Hugging Face's logo

framboiseb
/
paligemma_educacode

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
framboiseb commited on
Commit
f926cd2
·
verified ·
1 Parent(s): 963c91f

Model save

Browse files
Files changed (14) hide show
  1. README.md +59 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jun05_10-14-26_gpu-l4-ab/events.out.tfevents.1717582549.gpu-l4-ab.40677.0 +3 -0
  5. runs/Jun05_10-20-37_gpu-l4-ab/events.out.tfevents.1717582837.gpu-l4-ab.42008.0 +3 -0
  6. runs/Jun05_12-33-55_gpu-l4-ab/events.out.tfevents.1717590836.gpu-l4-ab.64311.0 +3 -0
  7. runs/Jun05_13-00-33_gpu-l4-ab/events.out.tfevents.1717592438.gpu-l4-ab.64311.1 +3 -0
  8. runs/Jun05_13-01-46_gpu-l4-ab/events.out.tfevents.1717592507.gpu-l4-ab.68303.0 +3 -0
  9. runs/Jun06_08-15-43_gpu-l4-ab/events.out.tfevents.1717661745.gpu-l4-ab.2926.0 +3 -0
  10. runs/Jun06_08-25-37_gpu-l4-ab/events.out.tfevents.1717662338.gpu-l4-ab.9591.0 +3 -0
  11. runs/Jun06_08-44-12_gpu-l4-ab/events.out.tfevents.1717663503.gpu-l4-ab +3 -0
  12. runs/Jun06_08-51-00_gpu-l4-ab/events.out.tfevents.1717663864.gpu-l4-ab +3 -0
  13. runs/Jun06_09-10-03_gpu-l4-ab/events.out.tfevents.1717665004.gpu-l4-ab +3 -0
  14. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: gemma
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: google/paligemma-3b-pt-224
7
+ datasets:
8
+ - imagefolder
9
+ model-index:
10
+ - name: paligemma_educacode
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # paligemma_educacode
18
+
19
+ This model is a fine-tuned version of [google/paligemma-3b-pt-224](https://huggingface.co/google/paligemma-3b-pt-224) on the imagefolder dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 8
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 2
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.11.1
56
+ - Transformers 4.41.2
57
+ - Pytorch 2.3.1+cu121
58
+ - Datasets 2.19.2
59
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/paligemma-3b-pt-224",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "k_proj",
25
+ "up_proj",
26
+ "down_proj",
27
+ "gate_proj",
28
+ "v_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d572a7c05146bab15b77c5da395cd976cb6ea0dfefa923dc5de40ecb63cffa
3
+ size 45258384
runs/Jun05_10-14-26_gpu-l4-ab/events.out.tfevents.1717582549.gpu-l4-ab.40677.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a22b5dfb8cfb8ef172dca6d91f91f02e72e130d21d2e259c01a8390f3480e3
3
+ size 5682
runs/Jun05_10-20-37_gpu-l4-ab/events.out.tfevents.1717582837.gpu-l4-ab.42008.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3123335d87886495b4cba570d518be5c0993446cdcf254bd721639e5ff90d6e
3
+ size 5682
runs/Jun05_12-33-55_gpu-l4-ab/events.out.tfevents.1717590836.gpu-l4-ab.64311.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e5119c42b97bfeb48afa352f41d435c7b683f500224002920c9b7e6ba62d2f
3
+ size 5682
runs/Jun05_13-00-33_gpu-l4-ab/events.out.tfevents.1717592438.gpu-l4-ab.64311.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5d873c3dfdf1cdac4da0edd6175d8eab647cfa7cdbfa39b1f242c5306f530c
3
+ size 5682
runs/Jun05_13-01-46_gpu-l4-ab/events.out.tfevents.1717592507.gpu-l4-ab.68303.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9e2e9b8693155b401b54329b058c590046d88bf455eed250602ed48bcfdf8b
3
+ size 5682
runs/Jun06_08-15-43_gpu-l4-ab/events.out.tfevents.1717661745.gpu-l4-ab.2926.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df72734355ef20c1f5f8044eb4925ff8d6950b259022830a9547f7c9384f422
3
+ size 5201
runs/Jun06_08-25-37_gpu-l4-ab/events.out.tfevents.1717662338.gpu-l4-ab.9591.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df052391704e84512c532db39f3c8cb8a762179d14796b49d901fe0bfc2f023
3
+ size 5201
runs/Jun06_08-44-12_gpu-l4-ab/events.out.tfevents.1717663503.gpu-l4-ab ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd793704556c5c6725406becdb7d823ae5e4d9ba10fed08d0785ab87275df00
3
+ size 5153
runs/Jun06_08-51-00_gpu-l4-ab/events.out.tfevents.1717663864.gpu-l4-ab ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20cec6967318be92575bc9ef09d710654b1679ea416fc0cd1c14c9f362de660
3
+ size 5634
runs/Jun06_09-10-03_gpu-l4-ab/events.out.tfevents.1717665004.gpu-l4-ab ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a7ec0f14ea8768bf16e4ad4e26f8172606c15a5414f033917e98f804c416ae
3
+ size 6592
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d31753c17d5e9fd02ddc407e6c898088705486b4e67b8c9d0fabb8c10708ba6
3
+ size 5112