tattrongvu
commited on
Upload 129 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +16 -0
- chat_template.json +3 -0
- checkpoint-570/adapter_config.json +26 -0
- checkpoint-570/adapter_model.safetensors +3 -0
- checkpoint-570/generation_config.json +14 -0
- checkpoint-570/optimizer.pt +3 -0
- checkpoint-570/rng_state_0.pth +3 -0
- checkpoint-570/rng_state_1.pth +3 -0
- checkpoint-570/rng_state_10.pth +3 -0
- checkpoint-570/rng_state_11.pth +3 -0
- checkpoint-570/rng_state_12.pth +3 -0
- checkpoint-570/rng_state_13.pth +3 -0
- checkpoint-570/rng_state_14.pth +3 -0
- checkpoint-570/rng_state_15.pth +3 -0
- checkpoint-570/rng_state_16.pth +3 -0
- checkpoint-570/rng_state_17.pth +3 -0
- checkpoint-570/rng_state_18.pth +3 -0
- checkpoint-570/rng_state_19.pth +3 -0
- checkpoint-570/rng_state_2.pth +3 -0
- checkpoint-570/rng_state_20.pth +3 -0
- checkpoint-570/rng_state_21.pth +3 -0
- checkpoint-570/rng_state_22.pth +3 -0
- checkpoint-570/rng_state_23.pth +3 -0
- checkpoint-570/rng_state_24.pth +3 -0
- checkpoint-570/rng_state_25.pth +3 -0
- checkpoint-570/rng_state_26.pth +3 -0
- checkpoint-570/rng_state_27.pth +3 -0
- checkpoint-570/rng_state_28.pth +3 -0
- checkpoint-570/rng_state_29.pth +3 -0
- checkpoint-570/rng_state_3.pth +3 -0
- checkpoint-570/rng_state_30.pth +3 -0
- checkpoint-570/rng_state_31.pth +3 -0
- checkpoint-570/rng_state_4.pth +3 -0
- checkpoint-570/rng_state_5.pth +3 -0
- checkpoint-570/rng_state_6.pth +3 -0
- checkpoint-570/rng_state_7.pth +3 -0
- checkpoint-570/rng_state_8.pth +3 -0
- checkpoint-570/rng_state_9.pth +3 -0
- checkpoint-570/scheduler.pt +3 -0
- checkpoint-570/trainer_state.json +325 -0
- checkpoint-570/training_args.bin +3 -0
- checkpoint-760/adapter_config.json +26 -0
- checkpoint-760/adapter_model.safetensors +3 -0
- checkpoint-760/generation_config.json +14 -0
- checkpoint-760/optimizer.pt +3 -0
- checkpoint-760/rng_state_0.pth +3 -0
- checkpoint-760/rng_state_1.pth +3 -0
- checkpoint-760/rng_state_10.pth +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": "gaussian",
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 64,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
23 |
+
"task_type": "FEATURE_EXTRACTION",
|
24 |
+
"use_dora": false,
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5daee05fe822268d18e339a140785ca821c14f41d5b3e9963b43c8f917bfde19
|
3 |
+
size 323489928
|
added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|box_end|>": 151649,
|
3 |
+
"<|box_start|>": 151648,
|
4 |
+
"<|endoftext|>": 151643,
|
5 |
+
"<|im_end|>": 151645,
|
6 |
+
"<|im_start|>": 151644,
|
7 |
+
"<|image_pad|>": 151655,
|
8 |
+
"<|object_ref_end|>": 151647,
|
9 |
+
"<|object_ref_start|>": 151646,
|
10 |
+
"<|quad_end|>": 151651,
|
11 |
+
"<|quad_start|>": 151650,
|
12 |
+
"<|video_pad|>": 151656,
|
13 |
+
"<|vision_end|>": 151653,
|
14 |
+
"<|vision_pad|>": 151654,
|
15 |
+
"<|vision_start|>": 151652
|
16 |
+
}
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
3 |
+
}
|
checkpoint-570/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/home/pv_rwm_models/models/qwen2vl-7b-instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": "gaussian",
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 64,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
23 |
+
"task_type": "FEATURE_EXTRACTION",
|
24 |
+
"use_dora": false,
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
checkpoint-570/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:198985f87a593aa6c14316a22b907c52bc2591b8fb7c6cb72392d62d4ebd8cac
