Training in progress, step 500
Browse files- adapter_config.json +43 -0
- adapter_model.safetensors +3 -0
- runs/Apr26_21-52-12_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714168409.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.225.0 +3 -0
- runs/Apr26_22-10-27_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714169491.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.647.0 +3 -0
- runs/Apr27_23-11-07_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714259518.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.17.0 +3 -0
- runs/Apr27_23-18-59_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714259947.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.296.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +60 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 8,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"k_proj",
|
27 |
+
"o_proj",
|
28 |
+
"fc2",
|
29 |
+
"linear_1",
|
30 |
+
"v_proj",
|
31 |
+
"up_proj",
|
32 |
+
"lm_head",
|
33 |
+
"out_proj",
|
34 |
+
"fc1",
|
35 |
+
"linear_2",
|
36 |
+
"q_proj",
|
37 |
+
"gate_proj",
|
38 |
+
"down_proj"
|
39 |
+
],
|
40 |
+
"task_type": null,
|
41 |
+
"use_dora": false,
|
42 |
+
"use_rslora": false
|
43 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6f88398937d46b53492a1789cd1dcd8114fc1afd14212356b1317f41b6089ed
|
3 |
+
size 621143576
|
runs/Apr26_21-52-12_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714168409.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.225.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae497ef270b4e876261ae04077234d198cf3dc625dc4cd6ea21912b421c5bfc7
|
3 |
+
size 5556
|
runs/Apr26_22-10-27_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714169491.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.647.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57fb34fb86922b1e786187a064fbee5bd20e5ac3af063742460213fe74ac857d
|
3 |
+
size 5556
|
runs/Apr27_23-11-07_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714259518.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.17.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7507209a9be1e5e6984ebdee73aa05c2f6b94111639fafe6c36755db3bdcc966
|
3 |
+
size 5556
|
runs/Apr27_23-18-59_pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167/events.out.tfevents.1714259947.pytorch-2-2-0-gpu-py-ml-p3-2xlarge-95bb9c479645152f5dc45b307167.296.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92b0f067300e1e8ba1ed310a954bfa2cceae09a51d23830ef3e71a5297826f84
|
3 |
+
size 26556
|
special_tokens_map.json
ADDED
@@ -0,0 +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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<image>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<pad>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"bos_token": "<s>",
|
47 |
+
"chat_template": "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. {% for message in messages %}{% if message['role'] == 'user' %}USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}{% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}",
|
48 |
+
"clean_up_tokenization_spaces": false,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"legacy": false,
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"padding_side": "left",
|
54 |
+
"processor_class": "LlavaProcessor",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"tokenizer_class": "LlamaTokenizer",
|
57 |
+
"trust_remote_code": false,
|
58 |
+
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": false
|
60 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e6f1e943390b574d687a7264674dd0ff49cae3bb8ecb55fbc6780359ff60305
|
3 |
+
size 5048
|