htlou commited on
Commit
04f245c
1 Parent(s): 38a0140

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ wandb/debug-internal.log filter=lfs diff=lfs merge=lfs -text
37
+ wandb/run-20240922_183418-smhpt648/logs/debug-internal.log filter=lfs diff=lfs merge=lfs -text
38
+ wandb/run-20240922_183418-smhpt648/run-smhpt648.wandb filter=lfs diff=lfs merge=lfs -text
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
+ }
arguments.yaml ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ data_cfgs:
2
+ eval_data_files: null
3
+ eval_datasets: null
4
+ eval_optional_args: []
5
+ eval_size: null
6
+ eval_split: null
7
+ eval_subset: null
8
+ eval_template: null
9
+ ptx_data_files: extracted_panda.json
10
+ ptx_datasets: /aifs4su/yaodong/datasets/ShareGPT4Video/extracted
11
+ ptx_optional_args: []
12
+ ptx_size: 25000
13
+ ptx_split: train
14
+ ptx_subset: null
15
+ ptx_template: NExTQA
16
+ train_data_files: extracted_preference_10k_washed.json
17
+ train_datasets: /aifs4su/yaodong/datasets/aaa_dataset/TV2T-preference/extracted
18
+ train_optional_args: []
19
+ train_size: null
20
+ train_split: train
21
+ train_subset: null
22
+ train_template: NExTQA_preference
23
+ logger_cfgs:
24
+ cache_dir: null
25
+ log_project: align-anything
26
+ log_run_name: ppo
27
+ log_type: wandb
28
+ output_dir: ../outputs/ppo_qwen2vl_10k_baseline
29
+ save_interval: 300.0
30
+ model_cfgs:
31
+ actor_model_name_or_path: /aifs4su/yaodong/models/Qwen2-VL-7B-Instruct
32
+ model_max_length: 2048
33
+ repetition_penalty: 1.0
34
+ reward_critic_model_name_or_path: /aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline
35
+ reward_model_name_or_path: /aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline
36
+ temperature: 1.0
37
+ top_p: 1.0
38
+ trust_remote_code: true
39
+ special_tokens: null
40
+ train_cfgs:
41
+ actor_gradient_checkpointing: true
42
+ actor_lr: 5.0e-07
43
+ actor_lr_scheduler_type: cosine
44
+ actor_lr_warmup_ratio: 0.03
45
+ actor_weight_decay: 0.0
46
+ adam_betas:
47
+ - 0.9
48
+ - 0.95
49
+ bf16: true
50
+ clip_range_ratio: 0.2
51
+ clip_range_score: 50.0
52
+ clip_range_value: 5.0
53
+ critic_gradient_checkpointing: true
54
+ critic_lr: 5.0e-07
55
+ critic_lr_scheduler_type: constant
56
+ critic_lr_warmup_ratio: 0.03
57
+ critic_weight_decay: 0.0
58
+ ds_cfgs: ds_z3_config.json
59
+ epochs: 3
60
+ eval_interval: 10
61
+ eval_strategy: epoch
62
+ fp16: false
63
+ freeze_language_model: false
64
+ freeze_mm_proj: false
65
+ freeze_vision_tower: true
66
+ gae_lambda: 0.95
67
+ gamma: 1.0
68
+ gradient_accumulation_steps: 1
69
+ kl_coeff: 0.02
70
+ normalize_reward: false
71
+ per_device_eval_batch_size: 2
72
+ per_device_prompt_batch_size: 2
73
+ per_device_train_batch_size: 2
74
+ ptx_coeff: 16.0
75
+ seed: 42
76
+ update_iters: 1
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/aifs4su/yaodong/models/Qwen2-VL-7B-Instruct",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128245,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 151643,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": {
23
+ "mrope_section": [
24
+ 16,
25
+ 24,
26
+ 24
27
+ ],
28
+ "rope_type": "default",
29
+ "type": "default"
30
+ },
31
+ "rope_theta": 1000000.0,
32
+ "sliding_window": 32768,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.45.0.dev0",
36
+ "use_cache": true,
37
+ "use_sliding_window": false,
38
+ "video_token_id": 151656,
39
+ "vision_config": {
40
+ "in_chans": 3,
41
+ "model_type": "qwen2_vl",
42
+ "spatial_patch_size": 14
43
+ },
44
+ "vision_end_token_id": 151653,
45
+ "vision_start_token_id": 151652,
46
+ "vision_token_id": 151654,
47
+ "vocab_size": 151657
48
+ }
environ.txt ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ CONDA_DEFAULT_ENV=hantao_new
2
+ CONDA_EXE=/aifs4su/yaodong/miniconda3/bin/conda
3
+ CONDA_PREFIX=/aifs4su/yaodong/miniconda3/envs/hantao_new
4
+ CONDA_PREFIX_1=/aifs4su/yaodong/miniconda3
5
+ CONDA_PYTHON_EXE=/aifs4su/yaodong/miniconda3/bin/python
6
+ CROSS_RANK=0
7
+ CROSS_SIZE=2
8
+ CUDA_HOME=/aifs4su/yaodong/miniconda3/envs/hantao_new
9
+ CUDA_MODULE_LOADING=LAZY
10
+ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
11
+ DBUS_SESSION_BUS_ADDRESS=unix:path=/run/user/1028/bus
12
+ HOME=/home/yangyaodong
13
+ KMP_DUPLICATE_LIB_OK=True
14
+ KMP_INIT_AT_FORK=FALSE
15
+ LANG=C.UTF-8
16
+ LD_LIBRARY_PATH=/aifs4su/yaodong/miniconda3/envs/hantao_new/lib:/usr/mpi/gcc/openmpi-4.1.7a1/lib:/usr/local/cuda/lib64:/usr/local/cuda/lib64:/cm/shared/apps/slurm/current/lib64/slurm:/cm/shared/apps/slurm/current/lib64
17
+ LD_LIBRARY_PATH_modshare=/cm/shared/apps/slurm/current/lib64:1:/usr/mpi/gcc/openmpi-4.1.7a1/lib:1:/cm/shared/apps/slurm/current/lib64/slurm:1:/usr/local/cuda/lib64:1
18
+ LD_RUN_PATH=/usr/mpi/gcc/openmpi-4.1.7a1/lib
19
+ LIBRARY_PATH=/cm/shared/apps/slurm/current/lib64/slurm:/cm/shared/apps/slurm/current/lib64
20
+ LOCAL_RANK=0
21
+ LOCAL_SIZE=8
22
+ LOGNAME=yangyaodong
23
+ MASTER_ADDR=10.34.2.157
24
+ MASTER_PORT=44401
25
+ MOTD_SHOWN=pam
26
+ NCCL_P2P_LEVEL=NVL
27
+ OLDPWD=/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/scripts
28
+ PATH=/aifs4su/yaodong/google-cloud-sdk/bin:/aifs4su/yaodong/miniconda3/envs/hantao_new/bin:/aifs4su/yaodong/miniconda3/condabin:/usr/mpi/gcc/openmpi-4.1.7a1/bin:/usr/local/cuda/bin:/usr/lpp/mmfs/bin:/usr/local/cuda/bin:/opt/bin:/usr/local/cuda/bin:/usr/lpp/mmfs/bin:/cm/shared/apps/slurm/current/sbin:/cm/shared/apps/slurm/current/bin:/usr/local/cuda/bin:/opt/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/sbin:/usr/sbin:/cm/local/apps/environment-modules/4.5.3/bin