|
3 |
+
size 323489928
|
checkpoint-570/generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attn_implementation": "flash_attention_2",
|
3 |
+
"bos_token_id": 151643,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
151645,
|
7 |
+
151643
|
8 |
+
],
|
9 |
+
"pad_token_id": 151643,
|
10 |
+
"temperature": 0.01,
|
11 |
+
"top_k": 1,
|
12 |
+
"top_p": 0.001,
|
13 |
+
"transformers_version": "4.46.3"
|
14 |
+
}
|
checkpoint-570/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25d8be0b4d3095c92cd2b6e8f761e9fed8c2a889db4b83ed24f6fe973700a755
|
3 |
+
size 647205360
|
checkpoint-570/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6785da9fb3a85e9b48178471fb9a817bea7ac2c862e0c74f37bf8abab5d03a7
|
3 |
+
size 15920
|
checkpoint-570/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16631e30ab2d5048d05cefd0d086af14da61a5ca2cd771e9f0bf21f43aa578a3
|
3 |
+
size 15920
|
checkpoint-570/rng_state_10.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e28ecca313728f00bf3e8f6e351a1a34b3cef6d22217553b6f96b5621ae43fb
|
3 |
+
size 15933
|
checkpoint-570/rng_state_11.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fda88ea6ded4f60e1856bd0bbb255e39d2c06309821ce57649b199a32b7c07c3
|
3 |
+
size 15933
|
checkpoint-570/rng_state_12.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad5732812f3027fb565fc37d887f4f4b5f8d43e762b5aa1aaac7382bb18a0690
|
3 |
+
size 15933
|
checkpoint-570/rng_state_13.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5dcf25d02cf8562b72b65a00ce2c84e8a98b89ba39425a79ec8e50d1776eab5
|
3 |
+
size 15933
|
checkpoint-570/rng_state_14.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a80c774ad1154df35c81a03af0c4afdf7392387252b3fc3e1cd70bc8f9fe2aab
|
3 |
+
size 15933
|
checkpoint-570/rng_state_15.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6beb2a5710113ab8bfc398ae581065d5d9a47d5fbf594c6d2cd1644d9b4edab3
|
3 |
+
size 15933
|
checkpoint-570/rng_state_16.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1d646b93a6850747a3984e111c5893c6e0332d768ff60ac69ed0b66bd350d25
|
3 |
+
size 15933
|
checkpoint-570/rng_state_17.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8689f9a507977bf6d9e92fb8ea7c74365daee5d10525d3c5f0ccae22d842058c
|
3 |
+
size 15933
|
checkpoint-570/rng_state_18.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7eb21741dbc3dc66454d594d059bfc3972d0304fbe8ad429943e5940d43b200a
|
3 |
+
size 15933
|
checkpoint-570/rng_state_19.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c3adf99d91b7905c948df1d2d1621461b61066a7bf669b12c976b1355722d51
|
3 |
+
size 15933
|
checkpoint-570/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5444e7d5415c562fc2f59a5f29d849dfbcda9c7d757048cd444a518bf701f49c
|
3 |
+
size 15920
|
checkpoint-570/rng_state_20.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:511b1b74286fd9bdbf79cf69f1fdd422b33c4b848fe9e0a377141d8ef8f5741b
|
3 |
+
size 15933
|
checkpoint-570/rng_state_21.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1cff6318a0be0f755f3e654889c9aca413ddd07159ead440c4de3306cb5e4d1
|
3 |
+
size 15933
|
checkpoint-570/rng_state_22.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea7d6ed2ed0acd6d9dbb71b6d1f475b81957f37d715e735ddd26828bf85f5e6a
|
3 |
+
size 15933
|
checkpoint-570/rng_state_23.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:782f84687fc644b743c7d4dd8c213cef043b2dd5eea9ef82637320662c22c335
|
3 |
+
size 15933
|
