Hugging Face's logo

SaiChamakura
/
finetuned_model

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
SaiChamakura commited on
Commit
e97df6a
·
verified ·
1 Parent(s): 9617edf

End of training

Browse files
Files changed (11) hide show
  1. README.md +57 -0
  2. adapter_config.json +40 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Feb25_11-18-10_aicse/events.out.tfevents.1740462491.aicse.42671.0 +3 -0
  5. runs/Feb25_11-19-55_aicse/events.out.tfevents.1740462596.aicse.73813.0 +3 -0
  6. runs/Feb25_11-20-50_aicse/events.out.tfevents.1740462651.aicse.93811.0 +3 -0
  7. runs/Feb25_11-21-54_aicse/events.out.tfevents.1740462714.aicse.110143.0 +3 -0
  8. runs/Feb25_11-24-44_aicse/events.out.tfevents.1740462884.aicse.160897.0 +3 -0
  9. runs/Feb25_11-27-18_aicse/events.out.tfevents.1740463039.aicse.207935.0 +3 -0
  10. runs/Feb25_11-43-03_aicse/events.out.tfevents.1740463983.aicse.487846.0 +3 -0
  11. training_args.bin +3 -0
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: finetuned_model
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
+ # finetuned_model
16
+
17
+ This model is a fine-tuned version of [HuggingFaceTB/SmolVLM-Base](https://huggingface.co/HuggingFaceTB/SmolVLM-Base) on the None 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: 3
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.14.0
54
+ - Transformers 4.47.1
55
+ - Pytorch 2.5.1+cu121
56
+ - Datasets 3.2.0
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
+ "k_proj",
30
+ "up_proj",
31
+ "down_proj",
32
+ "q_proj",
33
+ "o_proj",
34
+ "gate_proj",
35
+ "v_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 sha256:183a2f01dcde3a857d7b75a6d5f96f97186263bfbb7a91f4022440d2df178756
3
+ size 42220792
runs/Feb25_11-18-10_aicse/events.out.tfevents.1740462491.aicse.42671.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8816f75785d02bb64f43ad554555b680e9920d8c9aa1a1721ece9c7d719c7f12
3
+ size 8445
runs/Feb25_11-19-55_aicse/events.out.tfevents.1740462596.aicse.73813.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbd4e8ce319e3c2e96697b81dba6abc48908a63e125b96441838a84c2da337b
3
+ size 8445
runs/Feb25_11-20-50_aicse/events.out.tfevents.1740462651.aicse.93811.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84cf156256d08d1bef56f975048abc052f7236e2731962c2a611d3093fa8db1a
3
+ size 8445
runs/Feb25_11-21-54_aicse/events.out.tfevents.1740462714.aicse.110143.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2830791ede2855f49377e78c58733267ce8996bf42c5a1d757e6fe0f7dcbb6ff
3
+ size 8445
runs/Feb25_11-24-44_aicse/events.out.tfevents.1740462884.aicse.160897.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2344b8f366ea78779c25e4a3e1046c906ff864b8ee4e7e8224067cd8f60ef893
3
+ size 8445
runs/Feb25_11-27-18_aicse/events.out.tfevents.1740463039.aicse.207935.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20fd59d9b7108745d82143a5864f983886b15fc7be32c17964e79f570be767bb
3
+ size 9207
runs/Feb25_11-43-03_aicse/events.out.tfevents.1740463983.aicse.487846.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afce31f5a2850b2e161af74fa4be931bafd3830adba2c0f3fa477ab52b3396a6
3
+ size 9170
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd2462c717273d22e4d4a2a4404839f94d8fc018f59720a52eaa729a1f279f6
3
+ size 5304