29
+ PWD=/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/scripts
30
+ PYTHONHASHSEED=42
31
+ PYTHONPATH=/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/scripts:/aifs4su/yaodong/projects/hantao/dev_cham/align-anything:/aifs4su/yaodong/projects/hantao/dev_cham/align-anything
32
+ RANK=0
33
+ SHELL=/bin/bash
34
+ SHLVL=0
35
+ SSH_CLIENT=10.33.5.36 35072 22
36
+ SSH_CONNECTION=10.33.5.36 35072 10.33.4.221 22
37
+ TMUX_PANE=%0
38
+ USER=yangyaodong
39
+ WANDB_API_KEY=547f38af44135ca76a4f4eed9c8d135532da4960
40
+ WANDB_SERVICE=2-424659-tcp-localhost-58441
41
+ WORLD_SIZE=16
42
+ XDG_RUNTIME_DIR=/run/user/1028
43
+ XDG_SESSION_CLASS=user
44
+ XDG_SESSION_ID=626
45
+ XDG_SESSION_TYPE=tty
46
+ _=/aifs4su/yaodong/miniconda3/envs/hantao_tiv/bin/python3.11
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 1003520,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b57dcb8f2ff9e4592bbd0137d9f7cfdcd08ea469b14f3eb480244e24e947802f
3
+ size 16577151950
pytorch_model_300.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78cb9fd9d357f8fa74ac31070a59f8e63550462e231021b8acc773aa3bd3a64
3
+ size 16577154886
pytorch_model_600.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cb81179965a164c636cc4b4029cb3722db888a5c2a6c8071bc61b3cb2ce1db
3
+ size 16577154886
pytorch_model_900.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:176114af6800414cdce832f02b100f97b98ca7f8f5090ec64b3f238e7a415b49
3
+ size 16577154886
script.sh ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env bash
2
+ #
3
+ # Copyright 2024 PKU-Alignment Team. All Rights Reserved.
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+ # ==============================================================================
17
+
18
+
19
+ # Initialize variables
20
+ # For wandb online logging
21
+ export WANDB_API_KEY="547f38af44135ca76a4f4eed9c8d135532da4960"
22
+ export NCCL_P2P_LEVEL=NVL
23
+ # Source the setup script
24
+ source ./setup.sh
25
+
26
+ ACTOR_MODEL_NAME_OR_PATH="/aifs4su/yaodong/models/Qwen2-VL-7B-Instruct"
27
+ CRITIC_MODEL_NAME_OR_PATH="/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline"
28
+ REWARD_MODEL_NAME_OR_PATH="/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline"
29
+ TRAIN_DATASETS="/aifs4su/yaodong/datasets/aaa_dataset/TV2T-preference/extracted"
30
+ PTX_DATASETS="/aifs4su/yaodong/datasets/ShareGPT4Video/extracted"
31
+ OUTPUT_DIR="../outputs/ppo_qwen2vl_10k_baseline"
32
+
33
+ # Source the setup script
34
+ source ./setup.sh
35
+
36
+ # Execute deepspeed command
37
+ deepspeed \
38
+ --hostfile ./host10 \
39
+ --master_port ${MASTER_PORT} \
40
+ --module align_anything.trainers.tiv_to_t.ppo \
41
+ --actor_model_name_or_path ${ACTOR_MODEL_NAME_OR_PATH} \
42
+ --reward_model_name_or_path ${REWARD_MODEL_NAME_OR_PATH} \
43
+ --reward_critic_model_name_or_path ${CRITIC_MODEL_NAME_OR_PATH} \
44
+ --train_datasets ${TRAIN_DATASETS} \
45
+ --train_template NExTQA_preference \
46
+ --train_data_files extracted_preference_10k_washed.json \
47
+ --train_split 'train' \
48
+ --ptx_datasets ${PTX_DATASETS} \
49
+ --ptx_data_files extracted_panda.json \
50
+ --ptx_template NExTQA \
51
+ --ptx_split 'train' \
52
+ --output_dir ${OUTPUT_DIR} \
53
+ --ddp_timeout 18000000000 \
54
+ --save_interval 300
special_tokens_map.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "bos_token": {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "eos_token": {
25
+ "content": "<|im_end|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": {
32
+ "content": "<|endoftext|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "unk_token": {
39
+ "content": "<unk>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "128244": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128245": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151643": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151644": {
29
+ "content": "<|im_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151645": {
37
+ "content": "<|im_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151646": {
45
+ "content": "<|object_ref_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151647": {
53
+ "content": "<|object_ref_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151648": {
61
+ "content": "<|box_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151649": {
69
+ "content": "<|box_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151650": {
77
+ "content": "<|quad_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151651": {
85
+ "content": "<|quad_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151652": {
93
+ "content": "<|vision_start|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151653": {
101
+ "content": "<|vision_end|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151654": {
109
+ "content": "<|vision_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151655": {
117
+ "content": "<|image_pad|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "151656": {
125
+ "content": "<|video_pad|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ }
132
+ },
133
+ "additional_special_tokens": [
134
+ "<|im_start|>",
135
+ "<|im_end|>",
136
+ "<|object_ref_start|>",
137
+ "<|object_ref_end|>",
138
+ "<|box_start|>",
139
+ "<|box_end|>",
140
+ "<|quad_start|>",
141
+ "<|quad_end|>",
142
+ "<|vision_start|>",
143
+ "<|vision_end|>",
144
+ "<|vision_pad|>",
145
+ "<|image_pad|>",
146
+ "<|video_pad|>"
147
+ ],
148
+ "bos_token": "<s>",
149
+ "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 %}",
150
+ "clean_up_tokenization_spaces": false,
151
+ "eos_token": "<|im_end|>",