checkpoint-570/rng_state_24.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a4a04cc406388757ad69b2c06ee84af9044f1a4cecb77bfad12274087ebe2a8
|
3 |
+
size 15933
|
checkpoint-570/rng_state_25.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a438fc733612c8b5b31d26a6a79a489842fd376b54167a3f50767505f282ec39
|
3 |
+
size 15933
|
checkpoint-570/rng_state_26.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80f1ace6cad11bac4c1cfc1aaa1c49872ae87fc9552f20fda2b7dbb848a900e9
|
3 |
+
size 15933
|
checkpoint-570/rng_state_27.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaef7905e6fda8cef9f118b57b747c1979fc6a7152581804f5f762bb68bd1bb1
|
3 |
+
size 15933
|
checkpoint-570/rng_state_28.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7da88e70c299ed7d1fbd69a9aacb3b7a2ed09a9a3e9bedbb5f7e96d19ca4b7ea
|
3 |
+
size 15933
|
checkpoint-570/rng_state_29.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc2aff0328e3323b8f3cf74d8a50245a2bc8f11f3d54e4d09b520279cd0d9eb7
|
3 |
+
size 15933
|
checkpoint-570/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0501eedadea3815cdf4b5df77ee13d390e848b28f2b79d9085372ff06ecadf3e
|
3 |
+
size 15920
|
checkpoint-570/rng_state_30.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b7f59bd395c84aafa6e79854937ea29b3d3c9cc30df7ade1d59333d10f3384b
|
3 |
+
size 15933
|
checkpoint-570/rng_state_31.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c17e8f4aa1584ec964df2ba40fd7700c00b1fe40798c2587651578569362c2e1
|
3 |
+
size 15933
|
checkpoint-570/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc0e83d3ef6dd8fc360069a52d02ddb96b68d9ee3e8f288d17fd898f9128d2f8
|
3 |
+
size 15920
|
checkpoint-570/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fa6c9345ac0915ea1e245f881cf74fae76e8683178669a080c56d183d83a9af
|
3 |
+
size 15920
|
checkpoint-570/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbc26844613810e772aa68f10a783ff22ca9d24aae9809116405627e84f8df87
|
3 |
+
size 15920
|
checkpoint-570/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:892898299280773e96cabb0f0afb7c727ff11bb498ea9d0c932e74027067832a
|
3 |
+
size 15920
|
checkpoint-570/rng_state_8.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c609494620f4b971b942716984871be70801a271268dac7b96ccbde674849708
|
3 |
+
size 15920
|
checkpoint-570/rng_state_9.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d94e40aecf5be44e4599a373b46069c177786e52ba8d01353c26bd215d2452b4
|
3 |
+
size 15920
|
checkpoint-570/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d20ffc77193346f4c050813d784202d22d2e0326b869060d495782d344203c9
|
3 |
+
size 1064
|
checkpoint-570/trainer_state.json
ADDED
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 50,
|
6 |
+
"global_step": 570,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.005263157894736842,
|
13 |
+
"eval_loss": 0.32585662603378296,
|
14 |
+
"eval_runtime": 13.4514,
|
15 |
+
"eval_samples_per_second": 148.684,
|
16 |
+
"eval_steps_per_second": 0.149,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.10526315789473684,
|
21 |
+
"grad_norm": 0.171875,
|
22 |
+
"learning_rate": 0.00019978517722878627,
|
23 |
+
"loss": 0.2249,
|
24 |
+
"step": 20
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.21052631578947367,
|
28 |
+
"grad_norm": 0.13671875,
|
29 |
+
"learning_rate": 0.00019548872180451127,
|
30 |
+
"loss": 0.1193,
|
31 |
+
"step": 40
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.2631578947368421,
|
35 |
+
"eval_loss": 0.07482124119997025,
|
36 |
+
"eval_runtime": 12.7644,
|
37 |
+
"eval_samples_per_second": 156.686,
|
38 |
+
