Commit
•
e6a919f
1
Parent(s):
7a1fd72
End of training
Browse files- README.md +7 -7
- adapter_config.json +8 -8
- adapter_model.safetensors +1 -1
- tokenizer.json +1 -1
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -6,16 +6,16 @@ tags:
|
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
#
|
17 |
|
18 |
-
This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,12 +35,12 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 1.4e-05
|
38 |
-
- train_batch_size:
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
@@ -51,6 +51,6 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
- PEFT 0.11.1
|
53 |
- Transformers 4.42.3
|
54 |
-
- Pytorch 2.
|
55 |
-
- Datasets 2.
|
56 |
- Tokenizers 0.19.1
|
|
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
+
- name: model
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
+
# model
|
17 |
|
18 |
+
This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on the None dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 1.4e-05
|
38 |
+
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
|
|
51 |
|
52 |
- PEFT 0.11.1
|
53 |
- Transformers 4.42.3
|
54 |
+
- Pytorch 2.1.0
|
55 |
+
- Datasets 2.15.0
|
56 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -23,19 +23,19 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"out_proj",
|
27 |
"fc1",
|
28 |
-
"
|
29 |
-
"q_proj",
|
30 |
"linear_2",
|
|
|
|
|
|
|
|
|
|
|
31 |
"linear_1",
|
32 |
"gate_proj",
|
33 |
-
"fc2",
|
34 |
"v_proj",
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"lm_head",
|
38 |
-
"down_proj"
|
39 |
],
|
40 |
"task_type": null,
|
41 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
|
|
26 |
"fc1",
|
27 |
+
"down_proj",
|
|
|
28 |
"linear_2",
|
29 |
+
"o_proj",
|
30 |
+
"q_proj",
|
31 |
+
"out_proj",
|
32 |
+
"up_proj",
|
33 |
+
"k_proj",
|
34 |
"linear_1",
|
35 |
"gate_proj",
|
|
|
36 |
"v_proj",
|
37 |
+
"fc2",
|
38 |
+
"lm_head"
|
|
|
|
|
39 |
],
|
40 |
"task_type": null,
|
41 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1290994752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3fa5a15365ef64e08deff7b334b15ae2ef70b5b17762115e326c6c87c26f6e5
|
3 |
size 1290994752
|
tokenizer.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"truncation": null,
|
4 |
"padding": {
|
5 |
"strategy": "BatchLongest",
|
6 |
-
"direction": "
|
7 |
"pad_to_multiple_of": null,
|
8 |
"pad_id": 32001,
|
9 |
"pad_type_id": 0,
|
|
|
3 |
"truncation": null,
|
4 |
"padding": {
|
5 |
"strategy": "BatchLongest",
|
6 |
+
"direction": "Left",
|
7 |
"pad_to_multiple_of": null,
|
8 |
"pad_id": 32001,
|
9 |
"pad_type_id": 0,
|
tokenizer_config.json
CHANGED
@@ -51,7 +51,7 @@
|
|
51 |
"legacy": false,
|
52 |
"model_max_length": 1000000000000000019884624838656,
|
53 |
"pad_token": "<pad>",
|
54 |
-
"padding_side": "
|
55 |
"processor_class": "LlavaProcessor",
|
56 |
"sp_model_kwargs": {},
|
57 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
51 |
"legacy": false,
|
52 |
"model_max_length": 1000000000000000019884624838656,
|
53 |
"pad_token": "<pad>",
|
54 |
+
"padding_side": "left",
|
55 |
"processor_class": "LlavaProcessor",
|
56 |
"sp_model_kwargs": {},
|
57 |
"tokenizer_class": "LlamaTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb3854861ed3b77e539fb7b3de4d44f9b985c327f59999bdf9a3a0d074515c2c
|
3 |
size 5112
|