Hugging Face's logo

mgertner
/
lora

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
mgertner commited on
Commit
3c373a9
·
verified ·
1 Parent(s): 1dd0a8b

Model save

Browse files
Files changed (15) hide show
  1. README.md +57 -0
  2. adapter_config.json +42 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Apr30_12-57-53_97416270aea6/events.out.tfevents.1746017887.97416270aea6.1945.0 +3 -0
  5. runs/Apr30_13-15-17_97416270aea6/events.out.tfevents.1746018938.97416270aea6.6793.0 +3 -0
  6. runs/Apr30_13-24-41_97416270aea6/events.out.tfevents.1746019495.97416270aea6.10415.0 +3 -0
  7. runs/Apr30_13-27-25_97416270aea6/events.out.tfevents.1746019648.97416270aea6.11532.0 +3 -0
  8. runs/Apr30_13-28-53_97416270aea6/events.out.tfevents.1746019741.97416270aea6.11532.1 +3 -0
  9. runs/Apr30_13-31-13_97416270aea6/events.out.tfevents.1746019882.97416270aea6.11532.2 +3 -0
  10. runs/Apr30_13-33-12_97416270aea6/events.out.tfevents.1746019998.97416270aea6.11532.3 +3 -0
  11. runs/Apr30_13-36-35_97416270aea6/events.out.tfevents.1746020199.97416270aea6.11532.4 +3 -0
  12. runs/Apr30_15-09-06_97416270aea6/events.out.tfevents.1746025761.97416270aea6.11532.5 +3 -0
  13. runs/Apr30_15-09-25_97416270aea6/events.out.tfevents.1746025770.97416270aea6.11532.6 +3 -0
  14. runs/Apr30_15-11-40_97416270aea6/events.out.tfevents.1746025903.97416270aea6.37954.0 +3 -0
  15. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.2
4
+ base_model: meta-llama/Llama-3.2-11B-Vision
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: lora
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
+ # lora
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision) 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: 2e-05
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - gradient_accumulation_steps: 4
41
+ - total_train_batch_size: 4
42
+ - optimizer: Use OptimizerNames.ADAMW_TORCH 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: 2
45
+ - num_epochs: 2
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.15.2
54
+ - Transformers 4.51.3
55
+ - Pytorch 2.6.0+cu124
56
+ - Datasets 3.5.1
57
+ - Tokenizers 0.21.1
adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "MllamaForConditionalGeneration",
5
+ "parent_library": "transformers.models.mllama.modeling_mllama"
6
+ },
7
+ "base_model_name_or_path": "meta-llama/Llama-3.2-11B-Vision",
8
+ "bias": "none",
9
+ "corda_config": null,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": "gaussian",
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 8,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "r": 8,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "o_proj",
31
+ "v_proj",
32
+ "k_proj",
33
+ "q_proj",
34
+ "up_proj",
35
+ "gate_proj",
36
+ "down_proj"
37
+ ],
38
+ "task_type": null,
39
+ "trainable_token_indices": null,
40
+ "use_dora": true,
41
+ "use_rslora": false
42
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce37e782e6f8a33aa64fe5598887789a31b3613ee7e5364266b2c1aeb03d99ed
3
+ size 125866776
runs/Apr30_12-57-53_97416270aea6/events.out.tfevents.1746017887.97416270aea6.1945.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf4582185d61797eaddffaf9a76921a78088cdfd94b3c01802216c14979986f
3
+ size 6127
runs/Apr30_13-15-17_97416270aea6/events.out.tfevents.1746018938.97416270aea6.6793.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec43d06ae4cc7b860874bff9b1ec8ac3448f19d8a96cc18899e5288a06b7e45c
3
+ size 6127
runs/Apr30_13-24-41_97416270aea6/events.out.tfevents.1746019495.97416270aea6.10415.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097353203678d3c7fb92c10d88dd68ba3a1b9a8edd3bd9f93f88b68acd98cfa6
3
+ size 4184
runs/Apr30_13-27-25_97416270aea6/events.out.tfevents.1746019648.97416270aea6.11532.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35497e90183d5e8e693585031b3aec0dba0916bf82c948b034d3d66126e237d
3
+ size 6604
runs/Apr30_13-28-53_97416270aea6/events.out.tfevents.1746019741.97416270aea6.11532.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d47f0ab41aba21b870507d445383ecc9d79184f499cd79974d9a51c4ed2f291
3
+ size 6603
runs/Apr30_13-31-13_97416270aea6/events.out.tfevents.1746019882.97416270aea6.11532.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cba71bacba34ba78143b1f8b32b6516df4bb847b0fde31f1dca88cd23817c3e
3
+ size 6617
runs/Apr30_13-33-12_97416270aea6/events.out.tfevents.1746019998.97416270aea6.11532.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2069a699807cb9ebd79f1115ad16e46827570c53ebe9af31c10dc21fe096b59
3
+ size 13146
runs/Apr30_13-36-35_97416270aea6/events.out.tfevents.1746020199.97416270aea6.11532.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e30ac83a43850b088431ee61089172fbf9b00e5aad98c4f12ee5824feac5f5e
3
+ size 7039
runs/Apr30_15-09-06_97416270aea6/events.out.tfevents.1746025761.97416270aea6.11532.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3f0b6e555a44cb92d37af0b5e9f14dd0a2a85678cf861761d983db43bfc748
3
+ size 4184
runs/Apr30_15-09-25_97416270aea6/events.out.tfevents.1746025770.97416270aea6.11532.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae311990fb4580d2daca719a80a92c73c7de3e3fda426e8e7f249cbd4360d97
3
+ size 12376
runs/Apr30_15-11-40_97416270aea6/events.out.tfevents.1746025903.97416270aea6.37954.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06321ef358d4542ee2d0bea348763bd0d132cae0d34ddf70af675d38cfa7d4e
3
+ size 12246
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a289a7edd3c94586cb86c0d9e4305d438acfe8364c018b2ec8850fa57a6d4aec
3
+ size 5304