152
+ "errors": "replace",
153
+ "model_max_length": 2048,
154
+ "pad_token": "<|endoftext|>",
155
+ "padding_side": "left",
156
+ "processor_class": "Qwen2VLProcessor",
157
+ "split_special_tokens": false,
158
+ "tokenizer_class": "Qwen2Tokenizer",
159
+ "unk_token": "<unk>"
160
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
wandb/debug-internal.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c35a543da0f959f86d6266e4bda18d777bd0f9accd8e87c361a447fafe630de
3
+ size 10515729
wandb/debug.log ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Current SDK version is 0.17.5
2
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Configure stats pid to 424659
3
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Loading settings from /home/yangyaodong/.config/wandb/settings
4
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Loading settings from /aifs4su/yaodong/projects/hantao/dev_cham/align-anything/scripts/wandb/settings
5
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'api_key': '***REDACTED***'}
6
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-09-22 18:34:18,526 WARNING MainThread:424659 [wandb_setup.py:_flush():76] Could not find program at -m align_anything.trainers.tiv_to_t.ppo
8
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m align_anything.trainers.tiv_to_t.ppo'}
9
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Applying login settings: {}
10
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_init.py:_log_setup():529] Logging user logs to ../outputs/ppo_qwen2vl_10k_baseline/wandb/run-20240922_183418-smhpt648/logs/debug.log
11
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:_log_setup():530] Logging internal logs to ../outputs/ppo_qwen2vl_10k_baseline/wandb/run-20240922_183418-smhpt648/logs/debug-internal.log
12
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():569] calling init triggers
13
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():576] wandb.init called with sweep_config: {}
14
+ config: {'train_cfgs': {'ds_cfgs': 'ds_z3_config.json', 'epochs': 3, 'seed': 42, 'per_device_prompt_batch_size': 2, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'gradient_accumulation_steps': 1, 'actor_gradient_checkpointing': True, 'critic_gradient_checkpointing': True, 'actor_lr': 5e-07, 'actor_lr_scheduler_type': 'cosine', 'actor_lr_warmup_ratio': 0.03, 'actor_weight_decay': 0.0, 'critic_lr': 5e-07, 'critic_lr_scheduler_type': 'constant', 'critic_lr_warmup_ratio': 0.03, 'critic_weight_decay': 0.0, 'adam_betas': [0.9, 0.95], 'bf16': True, 'fp16': False, 'eval_strategy': 'epoch', 'eval_interval': 10, 'kl_coeff': 0.02, 'clip_range_ratio': 0.2, 'clip_range_score': 50.0, 'clip_range_value': 5.0, 'ptx_coeff': 16.0, 'gamma': 1.0, 'gae_lambda': 0.95, 'normalize_reward': False, 'update_iters': 1, 'freeze_mm_proj': False, 'freeze_vision_tower': True, 'freeze_language_model': False}, 'data_cfgs': {'train_datasets': '/aifs4su/yaodong/datasets/aaa_dataset/TV2T-preference/extracted', 'train_template': 'NExTQA_preference', 'train_size': None, 'train_split': 'train', 'train_subset': None, 'train_data_files': 'extracted_preference_10k_washed.json', 'train_optional_args': [], 'eval_datasets': None, 'eval_template': None, 'eval_size': None, 'eval_split': None, 'eval_subset': None, 'eval_data_files': None, 'eval_optional_args': [], 'ptx_datasets': '/aifs4su/yaodong/datasets/ShareGPT4Video/extracted', 'ptx_template': 'NExTQA', 'ptx_size': 25000, 'ptx_subset': None, 'ptx_split': 'train', 'ptx_data_files': 'extracted_panda.json', 'ptx_optional_args': []}, 'logger_cfgs': {'log_type': 'wandb', 'log_project': 'align-anything', 'log_run_name': 'ppo', 'output_dir': '../outputs/ppo_qwen2vl_10k_baseline', 'cache_dir': None, 'save_interval': 300.0}, 'model_cfgs': {'actor_model_name_or_path': '/aifs4su/yaodong/models/Qwen2-VL-7B-Instruct', 'reward_model_name_or_path': '/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline', 'reward_critic_model_name_or_path': '/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline', 'trust_remote_code': True, 'model_max_length': 2048, 'temperature': 1.0, 'top_p': 1.0, 'repetition_penalty': 1.0}, 'special_tokens': None}
15
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():619] starting backend
16
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():623] setting up manager
17
+ 2024-09-22 18:34:18,529 INFO MainThread:424659 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-09-22 18:34:18,532 INFO MainThread:424659 [wandb_init.py:init():631] backend started and connected
19
+ 2024-09-22 18:34:18,535 INFO MainThread:424659 [wandb_init.py:init():720] updated telemetry
20
+ 2024-09-22 18:34:18,556 INFO MainThread:424659 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
21
+ 2024-09-22 18:34:19,037 INFO MainThread:424659 [wandb_run.py:_on_init():2435] communicating current version
22
+ 2024-09-22 18:34:19,230 INFO MainThread:424659 [wandb_run.py:_on_init():2444] got version response upgrade_message: "wandb version 0.18.1 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
23
+
24
+ 2024-09-22 18:34:19,230 INFO MainThread:424659 [wandb_init.py:init():804] starting run threads in backend
25
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_console_start():2413] atexit reg
26
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_redirect():2255] redirect: wrap_raw
27
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_redirect():2320] Wrapping output streams.
28
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_redirect():2345] Redirects installed.
