Hugging Face's logo

muhtasham
/
MiniCPM-V-2_6_ft_20240908_220534_ft_upsampled_new

Safetensors
minicpmv
Generated from Trainer
custom_code
Model card Files Community
muhtasham commited on
Commit
4899476
•
1 Parent(s): 870226f

Model save

Browse files
Files changed (6) hide show
  1. README.md +9 -9
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. trainer_state.json +0 -0
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [muhtasham/MiniCPM-V-2_6_ft_20240908_220534](https://huggingface.co/muhtasham/MiniCPM-V-2_6_ft_20240908_220534) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.3034
18
 
19
  ## Model description
20
 
@@ -34,14 +34,14 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 5e-05
37
- - train_batch_size: 4
38
- - eval_batch_size: 4
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
  - num_devices: 4
42
  - gradient_accumulation_steps: 4
43
- - total_train_batch_size: 64
44
- - total_eval_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.1
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
- | 0.0349 | 0.7055 | 100 | 0.2220 |
57
- | 0.0435 | 1.4109 | 200 | 0.2660 |
58
- | 0.02 | 2.1164 | 300 | 0.2626 |
59
- | 0.0204 | 2.8219 | 400 | 0.3034 |
60
 
61
 
62
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [muhtasham/MiniCPM-V-2_6_ft_20240908_220534](https://huggingface.co/muhtasham/MiniCPM-V-2_6_ft_20240908_220534) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.3133
18
 
19
  ## Model description
20
 
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 5e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 2
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
  - num_devices: 4
42
  - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - total_eval_batch_size: 8
45
  - optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.1
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.0543 | 0.2430 | 100 | 0.2796 |
57
+ | 0.0791 | 0.4860 | 200 | 0.3113 |
58
+ | 0.0233 | 0.7290 | 300 | 0.3244 |
59
+ | 0.1447 | 0.9721 | 400 | 0.3133 |
60
 
61
 
62
  ### Framework versions
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b62cc1834141103927647e37fd30d2601718b8dd21b12208cbbfc641be651df
3
  size 4874808224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:227ab29e159ec03b2b15e94a6ce11e097a1e800e427002bc1a213e53ec3bb796
3
  size 4874808224
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54119fa2d5c0d502b814b18ab163045c5a667366db95117776f1b95eca179f2b
3
  size 4932751376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468ae1f6cb4e4562a6ff13397d85a008f808a41805e4a0a21e74dd0ef8c2cf52
3
  size 4932751376
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:987b65ab3c049e6f1f036e1fb65378c0f524b88f33a579969cd88fa848e92643
3
  size 4330865536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f1c10b09cf816769c51cdb04ffb0aa2359fdcd113b93df8e9ff19e8464eb2a7
3
  size 4330865536
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55e131f397a4fd9aaac4b4e4c7f13f251bba45a5b730597b76b7c2ed4c62115b
3
  size 2060016624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9b2e0b215eba08c8d51387a98624a13a2206e0d163eb80a852d99577caafed
3
  size 2060016624
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff