Hugging Face's logo

zera09
/
New_video_llava_qlora

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
zera09 commited on
Commit
fae3b10
•
1 Parent(s): 0a747ce

End of training

Browse files
Files changed (8) hide show
  1. README.md +13 -17
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. runs/Oct01_17-51-34_dgx01/events.out.tfevents.1727779897.dgx01.690701.0 +2 -2
  5. runs/Oct01_17-51-34_dgx01/events.out.tfevents.1727788170.dgx01.690701.1 +3 -0
  6. runs/Oct01_17-52-36_dgx01/events.out.tfevents.1727779959.dgx01.690703.0 +2 -2
  7. runs/Oct01_20-32-33_dgx01/events.out.tfevents.1727789556.dgx01.690700.0 +3 -0
  8. training_args.bin +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 [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: 7.0486
19
 
20
  ## Model description
21
 
@@ -34,28 +34,24 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 2e-05
38
- - train_batch_size: 16
39
- - eval_batch_size: 8
40
  - seed: 42
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 10
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:----:|:---------------:|
49
- | 10.8987 | 1.0 | 12 | 10.7944 |
50
- | 10.5512 | 2.0 | 24 | 9.7724 |
51
- | 8.0719 | 3.0 | 36 | 8.8356 |
52
- | 7.9278 | 4.0 | 48 | 8.1534 |
53
- | 8.5148 | 5.0 | 60 | 7.6981 |
54
- | 7.752 | 6.0 | 72 | 7.4196 |
55
- | 6.9659 | 7.0 | 84 | 7.2470 |
56
- | 6.6744 | 8.0 | 96 | 7.1351 |
57
- | 6.4332 | 9.0 | 108 | 7.0703 |
58
- | 7.7343 | 10.0 | 120 | 7.0486 |
59
 
60
 
61
  ### Framework versions
 
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: 7.7978
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
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: 8
42
+ - total_train_batch_size: 16
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
+ | 9.6292 | 0.2266 | 10 | 9.4400 |
52
+ | 8.5995 | 0.4533 | 20 | 8.3454 |
53
+ | 8.3116 | 0.6799 | 30 | 7.9643 |
54
+ | 7.7798 | 0.9065 | 40 | 7.7978 |
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
adapter_config.json CHANGED
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
19
  "o_proj",
20
  "v_proj",
21
- "k_proj",
22
- "gate_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
+ "gate_proj",
20
  "o_proj",
21
  "v_proj",
22
+ "k_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:df5aa106dd2dfff7a7457a727fd2bb8be4379e0a281bd8445973348c46146807
3
  size 375459936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6db2a44c6d77a7904bfa4f87ffdd188d86afe55f41dca45a7d1f05b05b2212b
3
  size 375459936
runs/Oct01_17-51-34_dgx01/events.out.tfevents.1727779897.dgx01.690701.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:207fa3c20dc95e847b08b9908dbb4446f58274280326ae9f6644fd6d43193396
3
- size 8737
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eab7671db7847867b8d3297bba47e65150c91f10f244b6e2a9f49d2fe3fa16c
3
+ size 11835
runs/Oct01_17-51-34_dgx01/events.out.tfevents.1727788170.dgx01.690701.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4b61aab2fad8a1aa22994a9b8fd9ff908c35a0f394b96ddb5499f8ac63c57d
3
+ size 6194
runs/Oct01_17-52-36_dgx01/events.out.tfevents.1727779959.dgx01.690703.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87ab7d54862addbedd00f3b099e08e20aa0eb09e9bb41d34982b3bef9da31958
3
- size 8116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76abe8c06e909857a1a874e87bddc2450953d857e4791caaa40105b2bf9151da
3
+ size 16300
runs/Oct01_20-32-33_dgx01/events.out.tfevents.1727789556.dgx01.690700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201ba2d17ce0e37543409961e6dae30eefb015c2ec9b8aad67376010cc0bb6ec
3
+ size 5780
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16c0a20d2dbc701c7233602bc0b1af1b4c5b37aed007df07327d36007efcda79
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5888275934517f96fdcb4c9079c6ceb927e6aa31cf2567ab90c90f019b464b20
3
+ size 5176