29
+ 2024-09-22 18:34:25,441 INFO MainThread:424659 [wandb_init.py:init():847] run started, returning control to user process
30
+ 2024-09-23 11:15:07,137 INFO MainThread:424659 [wandb_run.py:_finish():2107] finishing run htlou/align-anything/smhpt648
31
+ 2024-09-23 11:15:07,139 INFO MainThread:424659 [wandb_run.py:_atexit_cleanup():2374] got exitcode: 0
32
+ 2024-09-23 11:15:07,156 INFO MainThread:424659 [wandb_run.py:_restore():2352] restore
33
+ 2024-09-23 11:15:07,156 INFO MainThread:424659 [wandb_run.py:_restore():2358] restore done
34
+ 2024-09-23 11:15:15,887 INFO MainThread:424659 [wandb_run.py:_footer_history_summary_info():4016] rendering history
35
+ 2024-09-23 11:15:15,888 INFO MainThread:424659 [wandb_run.py:_footer_history_summary_info():4048] rendering summary
36
+ 2024-09-23 11:15:15,897 INFO MainThread:424659 [wandb_run.py:_footer_sync_info():3975] logging synced files
wandb/run-20240922_183418-smhpt648/files/conda-environment.yaml ADDED
@@ -0,0 +1,513 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: hantao_new
2
+ channels:
3
+ - nvidia/label/cuda-12.1.0
4
+ - nvidia
5
+ - pytorch
6
+ - huggingface
7
+ - conda-forge
8
+ - defaults
9
+ dependencies:
10
+ - _libgcc_mutex=0.1=conda_forge
11
+ - _openmp_mutex=4.5=2_gnu
12
+ - aom=3.9.1=hac33072_0
13
+ - asttokens=2.4.1=pyhd8ed1ab_0
14
+ - blas=1.0=mkl
15
+ - brotli-python=1.1.0=py311hb755f60_1
16
+ - bzip2=1.0.8=h4bc722e_7
17
+ - ca-certificates=2024.8.30=hbcca054_0
18
+ - cairo=1.18.0=hebfffa5_3
19
+ - certifi=2024.8.30=pyhd8ed1ab_0
20
+ - cffi=1.16.0=py311hb3a22ac_0
21
+ - charset-normalizer=3.3.2=pyhd8ed1ab_0
22
+ - comm=0.2.2=pyhd8ed1ab_0
23
+ - cuda=12.1.0=0
24
+ - cuda-cccl=12.1.55=0
25
+ - cuda-command-line-tools=12.1.0=0
26
+ - cuda-compiler=12.1.0=0
27
+ - cuda-cudart=12.1.55=0
28
+ - cuda-cudart-dev=12.1.55=0
29
+ - cuda-cudart-static=12.1.55=0
30
+ - cuda-cuobjdump=12.1.55=0
31
+ - cuda-cupti=12.1.62=0
32
+ - cuda-cupti-static=12.1.62=0
33
+ - cuda-cuxxfilt=12.1.55=0
34
+ - cuda-demo-suite=12.1.55=0
35
+ - cuda-documentation=12.1.55=0
36
+ - cuda-driver-dev=12.1.55=0
37
+ - cuda-gdb=12.1.55=0
38
+ - cuda-libraries=12.1.0=0
39
+ - cuda-libraries-dev=12.1.0=0
40
+ - cuda-libraries-static=12.1.0=0
41
+ - cuda-nsight=12.1.55=0
42
+ - cuda-nsight-compute=12.1.0=0
43
+ - cuda-nvcc=12.1.66=0
44
+ - cuda-nvdisasm=12.1.55=0
45
+ - cuda-nvml-dev=12.1.55=0
46
+ - cuda-nvprof=12.1.55=0
47
+ - cuda-nvprune=12.1.55=0
48
+ - cuda-nvrtc=12.1.55=0
49
+ - cuda-nvrtc-dev=12.1.55=0
50
+ - cuda-nvrtc-static=12.1.55=0
51
+ - cuda-nvtx=12.1.66=0
52
+ - cuda-nvvp=12.1.55=0
53
+ - cuda-opencl=12.1.56=0
54
+ - cuda-opencl-dev=12.1.56=0
55
+ - cuda-profiler-api=12.1.55=0
56
+ - cuda-runtime=12.1.0=0
57
+ - cuda-sanitizer-api=12.1.55=0
58
+ - cuda-toolkit=12.1.0=0
59
+ - cuda-tools=12.1.0=0
60
+ - cuda-visual-tools=12.1.0=0
61
+ - dav1d=1.2.1=hd590300_0
62
+ - debugpy=1.8.2=py311h4332511_0
63
+ - decorator=5.1.1=pyhd8ed1ab_0
64
+ - exceptiongroup=1.2.2=pyhd8ed1ab_0
65
+ - executing=2.0.1=pyhd8ed1ab_0
66
+ - expat=2.6.2=h59595ed_0
67
+ - ffmpeg=7.0.1=gpl_h9be9148_104
68
+ - filelock=3.15.4=pyhd8ed1ab_0
69
+ - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
70
+ - font-ttf-inconsolata=3.000=h77eed37_0
71
+ - font-ttf-source-code-pro=2.038=h77eed37_0
72
+ - font-ttf-ubuntu=0.83=h77eed37_2
73
+ - fontconfig=2.14.2=h14ed4e7_0
74
+ - fonts-conda-ecosystem=1=0
75
+ - fonts-conda-forge=1=0
76
+ - freetype=2.12.1=h267a509_2
77
+ - fribidi=1.0.10=h36c2ea0_0
78
+ - gds-tools=1.6.0.25=0
79
+ - gettext=0.22.5=h59595ed_2
80
+ - gettext-tools=0.22.5=h59595ed_2
81
+ - git-lfs=3.5.1=ha770c72_0
82
+ - gmp=6.3.0=hac33072_2
83
+ - gmpy2=2.1.5=py311hc4f1f91_1
84
+ - gnutls=3.7.9=hb077bed_0
85
+ - graphite2=1.3.13=h59595ed_1003
86
+ - h2=4.1.0=pyhd8ed1ab_0
87
+ - harfbuzz=9.0.0=hda332d3_1
88
+ - hpack=4.0.0=pyh9f0ad1d_0
89
+ - hyperframe=6.0.1=pyhd8ed1ab_0
90
+ - icu=75.1=he02047a_0
91
+ - idna=3.7=pyhd8ed1ab_0
92
+ - importlib-metadata=8.2.0=pyha770c72_0
93
+ - importlib_metadata=8.2.0=hd8ed1ab_0
94
+ - intel-openmp=2022.0.1=h06a4308_3633
95
+ - ipykernel=6.29.5=pyh3099207_0
96
+ - ipython=8.26.0=pyh707e725_0
97
+ - jedi=0.19.1=pyhd8ed1ab_0
98
+ - jinja2=3.1.4=pyhd8ed1ab_0