"eval_steps_per_second": 0.157,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.3157894736842105,
|
43 |
+
"grad_norm": 0.1201171875,
|
44 |
+
"learning_rate": 0.0001911922663802363,
|
45 |
+
"loss": 0.1033,
|
46 |
+
"step": 60
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.42105263157894735,
|
50 |
+
"grad_norm": 0.138671875,
|
51 |
+
"learning_rate": 0.00018689581095596134,
|
52 |
+
"loss": 0.0973,
|
53 |
+
"step": 80
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.5263157894736842,
|
57 |
+
"grad_norm": 0.1279296875,
|
58 |
+
"learning_rate": 0.00018259935553168637,
|
59 |
+
"loss": 0.0932,
|
60 |
+
"step": 100
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.5263157894736842,
|
64 |
+
"eval_loss": 0.06730526685714722,
|
65 |
+
"eval_runtime": 12.8198,
|
66 |
+
"eval_samples_per_second": 156.009,
|
67 |
+
"eval_steps_per_second": 0.156,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.631578947368421,
|
72 |
+
"grad_norm": 0.10205078125,
|
73 |
+
"learning_rate": 0.0001783029001074114,
|
74 |
+
"loss": 0.0894,
|
75 |
+
"step": 120
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.7368421052631579,
|
79 |
+
"grad_norm": 0.0947265625,
|
80 |
+
"learning_rate": 0.00017400644468313644,
|
81 |
+
"loss": 0.0881,
|
82 |
+
"step": 140
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.7894736842105263,
|
86 |
+
"eval_loss": 0.06297393888235092,
|
87 |
+
"eval_runtime": 12.7629,
|
88 |
+
"eval_samples_per_second": 156.704,
|
89 |
+
"eval_steps_per_second": 0.157,
|
90 |
+
"step": 150
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.8421052631578947,
|
94 |
+
"grad_norm": 0.11767578125,
|
95 |
+
"learning_rate": 0.00016970998925886144,
|
96 |
+
"loss": 0.0862,
|
97 |
+
"step": 160
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.9473684210526315,
|
101 |
+
"grad_norm": 0.12060546875,
|
102 |
+
"learning_rate": 0.00016541353383458648,
|
103 |
+
"loss": 0.084,
|
104 |
+
"step": 180
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.0526315789473684,
|
108 |
+
"grad_norm": 0.10888671875,
|
109 |
+
"learning_rate": 0.00016111707841031148,
|
110 |
+
"loss": 0.08,
|
111 |
+
"step": 200
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.0526315789473684,
|
115 |
+
"eval_loss": 0.05776415765285492,
|
116 |
+
"eval_runtime": 12.8264,
|
117 |
+
"eval_samples_per_second": 155.929,
|
118 |
+
"eval_steps_per_second": 0.156,
|
119 |
+
"step": 200
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.1578947368421053,
|
123 |
+
"grad_norm": 0.091796875,
|
124 |
+
"learning_rate": 0.00015682062298603652,
|
125 |
+
"loss": 0.0759,
|
126 |
+
"step": 220
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 1.263157894736842,
|
130 |
+
"grad_norm": 0.1044921875,
|
131 |
+
"learning_rate": 0.00015252416756176155,
|
132 |
+
"loss": 0.0757,
|
133 |
+
"step": 240
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 1.3157894736842106,
|
137 |
+
"eval_loss": 0.05684072896838188,
|
138 |
+
"eval_runtime": 12.8684,
|
139 |
+
"eval_samples_per_second": 155.42,
|
140 |
+
"eval_steps_per_second": 0.155,
|
141 |
+
"step": 250
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.368421052631579,
|
145 |
+
"grad_norm": 0.09326171875,
|
146 |
+
"learning_rate": 0.00014822771213748658,
|
147 |
+
"loss": 0.0745,
|
148 |
+
"step": 260
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 1.4736842105263157,
|
152 |
+
"grad_norm": 0.1005859375,
|
153 |
+
"learning_rate": 0.00014393125671321162,
|
154 |
+
"loss": 0.0732,
