Hugging Face's logo

zera09
/
New_video_llava_qlora

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
zera09 commited on
Commit
ef7ae2b
•
1 Parent(s): 2b4e572

End of training

Browse files
Files changed (16) hide show
  1. README.md +3 -13
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Oct01_01-59-46_dgx01/events.out.tfevents.1727722788.dgx01.3958515.1 +3 -0
  5. runs/Oct01_02-39-35_dgx01/events.out.tfevents.1727725196.dgx01.4061283.0 +3 -0
  6. runs/Oct01_02-42-35_dgx01/events.out.tfevents.1727725357.dgx01.3958515.2 +3 -0
  7. runs/Oct01_10-09-00_dgx01/events.out.tfevents.1727752143.dgx01.4061283.1 +3 -0
  8. runs/Oct01_10-10-30_dgx01/events.out.tfevents.1727752233.dgx01.299292.0 +3 -0
  9. runs/Oct01_10-40-08_dgx01/events.out.tfevents.1727754011.dgx01.3958514.0 +3 -0
  10. runs/Oct01_10-57-19_dgx01/events.out.tfevents.1727755039.dgx01.3958515.3 +3 -0
  11. runs/Oct01_11-20-43_dgx01/events.out.tfevents.1727756449.dgx01.356807.0 +3 -0
  12. runs/Oct01_11-28-23_dgx01/events.out.tfevents.1727756906.dgx01.363232.0 +3 -0
  13. runs/Oct01_13-36-43_dgx01/events.out.tfevents.1727764618.dgx01.465362.0 +3 -0
  14. runs/Oct01_14-40-54_dgx01/events.out.tfevents.1727768456.dgx01.531424.0 +3 -0
  15. runs/Oct01_14-42-29_dgx01/events.out.tfevents.1727768551.dgx01.531423.0 +3 -0
  16. training_args.bin +1 -1
README.md CHANGED
@@ -14,8 +14,6 @@ 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
- It achieves the following results on the evaluation set:
18
- - Loss: 6.8629
19
 
20
  ## Model description
21
 
@@ -38,22 +36,14 @@ The following hyperparameters were used during training:
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: 2
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:------:|:----:|:---------------:|
51
- | 8.1798 | 0.2985 | 10 | 8.2246 |
52
- | 7.2412 | 0.5970 | 20 | 7.3507 |
53
- | 6.8157 | 0.8955 | 30 | 7.0556 |
54
- | 6.4395 | 1.1940 | 40 | 6.9667 |
55
- | 6.7558 | 1.4925 | 50 | 6.8976 |
56
- | 6.6077 | 1.7910 | 60 | 6.8629 |
57
 
58
 
59
  ### 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
 
18
  ## Model description
19
 
 
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
adapter_config.json CHANGED
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "gate_proj",
20
- "o_proj",
21
  "k_proj",
22
- "v_proj"
 
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "k_proj",
20
+ "o_proj",
21
+ "v_proj",
22
+ "gate_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d49c93f0396537a23e54cc0851dd451ff267476d399c6b9c2088e332791f249
3
  size 375459936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef16ff4d9b57a2106f74a551c4ce16a82ae867fbf3c67a8a2ce3609267a6fd4
3
  size 375459936
runs/Oct01_01-59-46_dgx01/events.out.tfevents.1727722788.dgx01.3958515.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ac79655bb7d4ea4c1081ce0ad3e44b360239ad915640cce3f127463158aab8
3
+ size 12716
runs/Oct01_02-39-35_dgx01/events.out.tfevents.1727725196.dgx01.4061283.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c49cd2f4671027625d7103ad16d85dd4114efeab179c138c984940dd081ed6a
3
+ size 10801
runs/Oct01_02-42-35_dgx01/events.out.tfevents.1727725357.dgx01.3958515.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53f19ddb000f98fb7af18e1cf86c0003fc3d507154b43915b33a3b18e090f4f
3
+ size 5781
runs/Oct01_10-09-00_dgx01/events.out.tfevents.1727752143.dgx01.4061283.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88de85c61d605ad6f37a418349ddd09390a63a694c8ecf5de0c3c6b2c92824ee
3
+ size 5780
runs/Oct01_10-10-30_dgx01/events.out.tfevents.1727752233.dgx01.299292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb9cba648b5705c4eac729cb8bf308a9c2a61541f76e93db0bb76966f629636
3
+ size 7370
runs/Oct01_10-40-08_dgx01/events.out.tfevents.1727754011.dgx01.3958514.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ca1a1a6939af49899d0f510a9d2930fe3316e2ea77b503b117905e6aac9917
3
+ size 7436
runs/Oct01_10-57-19_dgx01/events.out.tfevents.1727755039.dgx01.3958515.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8012e313c6c3c13f345e11e86ed713ebdde4232b7dd440d1f58b038c6e1f1dd
3
+ size 6194
runs/Oct01_11-20-43_dgx01/events.out.tfevents.1727756449.dgx01.356807.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98f3b37e90f75986c11757f8bce25c503fde43823e9225438cdce21c08511ce
3
+ size 5780
runs/Oct01_11-28-23_dgx01/events.out.tfevents.1727756906.dgx01.363232.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d874a40108836c4957f4d1fb0c191db613121465c66fd34d5265c661c7d890df
3
+ size 16300
runs/Oct01_13-36-43_dgx01/events.out.tfevents.1727764618.dgx01.465362.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0fdcc13a55b544f7ff120bc19d27641de9a4b61d6898fee93f5828bf018d5cf
3
+ size 14448
runs/Oct01_14-40-54_dgx01/events.out.tfevents.1727768456.dgx01.531424.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39f1ebf6d8c0f2c685670b39fb9fd56bad6a842cd7421f7bfb2e234864aa7ea
3
+ size 7784
runs/Oct01_14-42-29_dgx01/events.out.tfevents.1727768551.dgx01.531423.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75dc6770e900ad6ca336d35a5365e4b30a110d582849cb738fa692b607e6fe6
3
+ size 7229
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af7f9e277d8676ebfb790086f1d81372822e4135075c48a5161c906d5a4e8643
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c46b409c6fd72545dc3fd082e1c91c0640665a28484bded65634910f5b72168
3
  size 5176