allko14 commited on
Commit
ecd536b
·
verified ·
1 Parent(s): 6179ac7

End of training

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: HuggingFaceTB/SmolVLM-Base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: SmolVLM-Base-vqav2
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
+ # SmolVLM-Base-vqav2
16
+
17
+ This model is a fine-tuned version of [HuggingFaceTB/SmolVLM-Base](https://huggingface.co/HuggingFaceTB/SmolVLM-Base) 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: 0.0001
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 2
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 16
42
+ - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 20
45
+ - num_epochs: 1
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.14.0
54
+ - Transformers 4.48.3
55
+ - Pytorch 2.5.1+cu124
56
+ - Datasets 3.3.2
57
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Idefics3ForConditionalGeneration",
5
+ "parent_library": "transformers.models.idefics3.modeling_idefics3"
6
+ },
7
+ "base_model_name_or_path": "HuggingFaceTB/SmolVLM-Base",
8
+ "bias": "none",
9
+ "eva_config": null,
10
+ "exclude_modules": null,
11
+ "fan_in_fan_out": false,
12
+ "inference_mode": true,
13
+ "init_lora_weights": "gaussian",
14
+ "layer_replication": null,
15
+ "layers_pattern": null,
16
+ "layers_to_transform": null,
17
+ "loftq_config": {},
18
+ "lora_alpha": 8,
19
+ "lora_bias": false,
20
+ "lora_dropout": 0.1,
21
+ "megatron_config": null,
22
+ "megatron_core": "megatron.core",
23
+ "modules_to_save": null,
24
+ "peft_type": "LORA",
25
+ "r": 8,
26
+ "rank_pattern": {},
27
+ "revision": null,
28
+ "target_modules": [
29
+ "down_proj",
30
+ "up_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "v_proj",
34
+ "o_proj",
35
+ "q_proj"
36
+ ],
37
+ "task_type": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854285733ea0d73183f9af00732e614f79b5c120b478208ff8ccc4e7f6fcccc3
3
+ size 42220792
runs/Mar14_07-48-14_93496116b781/events.out.tfevents.1741938500.93496116b781.308.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98ce6a2b6b301c1e93059e98202625ff6578af5f3774377baa2d9c643fa16e46
3
+ size 8470
runs/Mar14_07-51-35_93496116b781/events.out.tfevents.1741938697.93496116b781.308.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252690875f40bcec61e6f8839097293b4f2492b9eb38def3a30d619d97e8e628
3
+ size 8470
runs/Mar14_07-57-28_93496116b781/events.out.tfevents.1741939050.93496116b781.308.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98786e70edc163d50b573bc95e4ab4a66d2985b3e3802f6c962fafafa2116c40
3
+ size 8470
runs/Mar14_08-08-09_93496116b781/events.out.tfevents.1741939689.93496116b781.308.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cfb65264d8060e680fa8780840c49125b829e5e1a1234f99e36e5ba544ef8b7
3
+ size 8470
runs/Mar14_08-15-38_93496116b781/events.out.tfevents.1741940138.93496116b781.308.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb4fefe11bef1c0e19ad0c718826d73eadff38042309a98b45a8bf4e8af38e7
3
+ size 8470
runs/Mar14_08-24-36_93496116b781/events.out.tfevents.1741940677.93496116b781.15191.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85eef32461c6438065f1692b1e5c868d88a4a16cde3514aadae04a11dff7acd8
3
+ size 8471
runs/Mar14_08-25-58_93496116b781/events.out.tfevents.1741940758.93496116b781.15191.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f1640f6263825074dee95f6c614b9038f3beed506ba59d8df09aa47522d01f
3
+ size 8471
runs/Mar14_08-29-04_93496116b781/events.out.tfevents.1741940945.93496116b781.15191.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1aa08527d14445def5c26431666fb177abec097314ba94d86236bd169f540b
3
+ size 10492
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d6d0e58af93c9d894726465022f8acb71f93bc88e57d787103ee0c9562bc74
3
+ size 5368