acchf commited on
Commit
d9cfc99
1 Parent(s): 7d059e9

End of training

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/paligemma-3b-mix-224
3
+ library_name: peft
4
+ license: gemma
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: paligemma-3b-adapter-dive-sa-vqa-224
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # paligemma-3b-adapter-dive-sa-vqa-224
16
+
17
+ This model is a fine-tuned version of [google/paligemma-3b-mix-224](https://huggingface.co/google/paligemma-3b-mix-224) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 32
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 2
46
+ - num_epochs: 1
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - PEFT 0.12.0
55
+ - Transformers 4.44.2
56
+ - Pytorch 2.4.1+cu121
57
+ - Datasets 3.0.0
58
+ - 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-mix-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
+ "o_proj",
25
+ "gate_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "v_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:ad43df636111716021b3ed678f52e0993d8a4e7d7bc159e06a9cdc1699443acb
3
+ size 45258384
runs/Sep12_14-07-18_0319-203921-80pwve7j-100-66-106-26/events.out.tfevents.1726150040.0319-203921-80pwve7j-100-66-106-26.3659.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15858af8bca4c33c8c3cfc6b195e2b822a1c96d9aea979ed77d9be26fb573b9
3
+ size 16245
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb7b965acb43bb2b649f99d8dba0df6689ae4fc52f06edee1bc3efdcff4a0fb
3
+ size 5240