0 +2 -2
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/idefics-9b-instruct](https://huggingface.co/HuggingFaceM4/idefics-9b-instruct) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 2.9658
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.0001
38
  - train_batch_size: 4
39
  - eval_batch_size: 8
40
  - seed: 42
@@ -42,15 +42,30 @@ The following hyperparameters were used during training:
42
  - total_train_batch_size: 32
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 1
 
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 3.5797 | 0.36 | 5 | 3.3566 |
53
- | 3.0965 | 0.72 | 10 | 2.9658 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [HuggingFaceM4/idefics-9b-instruct](https://huggingface.co/HuggingFaceM4/idefics-9b-instruct) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: nan
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
  - train_batch_size: 4
39
  - eval_batch_size: 8
40
  - seed: 42
 
42
  - total_train_batch_size: 32
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 3
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 3.7449 | 0.18 | 25 | 3.3985 |
54
+ | 2.0448 | 0.36 | 50 | 1.6004 |
55
+ | 0.7728 | 0.54 | 75 | 0.5974 |
56
+ | 0.5519 | 0.73 | 100 | 0.5353 |
57
+ | 0.5128 | 0.91 | 125 | nan |
58
+ | 6.5038 | 1.09 | 150 | nan |
59
+ | 8.2169 | 1.27 | 175 | nan |
60
+ | 3.1474 | 1.45 | 200 | nan |
61
+ | 3.2837 | 1.63 | 225 | nan |
62
+ | 2.7581 | 1.81 | 250 | nan |
63
+ | 6.01 | 2.0 | 275 | nan |
64
+ | 5.9971 | 2.18 | 300 | nan |
65
+ | 6.5173 | 2.36 | 325 | nan |
66
+ | 10.7043 | 2.54 | 350 | nan |
67
+ | 2.5312 | 2.72 | 375 | nan |
68
+ | 3.013 | 2.9 | 400 | nan |
69
 
70
 
71
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9f25059ddaabdae687170e048f753b17674769a725948eb9ceece41b684ed48
3
  size 79071880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33fd677eff13ad226ef7814d6724936baea917c108fead970bc0a65a884a15a4
3
  size 79071880
runs/Nov17_01-46-49_ai12.kuacc.ku.edu.tr/events.out.tfevents.1700174809.ai12.kuacc.ku.edu.tr.192886.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09df9d87eaf6f8f7610b955061218c8005952d32b193ecd3fa63b59fb1ca4d7e
3
- size 15849
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3041ce07e55094faba6d39f0a07c2faa75d507b46a266c8242803bb1a98ccb9
3
+ size 16360