|
155 |
+
"step": 280
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.5789473684210527,
|
159 |
+
"grad_norm": 0.095703125,
|
160 |
+
"learning_rate": 0.00013963480128893662,
|
161 |
+
"loss": 0.0732,
|
162 |
+
"step": 300
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.5789473684210527,
|
166 |
+
"eval_loss": 0.057122766971588135,
|
167 |
+
"eval_runtime": 12.9739,
|
168 |
+
"eval_samples_per_second": 154.156,
|
169 |
+
"eval_steps_per_second": 0.154,
|
170 |
+
"step": 300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.6842105263157894,
|
174 |
+
"grad_norm": 0.1142578125,
|
175 |
+
"learning_rate": 0.00013533834586466166,
|
176 |
+
"loss": 0.0749,
|
177 |
+
"step": 320
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.7894736842105263,
|
181 |
+
"grad_norm": 0.087890625,
|
182 |
+
"learning_rate": 0.0001310418904403867,
|
183 |
+
"loss": 0.0722,
|
184 |
+
"step": 340
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.8421052631578947,
|
188 |
+
"eval_loss": 0.055894188582897186,
|
189 |
+
"eval_runtime": 13.0028,
|
190 |
+
"eval_samples_per_second": 153.813,
|
191 |
+
"eval_steps_per_second": 0.154,
|
192 |
+
"step": 350
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.8947368421052633,
|
196 |
+
"grad_norm": 0.076171875,
|
197 |
+
"learning_rate": 0.00012674543501611172,
|
198 |
+
"loss": 0.0705,
|
199 |
+
"step": 360
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 2.0,
|
203 |
+
"grad_norm": 0.072265625,
|
204 |
+
"learning_rate": 0.00012244897959183676,
|
205 |
+
"loss": 0.069,
|
206 |
+
"step": 380
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.1052631578947367,
|
210 |
+
"grad_norm": 0.08251953125,
|
211 |
+
"learning_rate": 0.00011815252416756178,
|
212 |
+
"loss": 0.065,
|
213 |
+
"step": 400
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 2.1052631578947367,
|
217 |
+
"eval_loss": 0.05468890815973282,
|
218 |
+
"eval_runtime": 12.8106,
|
219 |
+
"eval_samples_per_second": 156.121,
|
220 |
+
"eval_steps_per_second": 0.156,
|
221 |
+
"step": 400
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.2105263157894735,
|
225 |
+
"grad_norm": 0.08642578125,
|
226 |
+
"learning_rate": 0.00011385606874328681,
|
227 |
+
"loss": 0.0645,
|
228 |
+
"step": 420
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.3157894736842106,
|
232 |
+
"grad_norm": 0.09130859375,
|
233 |
+
"learning_rate": 0.00010955961331901181,
|
234 |
+
"loss": 0.0637,
|
235 |
+
"step": 440
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.3684210526315788,
|
239 |
+
"eval_loss": 0.05291734263300896,
|
240 |
+
"eval_runtime": 12.8493,
|
241 |
+
"eval_samples_per_second": 155.651,
|
242 |
+
"eval_steps_per_second": 0.156,
|
243 |
+
"step": 450
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 2.4210526315789473,
|
247 |
+
"grad_norm": 0.1005859375,
|
248 |
+
"learning_rate": 0.00010526315789473685,
|
249 |
+
"loss": 0.0652,
|
250 |
+
"step": 460
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 2.526315789473684,
|
254 |
+
"grad_norm": 0.08203125,
|
255 |
+
"learning_rate": 0.00010096670247046187,
|
256 |
+
"loss": 0.0642,
|
257 |
+
"step": 480
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 2.6315789473684212,
|
261 |
+
"grad_norm": 0.09130859375,
|
262 |
+
"learning_rate": 9.66702470461869e-05,
|
263 |
+
"loss": 0.063,
|
264 |
+
"step": 500
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 2.6315789473684212,
|
268 |
+
"eval_loss": 0.05152459070086479,
|
269 |
+
