Louisnguyen
commited on
Commit
•
ec1a5e6
1
Parent(s):
8a8311c
Training in progress, step 500
Browse files- README.md +13 -13
- adapter_config.json +35 -35
- adapter_model.safetensors +1 -1
- runs/Jul26_04-32-02_ip-10-192-12-151/events.out.tfevents.1721968337.ip-10-192-12-151.8017.1 +3 -0
- runs/Jul26_05-28-52_ip-10-192-12-151/events.out.tfevents.1721971749.ip-10-192-12-151.8017.2 +3 -0
- runs/Jul26_05-32-51_ip-10-192-12-151/events.out.tfevents.1721971982.ip-10-192-12-151.8017.3 +3 -0
- special_tokens_map.json +30 -30
- tokenizer_config.json +61 -61
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
-
---
|
2 |
-
base_model: llava-hf/llava-1.5-7b-hf
|
3 |
-
library_name: peft
|
4 |
-
license: llama2
|
5 |
-
tags:
|
6 |
-
- trl
|
7 |
-
- sft
|
8 |
-
- generated_from_trainer
|
9 |
-
model-index:
|
10 |
-
- name: llava-1.5-7b-hf-train-bio2
|
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. -->
|
@@ -52,6 +52,6 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
- PEFT 0.12.0
|
54 |
- Transformers 4.43.2
|
55 |
-
- Pytorch 2.
|
56 |
- Datasets 2.20.0
|
57 |
- Tokenizers 0.19.1
|
|
|
1 |
+
---
|
2 |
+
base_model: llava-hf/llava-1.5-7b-hf
|
3 |
+
library_name: peft
|
4 |
+
license: llama2
|
5 |
+
tags:
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: llava-1.5-7b-hf-train-bio2
|
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. -->
|
|
|
52 |
|
53 |
- PEFT 0.12.0
|
54 |
- Transformers 4.43.2
|
55 |
+
- Pytorch 2.2.1+cu121
|
56 |
- Datasets 2.20.0
|
57 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -1,36 +1,36 @@
|
|
1 |
-
{
|
2 |
-
"alpha_pattern": {},
|
3 |
-
"auto_mapping": {
|
4 |
-
"base_model_class": "LlavaForConditionalGeneration",
|
5 |
-
"parent_library": "transformers.models.llava.modeling_llava"
|
6 |
-
},
|
7 |
-
"base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
|
8 |
-
"bias": "none",
|
9 |
-
"fan_in_fan_out": false,
|
10 |
-
"inference_mode": true,
|
11 |
-
"init_lora_weights": true,
|
12 |
-
"layer_replication": null,
|
13 |
-
"layers_pattern": null,
|
14 |
-
"layers_to_transform": null,
|
15 |
-
"loftq_config": {},
|
16 |
-
"lora_alpha": 16,
|
17 |
-
"lora_dropout": 0.0,
|
18 |
-
"megatron_config": null,
|
19 |
-
"megatron_core": "megatron.core",
|
20 |
-
"modules_to_save": null,
|
21 |
-
"peft_type": "LORA",
|
22 |
-
"r": 64,
|
23 |
-
"rank_pattern": {},
|
24 |
-
"revision": null,
|
25 |
-
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
],
|
33 |
-
"task_type": null,
|
34 |
-
"use_dora": false,
|
35 |
-
"use_rslora": false
|
36 |
}
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlavaForConditionalGeneration",
|
5 |
+
"parent_library": "transformers.models.llava.modeling_llava"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_dropout": 0.0,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 64,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"q_proj",
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"v_projfc1",
|
30 |
+
"k_proj",
|
31 |
+
"fc2up_proj"
|
32 |
+
],
|
33 |
+
"task_type": null,
|
34 |
+
"use_dora": false,
|
35 |
+
"use_rslora": false
|
36 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 406901688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22574490638dcb4a3a335722f7a8378733ec6197069567c5eb1fc80ccfdfdf2f
|
3 |
size 406901688
|
runs/Jul26_04-32-02_ip-10-192-12-151/events.out.tfevents.1721968337.ip-10-192-12-151.8017.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1371ba020ad967f7d1adacb99c70d938d06aa81d995f8d8630dba1b0d1ed0b7c
|
3 |
+
size 7959
|
runs/Jul26_05-28-52_ip-10-192-12-151/events.out.tfevents.1721971749.ip-10-192-12-151.8017.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2a6d5bf6dbb4ed40032a7958e768a6c74d106a6c380c98116fbd0426f2f0463
|
3 |
+
size 6080
|
runs/Jul26_05-32-51_ip-10-192-12-151/events.out.tfevents.1721971982.ip-10-192-12-151.8017.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:044df83ef2b89bd892a7888928db961645e1a80ceeb02ad34c24daaf7c0be339
