Hugging Face's logo

emendes3
/
llava_13b_city_synthetic

PEFT
Safetensors
llava_llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
emendes3 commited on
Commit
7e31666
•
1 Parent(s): e6c588c

Model save

Browse files
Files changed (8) hide show
  1. README.md +6 -14
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. num_examples=200/llava-v1.5-13b_1.0/adapter_config.json +4 -4
  5. num_examples=200/llava-v1.5-13b_1.0/adapter_model.safetensors +1 -1
  6. num_examples=200/llava-v1.5-13b_1.0/training_args.bin +1 -1
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -1,27 +1,19 @@
1
  ---
2
  library_name: peft
3
  tags:
4
- - liuhaotian/llava-v1.5-13b_20.0
5
  - generated_from_trainer
6
  base_model: liuhaotian/llava-v1.5-13b
7
  model-index:
8
- - name: liuhaotian/llava-v1.5-13b_20.0
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
- # liuhaotian/llava-v1.5-13b_20.0
16
 
17
- This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_20.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_20.0) on an unknown dataset.
18
- It achieves the following results on the evaluation set:
19
- - eval_loss: 0.0084
20
- - eval_runtime: 97.4436
21
- - eval_samples_per_second: 8.897
22
- - eval_steps_per_second: 0.564
23
- - epoch: 19.0
24
- - step: 1045
25
 
26
  ## Model description
27
 
@@ -45,9 +37,9 @@ The following hyperparameters were used during training:
45
  - eval_batch_size: 4
46
  - seed: 42
47
  - distributed_type: multi-GPU
48
- - num_devices: 4
49
- - total_train_batch_size: 16
50
- - total_eval_batch_size: 16
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: cosine
53
  - lr_scheduler_warmup_ratio: 0.03
 
1
  ---
2
  library_name: peft
3
  tags:
 
4
  - generated_from_trainer
5
  base_model: liuhaotian/llava-v1.5-13b
6
  model-index:
7
+ - name: llava_13b_city_synthetic
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
+ # llava_13b_city_synthetic
15
 
16
+ This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
 
 
 
 
 
 
 
17
 
18
  ## Model description
19
 
 
37
  - eval_batch_size: 4
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
+ - num_devices: 8
41
+ - total_train_batch_size: 32
42
+ - total_eval_batch_size: 32
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_ratio: 0.03
adapter_config.json CHANGED
@@ -21,12 +21,12 @@
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
24
- "down_proj",
25
- "up_proj",
26
  "o_proj",
27
- "k_proj",
28
  "v_proj",
29
- "gate_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
 
 
24
  "o_proj",
 
25
  "v_proj",
26
+ "gate_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6c6e6a0e45fc995e3359e7b7e34bf0606ee310814d7e3303360a1f55cd4548c
3
  size 1001466944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9985bb50dd6bfc13d8e5f797d021e8c984c4e4dda70293bb9d732aa5d5d7548
3
  size 1001466944
num_examples=200/llava-v1.5-13b_1.0/adapter_config.json CHANGED
@@ -21,12 +21,12 @@
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
24
- "down_proj",
25
- "up_proj",
26
  "o_proj",
27
- "k_proj",
28
  "v_proj",
29
- "gate_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "q_proj",
 
 
24
  "o_proj",
 
25
  "v_proj",
26
+ "gate_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
num_examples=200/llava-v1.5-13b_1.0/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba25291c06cb1e6a47f02c31103209d74d0e864b2764f62cee4154f3279409ac
3
  size 1001466944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9985bb50dd6bfc13d8e5f797d021e8c984c4e4dda70293bb9d732aa5d5d7548
3
  size 1001466944
num_examples=200/llava-v1.5-13b_1.0/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68b1bbb11bfc8c644064cc5e96ef02c8b9757944773b9997a7c1459682ec6cfc
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0d06c9fd7490c2d447d2a52d23b09dc37d018262a7480fbe9852e170816a8a
3
  size 6776
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68b1bbb11bfc8c644064cc5e96ef02c8b9757944773b9997a7c1459682ec6cfc
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0d06c9fd7490c2d447d2a52d23b09dc37d018262a7480fbe9852e170816a8a
3
  size 6776