"eval_runtime": 12.8186,
|
270 |
+
"eval_samples_per_second": 156.024,
|
271 |
+
"eval_steps_per_second": 0.156,
|
272 |
+
"step": 500
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.736842105263158,
|
276 |
+
"grad_norm": 0.19140625,
|
277 |
+
"learning_rate": 9.237379162191193e-05,
|
278 |
+
"loss": 0.0635,
|
279 |
+
"step": 520
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 2.8421052631578947,
|
283 |
+
"grad_norm": 0.09716796875,
|
284 |
+
"learning_rate": 8.807733619763695e-05,
|
285 |
+
"loss": 0.064,
|
286 |
+
"step": 540
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 2.8947368421052633,
|
290 |
+
"eval_loss": 0.05137969180941582,
|
291 |
+
"eval_runtime": 12.8105,
|
292 |
+
"eval_samples_per_second": 156.122,
|
293 |
+
"eval_steps_per_second": 0.156,
|
294 |
+
"step": 550
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 2.9473684210526314,
|
298 |
+
"grad_norm": 0.0849609375,
|
299 |
+
"learning_rate": 8.378088077336199e-05,
|
300 |
+
"loss": 0.0634,
|
301 |
+
"step": 560
|
302 |
+
}
|
303 |
+
],
|
304 |
+
"logging_steps": 20,
|
305 |
+
"max_steps": 950,
|
306 |
+
"num_input_tokens_seen": 0,
|
307 |
+
"num_train_epochs": 5,
|
308 |
+
"save_steps": 500,
|
309 |
+
"stateful_callbacks": {
|
310 |
+
"TrainerControl": {
|
311 |
+
"args": {
|
312 |
+
"should_epoch_stop": false,
|
313 |
+
"should_evaluate": false,
|
314 |
+
"should_log": false,
|
315 |
+
"should_save": true,
|
316 |
+
"should_training_stop": false
|
317 |
+
},
|
318 |
+
"attributes": {}
|
319 |
+
}
|
320 |
+
},
|
321 |
+
"total_flos": 5.685776305150021e+19,
|
322 |
+
"train_batch_size": 64,
|
323 |
+
"trial_name": null,
|
324 |
+
"trial_params": null
|
325 |
+
}
|
checkpoint-570/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87265727decc0a98a4f097e1876e05a86f58eeeec1be906a56c9562796bd8c68
|
3 |
+
size 5496
|
checkpoint-760/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "/home/pv_rwm_models/models/qwen2vl-7b-instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": "gaussian",
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 64,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": "(.*(model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
23 |
+
"task_type": "FEATURE_EXTRACTION",
|
24 |
+
"use_dora": false,
|
25 |
+
"use_rslora": false
|
26 |
+
}
|
checkpoint-760/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:882c7904c44a59084f7c5bbb5e2941556fc469265694fd63a71251b973c3ff59
|
3 |
+
size 323489928
|
checkpoint-760/generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attn_implementation": "flash_attention_2",
|
3 |
+
"bos_token_id": 151643,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
151645,
|
7 |
+
151643
|
8 |
+
],
|
9 |
+
"pad_token_id": 151643,
|
10 |
+
"temperature": 0.01,
|
11 |
+
"top_k": 1,
|
12 |
+
"top_p": 0.001,
|
13 |
+
"transformers_version": "4.46.3"
|
14 |
+
}
|
checkpoint-760/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d4302fa80226bd89c5ce2dddd3e230b2265382d7fa723f645c0013cedd8641e
|
3 |
+
size 647205360
|
checkpoint-760/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d324201c8dd00963ff312d4d7856c63f4ee278b0ccba92590749e13a896629bc
|
3 |
+
size 15920
|
checkpoint-760/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c014d35175b258a36b49f1c221b83d26a00f666dc7b0b06e232e97823d0331c
|
3 |
+
size 15920
|
checkpoint-760/rng_state_10.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e5b7118186583995908b7430a1f95a94731b49b6e1be6813de4e045fbd7eb21
|
3 |
+
size 15933
|