Hugging Face's logo

zera09
/
New_video_llava_qlora

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
zera09 commited on
Commit
ce1bfa8
•
1 Parent(s): 9c5ef1b

End of training

Browse files
Files changed (12) hide show
  1. README.md +9 -2
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +1 -1
  4. runs/Oct01_22-16-02_dgx01/events.out.tfevents.1727795765.dgx01.909069.0 +2 -2
  5. runs/Oct02_00-37-32_dgx01/events.out.tfevents.1727804255.dgx01.1106375.0 +3 -0
  6. runs/Oct02_00-38-14_dgx01/events.out.tfevents.1727804296.dgx01.1099135.0 +3 -0
  7. runs/Oct02_11-20-37_dgx01/events.out.tfevents.1727842843.dgx01.1864498.0 +3 -0
  8. runs/Oct07_14-03-25_dgx01/events.out.tfevents.1728284611.dgx01.283732.0 +3 -0
  9. runs/Oct07_14-07-28_dgx01/events.out.tfevents.1728284871.dgx01.283742.0 +3 -0
  10. runs/Oct07_14-09-06_dgx01/events.out.tfevents.1728284948.dgx01.283742.1 +3 -0
  11. runs/Oct07_14-11-05_dgx01/events.out.tfevents.1728285066.dgx01.283742.2 +3 -0
  12. training_args.bin +1 -1
README.md CHANGED
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
  # New_video_llava_qlora
15
 
16
  This model is a fine-tuned version of [LanguageBind/Video-LLaVA-7B-hf](https://huggingface.co/LanguageBind/Video-LLaVA-7B-hf) on an unknown dataset.
 
 
17
 
18
  ## Model description
19
 
@@ -36,14 +38,19 @@ The following hyperparameters were used during training:
36
  - train_batch_size: 2
37
  - eval_batch_size: 2
38
  - seed: 42
39
- - gradient_accumulation_steps: 8
40
- - total_train_batch_size: 16
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - num_epochs: 1
44
 
45
  ### Training results
46
 
 
 
 
 
 
47
 
48
 
49
  ### Framework versions
 
14
  # New_video_llava_qlora
15
 
16
  This model is a fine-tuned version of [LanguageBind/Video-LLaVA-7B-hf](https://huggingface.co/LanguageBind/Video-LLaVA-7B-hf) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 7.2629
19
 
20
  ## Model description
21
 
 
38
  - train_batch_size: 2
39
  - eval_batch_size: 2
40
  - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 4
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - num_epochs: 1
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:----:|:---------------:|
51
+ | 8.2651 | 0.2985 | 10 | 8.3503 |
52
+ | 7.3708 | 0.5970 | 20 | 7.5340 |
53
+ | 6.9103 | 0.8955 | 30 | 7.2629 |
54
 
55
 
56
  ### Framework versions
adapter_config.json CHANGED
@@ -17,8 +17,8 @@
17
  "revision": null,
18
  "target_modules": [
19
  "gate_proj",
20
- "o_proj",
21
  "v_proj",
 
22
  "k_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
 
17
  "revision": null,
18
  "target_modules": [
19
  "gate_proj",
 
20
  "v_proj",
21
+ "o_proj",
22
  "k_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92659ed60acc94fc2a5aac00ad6e6b364bb3dde766a454b573ff491f2e39a436
3
  size 375459936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e7a5d76f05ffeaaa084f8021ec9b277c529dbb27db5c5ce87d4f8336019257
3
  size 375459936
runs/Oct01_22-16-02_dgx01/events.out.tfevents.1727795765.dgx01.909069.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b837e8dc43f6b51ba3534a84875cb69ee5c88ffc7a01c88f68adefade9d27c01
3
- size 7229
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7737b6a2fec175dea88f53c15226c1e2e77b0cd2151f737fb326d1fa43cd891f
3
+ size 11835
runs/Oct02_00-37-32_dgx01/events.out.tfevents.1727804255.dgx01.1106375.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a944329878d91ef71def7171845d88a473599463f47981deebc12dc96a339fc1
3
+ size 17808
runs/Oct02_00-38-14_dgx01/events.out.tfevents.1727804296.dgx01.1099135.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f99dfefdd687f20b408217b7354c4fd6f72275bc0a8bee721d1ed4dd1587aa
3
+ size 9144
runs/Oct02_11-20-37_dgx01/events.out.tfevents.1727842843.dgx01.1864498.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fdd991f87e5b1e9452a02eb68cbf6c032de8cb87f72d07ba29d9ddb2e055b93
3
+ size 17808
runs/Oct07_14-03-25_dgx01/events.out.tfevents.1728284611.dgx01.283732.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0239f900b0676aa6d275c359d0775d4aababc5f3385cd5aab0a12b8a376a77b8
3
+ size 13757
runs/Oct07_14-07-28_dgx01/events.out.tfevents.1728284871.dgx01.283742.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c3cf83cf1b5d2a2bcd37c199f86991c0f193dbf4ce888bb8433ed6c282b1ed
3
+ size 5780
runs/Oct07_14-09-06_dgx01/events.out.tfevents.1728284948.dgx01.283742.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33ee590a538056344d022c3efa60358f7592ed553843880bb6b806b483a6787
3
+ size 5780
runs/Oct07_14-11-05_dgx01/events.out.tfevents.1728285066.dgx01.283742.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6186f9266c98ff960ad6a1c72990d1c8f0c0abf886c87832b1518be0f5497a9d
3
+ size 11694
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6a0d8eef84b3112d6e4cc97aea7b38701499d9a9150110c21de59208520006
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea153a4f0d521ac146c9fac4ac6779a034e416bdb10918eb17b5331d5faf678
3
  size 5176