Hugging Face's logo

merve
/
idefics3-llama-vqav2

Transformers
TensorBoard
Safetensors
Model card Files
xet
Metrics Community
merve HF Staff commited on
Commit
6062d83
·
verified ·
1 Parent(s): d0b6c00

End of training

Browse files
Files changed (15) hide show
  1. README.md +57 -0
  2. adapter_config.json +37 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Sep10_16-28-47_hf-dgx-01/events.out.tfevents.1725978528.hf-dgx-01.4020671.0 +3 -0
  5. runs/Sep10_17-04-18_hf-dgx-01/events.out.tfevents.1725980659.hf-dgx-01.1002733.0 +3 -0
  6. runs/Sep10_17-08-34_hf-dgx-01/events.out.tfevents.1725980915.hf-dgx-01.2608083.0 +3 -0
  7. runs/Sep10_17-15-44_hf-dgx-01/events.out.tfevents.1725981346.hf-dgx-01.3941701.0 +3 -0
  8. runs/Sep10_17-20-12_hf-dgx-01/events.out.tfevents.1725981613.hf-dgx-01.969722.0 +3 -0
  9. runs/Sep10_17-22-25_hf-dgx-01/events.out.tfevents.1725981746.hf-dgx-01.3933237.0 +3 -0
  10. runs/Sep10_17-24-47_hf-dgx-01/events.out.tfevents.1725981890.hf-dgx-01.2953170.0 +3 -0
  11. runs/Sep10_17-26-09_hf-dgx-01/events.out.tfevents.1725981971.hf-dgx-01.704174.0 +3 -0
  12. runs/Sep10_17-47-39_hf-dgx-01/events.out.tfevents.1725983260.hf-dgx-01.2708259.0 +3 -0
  13. runs/Sep10_17-51-41_hf-dgx-01/events.out.tfevents.1725983503.hf-dgx-01.3227324.0 +3 -0
  14. runs/Sep10_17-58-37_hf-dgx-01/events.out.tfevents.1725983919.hf-dgx-01.876273.0 +3 -0
  15. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceM4/Idefics3-8B-Llama3
3
+ library_name: peft
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: idefics3-llama-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
+ # idefics3-llama-vqav2
16
+
17
+ This model is a fine-tuned version of [HuggingFaceM4/Idefics3-8B-Llama3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) 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: 8
41
+ - total_train_batch_size: 32
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 50
45
+ - num_epochs: 1
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.12.0
54
+ - Transformers 4.45.0.dev0
55
+ - Pytorch 2.3.1+cu121
56
+ - Datasets 2.19.1
57
+ - Tokenizers 0.19.1
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": "HuggingFaceM4/Idefics3-8B-Llama3",
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
+ "o_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "q_proj",
30
+ "k_proj",
31
+ "down_proj",
32
+ "v_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:e16d5fdbe8b4fb10a93ecdc622b3abb3643b15104e8dd8f846a2d6287fa033a4
3
+ size 89947240
runs/Sep10_16-28-47_hf-dgx-01/events.out.tfevents.1725978528.hf-dgx-01.4020671.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fefab01d605158e9df9bd8777432f5e04451e47a31d6ae82b60af67e63c6075f
3
+ size 13091
runs/Sep10_17-04-18_hf-dgx-01/events.out.tfevents.1725980659.hf-dgx-01.1002733.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad967f83a1d80803d04854c2f6a9c43ec1ecf8348c7681b444056c8a6133f27b
3
+ size 12056
runs/Sep10_17-08-34_hf-dgx-01/events.out.tfevents.1725980915.hf-dgx-01.2608083.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b020f749fff01c2481141979e6ac89ef3b1da1011869f492defef55caeb705a
3
+ size 12057
runs/Sep10_17-15-44_hf-dgx-01/events.out.tfevents.1725981346.hf-dgx-01.3941701.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ef546edf71460050597356d590358303ab0d7927e5f506b5160543ec897398
3
+ size 12056
runs/Sep10_17-20-12_hf-dgx-01/events.out.tfevents.1725981613.hf-dgx-01.969722.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89f0258243dcb7924845c27a6c870791a39466cf4cabeb0a5912403d6560a64
3
+ size 12048
runs/Sep10_17-22-25_hf-dgx-01/events.out.tfevents.1725981746.hf-dgx-01.3933237.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f68b824e075d1b1d9eb0a68673564aec8397ac77ef6649db14ada5bf9d94e38
3
+ size 12048
runs/Sep10_17-24-47_hf-dgx-01/events.out.tfevents.1725981890.hf-dgx-01.2953170.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0249a9da77394c81af898d5ad0e7102bb02af60d2aac96e682277bc96b8455a4
3
+ size 12048
runs/Sep10_17-26-09_hf-dgx-01/events.out.tfevents.1725981971.hf-dgx-01.704174.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63573e8afdbc7b60cbd91db1b92f76937e26a19a7e5ecc172b8b506070f09277
3
+ size 12048
runs/Sep10_17-47-39_hf-dgx-01/events.out.tfevents.1725983260.hf-dgx-01.2708259.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0db814ce1118792085171ebb0e502bc6680e978b023f40144ee13501f6f35e
3
+ size 12048
runs/Sep10_17-51-41_hf-dgx-01/events.out.tfevents.1725983503.hf-dgx-01.3227324.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47f238bd413cff0ad2796eb3ac2782daf5873f1a9db4fa34df6c65cee7722933
3
+ size 12048
runs/Sep10_17-58-37_hf-dgx-01/events.out.tfevents.1725983919.hf-dgx-01.876273.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba8a2d82c50feeaf93ea3d59f109b0b66183986fb03658c7868327505e8aaf1
3
+ size 13437
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca5c348e5828cab2992d93668b0c4427c061ad53aec36abeae1484fae94da28
3
+ size 5176