allknowingroger commited on
Commit
21eb202
1 Parent(s): b47e3e4

End of training

Browse files
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 16
42
+ - optimizer: Use 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: 50
45
+ - num_epochs: 1
46
+
47
+ ### Framework versions
48
+
49
+ - PEFT 0.13.2
50
+ - Transformers 4.46.2
51
+ - Pytorch 2.5.1+cu121
52
+ - Datasets 3.1.0
53
+ - Tokenizers 0.20.3
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": "gaussian",
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 8,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "up_proj",
27
+ "gate_proj",
28
+ "k_proj",
29
+ "o_proj",
30
+ "q_proj",
31
+ "v_proj",
32
+ "down_proj"
33
+ ],
34
+ "task_type": null,
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f82cd68064ba6ec98f54e808cddbf4a69005671f22901c76368fe0f190a7d4
3
+ size 42220792
runs/Dec02_15-52-21_c28afaa25e22/events.out.tfevents.1733154750.c28afaa25e22.261.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6baee89f4ae1122e073ab2fb893efb29c0a27f44a5d38ad48594ff2e9b1491
3
+ size 8280
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419327e3e1ad01079b893b7f1f831d8589c8d31bddda86247781cac7f5802610
3
+ size 5304