|
3 |
+
size 10280
|
special_tokens_map.json
CHANGED
@@ -1,30 +1,30 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<pad>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1,61 +1,61 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": null,
|
5 |
-
"added_tokens_decoder": {
|
6 |
-
"0": {
|
7 |
-
"content": "<unk>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": true
|
13 |
-
},
|
14 |
-
"1": {
|
15 |
-
"content": "<s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false,
|
20 |
-
"special": true
|
21 |
-
},
|
22 |
-
"2": {
|
23 |
-
"content": "</s>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": false,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false,
|
28 |
-
"special": true
|
29 |
-
},
|
30 |
-
"32000": {
|
31 |
-
"content": "<image>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
-
},
|
38 |
-
"32001": {
|
39 |
-
"content": "<pad>",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false,
|
44 |
-
"special": true
|
45 |
-
}
|
46 |
-
},
|
47 |
-
"bos_token": "<s>",
|
48 |
-
"chat_template": "A chat between
|
49 |
-
"clean_up_tokenization_spaces": false,
|
50 |
-
"eos_token": "</s>",
|
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",
|
58 |
-
"trust_remote_code": false,
|
59 |
-
"unk_token": "<unk>",
|
60 |
-
"use_default_system_prompt": false
|
61 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<image>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<pad>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"bos_token": "<s>",
|
48 |
+
"chat_template": "A chat between an user and an artificial intelligence assistant about Science Question Answering. The assistant gives helpful, detailed, and polite answers to the user's questions.\nBased on the image and question, please choose one of the given choices that answer the question.\nGive yourself room to think by extracting the image and question before choosing the choice.\nDon't return the thinking, only return the highest accuracy choice.\nMake sure your answers are as correct as possible.\n{% for tag, content in messages.items() %}\n{% if tag == 'sample_question' %}\nUse the following examples as reference for the ideal answer style.\n{% for message in content %}\n{% if message['role'] == 'user' %} \nExample\nUSER: {% else %}ASSISTANT: {% endif %}\n{% for item in message['content'] %}\n{% if item['type'] == 'text_question' %}\nQuestion: {{ item['question'] }}\n{% elif item['type'] == 'text_choice' %}\nChoices: {{ item['choice'] }}\n{% elif item['type'] == 'text_solution' %}\nSolution: {{ item['solution'] }}\n{% elif item['type'] == 'text_answer' %}\nAnswer: {{ item['answer'] }}{% elif item['type'] == 'image' %}<image>\n{% endif %}\n{% endfor %}\n{% if message['role'] == 'user' %}\n{% else %}\n{{eos_token}}\n{% endif %}{% endfor %}{% endif %}\n\n{% if tag == 'real_question' %}\nNow use the following image and question to choose the choice:\n{% for message in content %}\n{% if message['role'] == 'user' %}USER: {% else %}ASSISTANT: {% endif %}\n{% for item in message['content'] %}\n{% if item['type'] == 'text_question' %}\nQuestion: {{ item['question'] }}\n{% elif item['type'] == 'text_choice' %}\nChoices: {{ item['choice'] }}\n{% elif item['type'] == 'text_solution' %}\nSolution: {{ item['solution'] }}\n{% elif item['type'] == 'text_answer' %}\nAnswer: {{ item['answer'] }}{% elif item['type'] == 'image' %}<image>\n{% endif %}\n{% endfor %}\n{% if message['role'] == 'user' %}\n{% else %}\n{{eos_token}}\n{% endif %}{% endfor %}{% endif %}\n{% endfor %}",
|
49 |
+
"clean_up_tokenization_spaces": false,
|
50 |
+
"eos_token": "</s>",
|
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",
|
58 |
+
"trust_remote_code": false,
|
59 |
+
"unk_token": "<unk>",
|
60 |
+
"use_default_system_prompt": false
|
61 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e9705325b640d251bcc226e086bcb6e10a8bfdd500e23b4a747cdeb0dfa9850
|
3 |
size 5496
|