Hugging Face's logo

justinkarlin
/
idefics3-qlora-faces4

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
justinkarlin commited on
Commit
78a4cdc
·
verified ·
1 Parent(s): a895aaf

End of training

Browse files
Files changed (12) hide show
  1. README.md +59 -0
  2. adapter_config.json +34 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Oct31_20-13-48_2b7adc8130d4/events.out.tfevents.1730405634.2b7adc8130d4.647.0 +3 -0
  5. runs/Oct31_20-17-00_2b7adc8130d4/events.out.tfevents.1730405827.2b7adc8130d4.647.1 +3 -0
  6. runs/Oct31_20-17-53_2b7adc8130d4/events.out.tfevents.1730405878.2b7adc8130d4.647.2 +3 -0
  7. runs/Oct31_20-19-14_2b7adc8130d4/events.out.tfevents.1730405960.2b7adc8130d4.647.3 +3 -0
  8. runs/Oct31_20-23-52_2b7adc8130d4/events.out.tfevents.1730406237.2b7adc8130d4.647.4 +3 -0
  9. runs/Oct31_20-29-35_2b7adc8130d4/events.out.tfevents.1730406581.2b7adc8130d4.647.5 +3 -0
  10. runs/Oct31_20-35-22_2b7adc8130d4/events.out.tfevents.1730406930.2b7adc8130d4.48372.0 +3 -0
  11. runs/Oct31_20-37-00_2b7adc8130d4/events.out.tfevents.1730407026.2b7adc8130d4.48372.1 +3 -0
  12. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceM4/Idefics3-8B-Llama3
3
+ datasets:
4
+ - imagefolder
5
+ library_name: peft
6
+ license: apache-2.0
7
+ tags:
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: idefics3-qlora-faces4
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
+ # idefics3-qlora-faces4
18
+
19
+ This model is a fine-tuned version of [HuggingFaceM4/Idefics3-8B-Llama3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) 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: 0.0001
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 50
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.13.2
56
+ - Transformers 4.45.0.dev0
57
+ - Pytorch 2.5.0+cu121
58
+ - Datasets 3.1.0
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": "HuggingFaceM4/Idefics3-8B-Llama3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": "gaussian",
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 8,
14
+ "lora_dropout": 0.1,
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
+ "up_proj",
24
+ "gate_proj",
25
+ "down_proj",
26
+ "o_proj",
27
+ "k_proj",
28
+ "v_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "FEATURE_EXTRACTION",
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 sha256:2f6f32bc61615b49a4e49afcd8b720e17ba14aae6c747afc3c7876c7af720a35
3
+ size 89947240
runs/Oct31_20-13-48_2b7adc8130d4/events.out.tfevents.1730405634.2b7adc8130d4.647.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d493d3238ba0447a9a3d0b85d36e1a6e41e76dd452d75f576f79e4f9bd61ebb
3
+ size 11597
runs/Oct31_20-17-00_2b7adc8130d4/events.out.tfevents.1730405827.2b7adc8130d4.647.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e02edcd6c012817ec5ea49655e5727de4ae3ca0bde0c493c0e1bee5cec7831e
3
+ size 11593
runs/Oct31_20-17-53_2b7adc8130d4/events.out.tfevents.1730405878.2b7adc8130d4.647.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266f1faf057b22fdff167370ad30fc45070c192352c0b16dffc007798b1dc376
3
+ size 23098
runs/Oct31_20-19-14_2b7adc8130d4/events.out.tfevents.1730405960.2b7adc8130d4.647.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41bcccac079b235bc44bb9b43e7ffeabde7a32c19953e8ad1f27c26e22880682
3
+ size 11592
runs/Oct31_20-23-52_2b7adc8130d4/events.out.tfevents.1730406237.2b7adc8130d4.647.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13c25130d6ae3dd314ea123819ab695558083d5409b33b738e8f2e84f99250a
3
+ size 23096
runs/Oct31_20-29-35_2b7adc8130d4/events.out.tfevents.1730406581.2b7adc8130d4.647.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfdd1f1ca6bb8721e1522090019d5aeba4cabe8c880d81414c39b841a7c60f32
3
+ size 11599
runs/Oct31_20-35-22_2b7adc8130d4/events.out.tfevents.1730406930.2b7adc8130d4.48372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6113de556eaf45c8f0b1bd1712829dc9034200c18cfdb2dd4d155dd59426883d
3
+ size 12079
runs/Oct31_20-37-00_2b7adc8130d4/events.out.tfevents.1730407026.2b7adc8130d4.48372.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86fcd3b909e410b4675233cdc1acae73b9320d95e2c935d563db5860d311134
3
+ size 12426
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3d27f14b314fadeb3ea82f01372cb8c57a3d98d5f6de39d3ea31c4a7b7fa51
3
+ size 5304