99
+ - jupyter_client=8.6.2=pyhd8ed1ab_0
100
+ - jupyter_core=5.7.2=py311h38be061_0
101
+ - keyutils=1.6.1=h166bdaf_0
102
+ - krb5=1.21.3=h659f571_0
103
+ - lame=3.100=h166bdaf_1003
104
+ - lcms2=2.16=hb7c19ff_0
105
+ - ld_impl_linux-64=2.40=hf3520f5_7
106
+ - lerc=4.0.0=h27087fc_0
107
+ - libabseil=20240116.2=cxx17_he02047a_1
108
+ - libasprintf=0.22.5=h661eb56_2
109
+ - libasprintf-devel=0.22.5=h661eb56_2
110
+ - libass=0.17.1=h39113c1_2
111
+ - libblas=3.9.0=16_linux64_mkl
112
+ - libcblas=3.9.0=16_linux64_mkl
113
+ - libcublas=12.1.0.26=0
114
+ - libcublas-dev=12.1.0.26=0
115
+ - libcublas-static=12.1.0.26=0
116
+ - libcufft=11.0.2.4=0
117
+ - libcufft-dev=11.0.2.4=0
118
+ - libcufft-static=11.0.2.4=0
119
+ - libcufile=1.6.0.25=0
120
+ - libcufile-dev=1.6.0.25=0
121
+ - libcufile-static=1.6.0.25=0
122
+ - libcurand=10.3.2.56=0
123
+ - libcurand-dev=10.3.2.56=0
124
+ - libcurand-static=10.3.2.56=0
125
+ - libcusolver=11.4.4.55=0
126
+ - libcusolver-dev=11.4.4.55=0
127
+ - libcusolver-static=11.4.4.55=0
128
+ - libcusparse=12.0.2.55=0
129
+ - libcusparse-dev=12.0.2.55=0
130
+ - libcusparse-static=12.0.2.55=0
131
+ - libdeflate=1.20=hd590300_0
132
+ - libdrm=2.4.122=h4ab18f5_0
133
+ - libedit=3.1.20191231=he28a2e2_2
134
+ - libexpat=2.6.2=h59595ed_0
135
+ - libffi=3.4.2=h7f98852_5
136
+ - libgcc=14.1.0=h77fa898_1
137
+ - libgcc-ng=14.1.0=h69a702a_1
138
+ - libgettextpo=0.22.5=h59595ed_2
139
+ - libgettextpo-devel=0.22.5=h59595ed_2
140
+ - libglib=2.80.3=h8a4344b_1
141
+ - libgomp=14.1.0=h77fa898_1
142
+ - libhwloc=2.11.1=default_hecaa2ac_1000
143
+ - libiconv=1.17=hd590300_2
144
+ - libidn2=2.3.7=hd590300_0
145
+ - libjpeg-turbo=3.0.0=hd590300_1
146
+ - liblapack=3.9.0=16_linux64_mkl
147
+ - libnpp=12.0.2.50=0
148
+ - libnpp-dev=12.0.2.50=0
149
+ - libnpp-static=12.0.2.50=0
150
+ - libnsl=2.0.1=hd590300_0
151
+ - libnvjitlink=12.1.105=0
152
+ - libnvjitlink-dev=12.1.55=0
153
+ - libnvjpeg=12.1.0.39=0
154
+ - libnvjpeg-dev=12.1.0.39=0
155
+ - libnvjpeg-static=12.1.0.39=0
156
+ - libnvvm-samples=12.1.55=0
157
+ - libopenvino=2024.2.0=h2da1b83_1
158
+ - libopenvino-auto-batch-plugin=2024.2.0=hb045406_1
159
+ - libopenvino-auto-plugin=2024.2.0=hb045406_1
160
+ - libopenvino-hetero-plugin=2024.2.0=h5c03a75_1
161
+ - libopenvino-intel-cpu-plugin=2024.2.0=h2da1b83_1
162
+ - libopenvino-intel-gpu-plugin=2024.2.0=h2da1b83_1
163
+ - libopenvino-intel-npu-plugin=2024.2.0=he02047a_1
164
+ - libopenvino-ir-frontend=2024.2.0=h5c03a75_1
165
+ - libopenvino-onnx-frontend=2024.2.0=h07e8aee_1
166
+ - libopenvino-paddle-frontend=2024.2.0=h07e8aee_1
167
+ - libopenvino-pytorch-frontend=2024.2.0=he02047a_1
168
+ - libopenvino-tensorflow-frontend=2024.2.0=h39126c6_1
169
+ - libopenvino-tensorflow-lite-frontend=2024.2.0=he02047a_1
170
+ - libopus=1.3.1=h7f98852_1
171
+ - libpciaccess=0.18=hd590300_0
172
+ - libpng=1.6.43=h2797004_0
173
+ - libprotobuf=4.25.3=h08a7969_0
174
+ - libsodium=1.0.18=h36c2ea0_1
175
+ - libsqlite=3.46.0=hde9e2c9_0
176
+ - libstdcxx=14.1.0=hc0a3c3a_1
177
+ - libstdcxx-ng=14.1.0=h4852527_1
178
+ - libtasn1=4.19.0=h166bdaf_0
179
+ - libtiff=4.6.0=h1dd3fc0_3
180
+ - libunistring=0.9.10=h7f98852_0
181
+ - libuuid=2.38.1=h0b41bf4_0
182
+ - libva=2.22.0=hb711507_0
183
+ - libvpx=1.14.1=hac33072_0
184
+ - libwebp-base=1.4.0=hd590300_0
185
+ - libxcb=1.16=hd590300_0
186
+ - libxcrypt=4.4.36=hd590300_1
187
+ - libxml2=2.12.7=he7c6b58_4
188
+ - libzlib=1.3.1=h4ab18f5_1
189
+ - llvm-openmp=15.0.7=h0cdce71_0
190
+ - markupsafe=2.1.5=py311h459d7ec_0
191
+ - matplotlib-inline=0.1.7=pyhd8ed1ab_0
192
+ - mkl=2022.1.0=hc2b9512_224
193
+ - mpc=1.3.1=hfe3b2da_0
194
+ - mpfr=4.2.1=h38ae2d0_2
195
+ - mpmath=1.3.0=pyhd8ed1ab_0
196
+ - ncurses=6.5=h59595ed_0
197
+ - nest-asyncio=1.6.0=pyhd8ed1ab_0
198
+ - nettle=3.9.1=h7ab15ed_0
199
+ - networkx=3.3=pyhd8ed1ab_1
200
+ - nsight-compute=2023.1.0.15=0
201
+ - ocl-icd=2.3.2=hd590300_1
202
+ - openh264=2.4.1=h59595ed_0
203
+ - openjpeg=2.5.2=h488ebb8_0
204
+ - openssl=3.3.2=hb9d3cd8_0
205
+ - p11-kit=0.24.1=hc5aa10d_0
206
+ - packaging=24.1=pyhd8ed1ab_0
207
+ - parso=0.8.4=pyhd8ed1ab_0
208
+ - pcre2=10.44=h0f59acf_0
209
+ - pexpect=4.9.0=pyhd8ed1ab_0
210
+ - pickleshare=0.7.5=py_1003
