Hugging Face's logo

Raj-hf
/
paligemma_vqav2

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Raj-hf commited on
Commit
e853a2d
·
verified ·
1 Parent(s): a903b90

Raj-hf/paligemma_radioVQAv2

Browse files
Files changed (16) hide show
  1. README.md +4 -4
  2. adapter_config.json +6 -6
  3. adapter_model.safetensors +2 -2
  4. runs/Jan03_06-58-22_d054c89bc9c0/events.out.tfevents.1735887508.d054c89bc9c0.396.0 +3 -0
  5. runs/Jan03_06-58-59_d054c89bc9c0/events.out.tfevents.1735887541.d054c89bc9c0.396.1 +3 -0
  6. runs/Jan03_07-10-46_d054c89bc9c0/events.out.tfevents.1735888248.d054c89bc9c0.396.2 +3 -0
  7. runs/Jan03_07-11-07_d054c89bc9c0/events.out.tfevents.1735888269.d054c89bc9c0.396.3 +3 -0
  8. runs/Jan03_07-12-51_d054c89bc9c0/events.out.tfevents.1735888375.d054c89bc9c0.396.4 +3 -0
  9. runs/Jan03_07-15-05_d054c89bc9c0/events.out.tfevents.1735888507.d054c89bc9c0.396.5 +3 -0
  10. runs/Jan03_07-27-54_d054c89bc9c0/events.out.tfevents.1735889278.d054c89bc9c0.551.0 +3 -0
  11. runs/Jan03_07-36-59_d054c89bc9c0/events.out.tfevents.1735889823.d054c89bc9c0.551.1 +3 -0
  12. runs/Jan03_07-38-44_d054c89bc9c0/events.out.tfevents.1735889928.d054c89bc9c0.551.2 +3 -0
  13. runs/Jan03_08-13-30_d054c89bc9c0/events.out.tfevents.1735892012.d054c89bc9c0.551.3 +3 -0
  14. runs/Jan03_08-15-14_d054c89bc9c0/events.out.tfevents.1735892116.d054c89bc9c0.551.4 +3 -0
  15. runs/Jan03_08-25-46_d054c89bc9c0/events.out.tfevents.1735892750.d054c89bc9c0.551.5 +3 -0
  16. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: peft
3
  license: gemma
4
- base_model: google/paligemma2-3b-pt-224
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # paligemma_vqav2
16
 
17
- This model is a fine-tuned version of [google/paligemma2-3b-pt-224](https://huggingface.co/google/paligemma2-3b-pt-224) on an unknown dataset.
18
 
19
  ## Model description
20
 
@@ -37,8 +37,8 @@ The following hyperparameters were used during training:
37
  - train_batch_size: 1
38
  - eval_batch_size: 8
39
  - seed: 42
40
- - gradient_accumulation_steps: 2
41
- - total_train_batch_size: 2
42
  - optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 2
 
1
  ---
2
  library_name: peft
3
  license: gemma
4
+ base_model: google/paligemma-3b-pt-224
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # paligemma_vqav2
16
 
17
+ This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on an unknown dataset.
18
 
19
  ## Model description
20
 
 
37
  - train_batch_size: 1
38
  - eval_batch_size: 8
39
  - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 4
42
  - optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 2
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "google/paligemma2-3b-pt-224",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "k_proj",
 
 
27
  "up_proj",
 
28
  "down_proj",
29
- "o_proj",
30
- "q_proj",
31
- "gate_proj",
32
- "v_proj"
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "google/paligemma-3b-pt-224",
5
  "bias": "none",
6
  "eva_config": null,
7
  "exclude_modules": null,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "gate_proj",
27
+ "q_proj",
28
+ "o_proj",
29
  "up_proj",
30
+ "v_proj",
31
  "down_proj",
32
+ "k_proj"
 
 
 
33
  ],
34
  "task_type": "CAUSAL_LM",
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fa48faf6ad0c168dbf62c18c9bd1ceb767e9f8a019f89b1305596b61baf249d
3
- size 47584968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a65b2e5a0228767735f44131564224416d6f8832dcf1a3a9eace0df71224677
3
+ size 45258384
runs/Jan03_06-58-22_d054c89bc9c0/events.out.tfevents.1735887508.d054c89bc9c0.396.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5086655b03cb243c34dd896438c9462a2e4e3c2505b113f33ab7014d00e15d
3
+ size 6238
runs/Jan03_06-58-59_d054c89bc9c0/events.out.tfevents.1735887541.d054c89bc9c0.396.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b24b2faba4295243f00770114b3a37e48619cfb5f5b597a716cd40be97f58f
3
+ size 6251
runs/Jan03_07-10-46_d054c89bc9c0/events.out.tfevents.1735888248.d054c89bc9c0.396.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c928aecaa28242258b744e0dda7125f16ec013e920746c171836fce07a03fbbb
3
+ size 6238
runs/Jan03_07-11-07_d054c89bc9c0/events.out.tfevents.1735888269.d054c89bc9c0.396.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f1149e787b85a37c08101916c4054f9fe2a62ccb078dd4338b7b68350f80be5
3
+ size 6251
runs/Jan03_07-12-51_d054c89bc9c0/events.out.tfevents.1735888375.d054c89bc9c0.396.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c2e8d88cce86f4fbbf022425be0df1d337f767d08d8d7c180a6754d74cc60d
3
+ size 6251
runs/Jan03_07-15-05_d054c89bc9c0/events.out.tfevents.1735888507.d054c89bc9c0.396.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9977f30eddabb8cf337414e5913ce01e20e50848279b7109902bdfb7560e101f
3
+ size 6246
runs/Jan03_07-27-54_d054c89bc9c0/events.out.tfevents.1735889278.d054c89bc9c0.551.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867221f0485a2b4f13b2e074f255f0c2d1510f0bb7e5346940e4bdc126bf8324
3
+ size 6238
runs/Jan03_07-36-59_d054c89bc9c0/events.out.tfevents.1735889823.d054c89bc9c0.551.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f76973728fe9a72049690d77c4ef50311b0ceb6309b49c49be77149e2f2913b
3
+ size 6067
runs/Jan03_07-38-44_d054c89bc9c0/events.out.tfevents.1735889928.d054c89bc9c0.551.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311f4a2b6336a5d5aa6e29ee782ce113189eb3adfc6810a38bf51343ff7d4174
3
+ size 10454
runs/Jan03_08-13-30_d054c89bc9c0/events.out.tfevents.1735892012.d054c89bc9c0.551.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c5a42f934a597d76c973c84a54f195b2b5153227e6295884ddb310ead082a3
3
+ size 6067
runs/Jan03_08-15-14_d054c89bc9c0/events.out.tfevents.1735892116.d054c89bc9c0.551.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261db1bfa5a69017aed58476799bd64e254d9355f0c7aebe8c7f3e138ef5c914
3
+ size 6274
runs/Jan03_08-25-46_d054c89bc9c0/events.out.tfevents.1735892750.d054c89bc9c0.551.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3ee4dfa29a057c4fa0deddae02d247f519b1b8e53c3fb99a546fb7849a0a0b
3
+ size 37816
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8df6a747de9c1df033c5429c8129a22d6fe904f7000d07c2b53e46f48c1e4298
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c731402fb9879b221c2fddbb0f28a39c6188a783ba6651f3777b8be011d6ef35
3
  size 5304