211
+ - pigz=2.8=h2797004_0
212
+ - pillow=10.4.0=py311h82a398c_0
213
+ - pip=24.0=pyhd8ed1ab_0
214
+ - pixman=0.43.2=h59595ed_0
215
+ - prompt-toolkit=3.0.47=pyha770c72_0
216
+ - psutil=6.0.0=py311h331c9d8_0
217
+ - pthread-stubs=0.4=h36c2ea0_1001
218
+ - ptyprocess=0.7.0=pyhd3deb0d_0
219
+ - pugixml=1.14=h59595ed_0
220
+ - pure_eval=0.2.3=pyhd8ed1ab_0
221
+ - pv=1.6.6=h470a237_0
222
+ - pycparser=2.22=pyhd8ed1ab_0
223
+ - pygments=2.18.0=pyhd8ed1ab_0
224
+ - pysocks=1.7.1=pyha2e5f31_6
225
+ - python=3.11.9=hb806964_0_cpython
226
+ - python_abi=3.11=4_cp311
227
+ - pytorch=2.4.0=py3.11_cuda12.1_cudnn9.1.0_0
228
+ - pytorch-cuda=12.1=ha16c6d3_5
229
+ - pytorch-mutex=1.0=cuda
230
+ - pyyaml=6.0.1=py311h459d7ec_1
231
+ - pyzmq=26.0.3=py311h08a0b41_0
232
+ - readline=8.2=h8228510_1
233
+ - requests=2.32.3=pyhd8ed1ab_0
234
+ - setuptools=71.0.4=pyhd8ed1ab_0
235
+ - six=1.16.0=pyh6c4a22f_0
236
+ - snappy=1.2.1=ha2e4443_0
237
+ - stack_data=0.6.2=pyhd8ed1ab_0
238
+ - svt-av1=2.1.2=hac33072_0
239
+ - sympy=1.13.0=pypyh2585a3b_103
240
+ - tbb=2021.12.0=h434a139_3
241
+ - tk=8.6.13=noxft_h4845f30_101
242
+ - torchaudio=2.4.0=py311_cu121
243
+ - torchtriton=3.0.0=py311
244
+ - tornado=6.4.1=py311h331c9d8_0
245
+ - traitlets=5.14.3=pyhd8ed1ab_0
246
+ - typing_extensions=4.12.2=pyha770c72_0
247
+ - urllib3=2.2.2=pyhd8ed1ab_1
248
+ - wayland=1.23.0=h5291e77_0
249
+ - wayland-protocols=1.36=hd8ed1ab_0
250
+ - wcwidth=0.2.13=pyhd8ed1ab_0
251
+ - wheel=0.43.0=pyhd8ed1ab_1
252
+ - x264=1!164.3095=h166bdaf_2
253
+ - x265=3.5=h924138e_3
254
+ - xorg-fixesproto=5.0=h7f98852_1002
255
+ - xorg-kbproto=1.0.7=h7f98852_1002
256
+ - xorg-libice=1.1.1=hd590300_0
257
+ - xorg-libsm=1.2.4=h7391055_0
258
+ - xorg-libx11=1.8.9=hb711507_1
259
+ - xorg-libxau=1.0.11=hd590300_0
260
+ - xorg-libxdmcp=1.1.3=h7f98852_0
261
+ - xorg-libxext=1.3.4=h0b41bf4_2
262
+ - xorg-libxfixes=5.0.3=h7f98852_1004
263
+ - xorg-libxrender=0.9.11=hd590300_0
264
+ - xorg-renderproto=0.11.1=h7f98852_1002
265
+ - xorg-xextproto=7.3.0=h0b41bf4_1003
266
+ - xorg-xproto=7.0.31=h7f98852_1007
267
+ - xz=5.2.6=h166bdaf_0
268
+ - yaml=0.2.5=h7f98852_2
269
+ - zeromq=4.3.5=h75354e8_4
270
+ - zipp=3.19.2=pyhd8ed1ab_0
271
+ - zlib=1.3.1=h4ab18f5_1
272
+ - zstandard=0.23.0=py311h5cd10c7_0
273
+ - zstd=1.5.6=ha6fb4c9_0
274
+ - pip:
275
+ - about-time==4.2.1
276
+ - absl-py==2.1.0
277
+ - accelerate==0.33.0
278
+ - aiofiles==23.2.1
279
+ - aiohttp==3.9.5
280
+ - aiohttp-retry==2.8.3
281
+ - aiosignal==1.3.1
282
+ - align-anything==0.0.1.dev0
283
+ - alive-progress==3.1.5
284
+ - amqp==5.2.0
285
+ - annotated-types==0.7.0
286
+ - antlr4-python3-runtime==4.9.3
287
+ - anyio==4.4.0
288
+ - appdirs==1.4.4
289
+ - asyncssh==2.16.0
290
+ - atpublic==5.0
291
+ - attrs==23.2.0
292
+ - audioread==3.0.1
293
+ - av==13.0.0
294
+ - backoff==2.2.1
295
+ - billiard==4.2.0
296
+ - boto3==1.35.9
297
+ - botocore==1.35.9
298
+ - cachetools==5.4.0
299
+ - celery==5.4.0
300
+ - cfgv==3.4.0
301
+ - click==8.1.7
302
+ - click-didyoumean==0.3.1
303
+ - click-plugins==1.1.1
304
+ - click-repl==0.3.0
305
+ - cloudpickle==3.0.0
306
+ - cmake==3.30.1
307
+ - colorama==0.4.6
308
+ - commonmark==0.9.1
309
+ - configobj==5.0.8
310
+ - contourpy==1.2.1
311
+ - cryptography==43.0.0
312
+ - cycler==0.12.1
313
+ - dacite==1.6.0
314
+ - dagshub==0.3.35
315
+ - dagshub-annotation-converter==0.1.0
316
+ - dataclasses-json==0.6.7
317
+ - datasets==2.20.0
318
+ - deepspeed==0.14.4
319
+ - deprecated==1.2.14
320
+ - dictdiffer==0.9.0
321
+ - diffusers==0.29.2
322
+ - dill==0.3.8
323
+ - diskcache==5.6.3
324
+ - distlib==0.3.8
325
+ - distro==1.9.0
326
+ - dnspython==2.6.1
327
+ - docker-pycreds==0.4.0
328
+ - dpath==2.2.0
329
+ - dulwich==0.22.1
330
+ - dvc==3.55.1
331
+ - dvc-data==3.16.5
332
+ - dvc-http==2.32.0
333
+ - dvc-objects==5.1.0
334
+ - dvc-render==1.0.2
335
+ - dvc-studio-client==0.21.0
336
+ - dvc-task==0.4.0
337
+ - email-validator==2.2.0
338
+ - entrypoints==0.4
339
+ - fastapi==0.111.1
340
+ - fastapi-cli==0.0.4
341
+ - ffmpy==0.3.3
342
+ - flatten-dict==0.4.2
343
+ - flufl-lock==8.1.0
344
+ - fonttools==4.53.1
345
+ - frozenlist==1.4.1
346
+ - fsspec==2024.5.0
347
+ - funcy==2.0
348
+ - fusepy==3.0.1
349
+ - gitdb==4.0.11
350
+ - gitpython==3.1.43
351
+ - gql==3.5.0
352
+ - gradio==4.39.0
353
+ - gradio-client==1.1.1
354
+ - gradio-multimodalchatbot==0.0.1
355
+ - grandalf==0.8
356
+ - grapheme==0.6.0
357
+ - graphql-core==3.2.3
358
+ - grpcio==1.65.1
359
+ - gto==1.7.1
360
+ - h11==0.14.0
361
+ - hjson==3.1.0
362
+ - httpcore==0.16.3
363
+ - httptools==0.6.1
364
+ - httpx==0.23.3
365
+ - huggingface-hub==0.24.3
366
+ - hydra-core==1.3.2
367
+ - identify==2.6.0
368
+ - importlib-resources==6.4.0
369
+ - iniconfig==2.0.0
370
+ - interegular==0.3.3
371
+ - iterative-telemetry==0.0.8
372
+ - jmespath==1.0.1
373
+ - joblib==1.4.2
374
+ - jsonschema==4.23.0
375
+ - jsonschema-specifications==2023.12.1
376
+ - kiwisolver==1.4.5
377
+ - kombu==5.4.0
378
+ - lark==1.1.9
379
+ - lazy-loader==0.4
380
+ - librosa==0.10.2.post1
381
+ - llvmlite==0.43.0
382
+ - lm-format-enforcer==0.10.3
383
+ - lxml==5.3.0
384
+ - markdown==3.6
385
+ - markdown-it-py==3.0.0
386
+ - marshmallow==3.22.0
387
+ - matplotlib==3.9.1
388
+ - mdurl==0.1.2
389
+ - mmsg==0.1.dev14+gbd2b056.d20240803
390
+ - msgpack==1.0.8
391
+ - multidict==6.0.5
392
+ - multiprocess==0.70.16
393
+ - mypy-extensions==1.0.0
394
+ - ninja==1.11.1.1
395
+ - nodeenv==1.9.1
396
+ - numba==0.60.0
397
+ - numpy==1.26.4
398
+ - nvidia-cublas-cu12==12.1.3.1
399
+ - nvidia-cuda-cupti-cu12==12.1.105
400
+ - nvidia-cuda-nvrtc-cu12==12.1.105
401
+ - nvidia-cuda-runtime-cu12==12.1.105
402
+ - nvidia-cudnn-cu12==8.9.2.26
403
+ - nvidia-cufft-cu12==11.0.2.54
404
+ - nvidia-curand-cu12==10.3.2.106
405
+ - nvidia-cusolver-cu12==11.4.5.107
406
+ - nvidia-cusparse-cu12==12.1.0.106
407
+ - nvidia-ml-py==12.535.161
408
+ - nvidia-nccl-cu12==2.20.5
409
+ - nvidia-nvjitlink-cu12==12.5.82
410
+ - nvidia-nvtx-cu12==12.1.105
411
+ - nvitop==1.3.2
412
+ - omegaconf==2.3.0
413
+ - openai==1.37.1
414
+ - optree==0.12.1
415
+ - orjson==3.10.6
416
+ - outlines==0.0.47.dev37+g26e2934
417
+ - pandas==2.2.2
418
+ - pathspec==0.12.1
419
+ - pathvalidate==3.0.0
420
+ - peft==0.12.0
421
+ - platformdirs==3.11.0
422
+ - pluggy==1.5.0
423
+ - pooch==1.8.2
424
+ - pre-commit==3.8.0
425
+ - prometheus-client==0.20.0
426
+ - prometheus-fastapi-instrumentator==7.0.0
427
+ - protobuf==4.25.4
428
+ - py-cpuinfo==9.0.0
429
+ - pyairports==2.1.1
430
+ - pyarrow==17.0.0
431
+ - pyarrow-hotfix==0.6
432
+ - pycountry==24.6.1
433
+ - pydantic==2.8.2
434
+ - pydantic-core==2.20.1
435
+ - pydot==3.0.1
436
+ - pydub==0.25.1
437
+ - pygit2==1.15.1
438
+ - pygithub==2.4.0
439
+ - pygtrie==2.5.0
440
+ - pyjwt==2.9.0
441
+ - pynacl==1.5.0
442
+ - pyparsing==3.1.2
443
+ - pytest==8.3.2
444
+ - python-dateutil==2.9.0.post0
445
+ - python-dotenv==1.0.1
446
+ - python-multipart==0.0.9
447
+ - pytz==2024.1
448
+ - ranger-fm==1.9.3
449
+ - ray==2.34.0
450
+ - referencing==0.35.1
451
+ - regex==2024.7.24
452
+ - requests-toolbelt==1.0.0
453
+ - rfc3986==1.5.0
454
+ - rich==13.1.0
455
+ - rpds-py==0.19.1
456
+ - ruamel-yaml==0.18.6
457
+ - ruamel-yaml-clib==0.2.8
458
+ - ruff==0.5.5
459
+ - s3transfer==0.10.2
460
+ - safetensors==0.4.3
461
+ - scikit-learn==1.5.1
462
+ - scipy==1.14.0
463
+ - scmrepo==3.3.7
464
+ - semantic-version==2.10.0
465
+ - semver==3.0.2
466
+ - sentencepiece==0.2.0
467
+ - sentry-sdk==2.11.0
468
+ - setproctitle==1.3.3
469
+ - shellingham==1.5.4
470
+ - shortuuid==1.0.13
471
+ - shtab==1.7.1
472
+ - smmap==5.0.1
473
+ - sniffio==1.3.1
474
+ - soundfile==0.12.1
475
+ - soxr==0.4.0
476
+ - sqltrie==0.11.1
477
+ - starlette==0.37.2
478
+ - tabulate==0.9.0
479
+ - tenacity==8.2.3
480
+ - tensorboard==2.17.0
481
+ - tensorboard-data-server==0.7.2
482
+ - term-image==0.7.2
483
+ - termcolor==2.4.0
484
+ - threadpoolctl==3.5.0
485
+ - tiktoken==0.7.0
486
+ - tokenizers==0.19.1
487
+ - tomlkit==0.12.0
488
+ - torch==2.3.1
489
+ - torchvision==0.18.1
490
+ - tqdm==4.66.4
491
+ - transformers==4.44.0.dev0
492
+ - treelib==1.6.4
493
+ - triton==2.3.1
494
+ - typer==0.12.3
495
+ - typing-inspect==0.9.0
496
+ - tzdata==2024.1
497
+ - uvicorn==0.30.3
498
+ - uvloop==0.19.0
499
+ - vine==5.1.0
500
+ - virtualenv==20.26.3
501
+ - vllm==0.5.3.post1
502
+ - vllm-flash-attn==2.5.9.post1
503
+ - voluptuous==0.15.2
504
+ - wandb==0.17.5
505
+ - watchfiles==0.22.0
506
+ - websockets==11.0.3
507
+ - werkzeug==3.0.3
508
+ - wrapt==1.16.0
509
+ - xformers==0.0.27
510
+ - xxhash==3.4.1
511
+ - yarl==1.9.4
512
+ - zc-lockfile==3.0.post1
513
+ prefix: /aifs4su/yaodong/miniconda3/envs/hantao_new
wandb/run-20240922_183418-smhpt648/files/config.yaml ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ train_cfgs:
4
+ desc: null
5
+ value:
6
+ ds_cfgs: ds_z3_config.json
7
+ epochs: 3
8
+ seed: 42
9
+ per_device_prompt_batch_size: 2
10
+ per_device_train_batch_size: 2
11
+ per_device_eval_batch_size: 2
12
+ gradient_accumulation_steps: 1
13
+ actor_gradient_checkpointing: true
14
+ critic_gradient_checkpointing: true
15
+ actor_lr: 5.0e-07
16
+ actor_lr_scheduler_type: cosine
17
+ actor_lr_warmup_ratio: 0.03
18
+ actor_weight_decay: 0.0
19
+ critic_lr: 5.0e-07
20
+ critic_lr_scheduler_type: constant
21
+ critic_lr_warmup_ratio: 0.03
22
+ critic_weight_decay: 0.0
23
+ adam_betas:
24
+ - 0.9
25
+ - 0.95
26
+ bf16: true
27
+ fp16: false
28
+ eval_strategy: epoch
29
+ eval_interval: 10
30
+ kl_coeff: 0.02
31
+ clip_range_ratio: 0.2
32
+ clip_range_score: 50.0
33
+ clip_range_value: 5.0
34
+ ptx_coeff: 16.0
35
+ gamma: 1.0
36
+ gae_lambda: 0.95
37
+ normalize_reward: false
38
+ update_iters: 1
39
+ freeze_mm_proj: false
40
+ freeze_vision_tower: true
41
+ freeze_language_model: false
42
+ data_cfgs:
43
+ desc: null
44
+ value:
45
+ train_datasets: /aifs4su/yaodong/datasets/aaa_dataset/TV2T-preference/extracted
46
+ train_template: NExTQA_preference
47
+ train_size: null
48
+ train_split: train
49
+ train_subset: null
50
+ train_data_files: extracted_preference_10k_washed.json
51
+ train_optional_args: []
52
+ eval_datasets: null
53
+ eval_template: null
54
+ eval_size: null
55
+ eval_split: null
56
+ eval_subset: null
57
+ eval_data_files: null
58
+ eval_optional_args: []
59
+ ptx_datasets: /aifs4su/yaodong/datasets/ShareGPT4Video/extracted
60
+ ptx_template: NExTQA
61
+ ptx_size: 25000
62
+ ptx_subset: null
63
+ ptx_split: train
64
+ ptx_data_files: extracted_panda.json
65
+ ptx_optional_args: []
66
+ logger_cfgs:
67
+ desc: null
68
+ value:
69
+ log_type: wandb
70
+ log_project: align-anything
71
+ log_run_name: ppo
72
+ output_dir: ../outputs/ppo_qwen2vl_10k_baseline
73
+ cache_dir: null
74
+ save_interval: 300.0
75
+ model_cfgs:
76
+ desc: null
77
+ value:
78
+ actor_model_name_or_path: /aifs4su/yaodong/models/Qwen2-VL-7B-Instruct
79
+ reward_model_name_or_path: /aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline
80
+ reward_critic_model_name_or_path: /aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline
81
+ trust_remote_code: true
82
+ model_max_length: 2048
83
+ temperature: 1.0
84
+ top_p: 1.0
85
+ repetition_penalty: 1.0
86
+ special_tokens:
87
+ desc: null
88
+ value: null
89
+ _wandb:
90
+ desc: null
91
+ value:
92
+ python_version: 3.11.9
93
+ cli_version: 0.17.5
94
+ framework: huggingface
95
+ huggingface_version: 4.45.0.dev0
96
+ is_jupyter_run: false
97
+ is_kaggle_kernel: false
98
+ start_time: 1727001258
99
+ t:
100
+ 1:
101
+ - 1
102
+ - 5
103
+ - 11
104
+ - 41
105
+ - 49
106
+ - 51
107
+ - 53
108
+ - 55
109
+ - 71
110
+ - 83
111
+ - 98
112
+ - 105
113
+ 2:
114
+ - 1
115
+ - 5
116
+ - 11
117
+ - 41
118
+ - 49
119
+ - 51
120
+ - 53
121
+ - 55
122
+ - 71
123
+ - 83
124
+ - 98
125
+ - 105
126
+ 3:
127
+ - 2
128
+ - 13
129
+ - 16
130
+ - 23
131
+ - 61
132
+ 4: 3.11.9
133
+ 5: 0.17.5
134
+ 6: 4.45.0.dev0
135
+ 8:
136
+ - 5
137
+ 13: linux-x86_64
wandb/run-20240922_183418-smhpt648/files/output.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20240922_183418-smhpt648/files/requirements.txt ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Brotli==1.1.0
2
+ GitPython==3.1.43
3
+ Jinja2==3.1.4
4
+ Markdown==3.6
5
+ MarkupSafe==2.1.5
6
+ PySocks==1.7.1
7
+ PyYAML==6.0.1
8
+ Pygments==2.18.0
9
+ Werkzeug==3.0.3
10
+ about-time==4.2.1
11
+ absl-py==2.1.0
12
+ accelerate==0.34.0
13
+ aiofiles==23.2.1
14
+ aiohttp-retry==2.8.3
15
+ aiohttp==3.9.5
16
+ aiosignal==1.3.1
17
+ align-anything==0.0.1.dev0
18
+ align-anything==0.0.1.dev0
19
+ alive-progress==3.1.5
20
+ amqp==5.2.0
21
+ annotated-types==0.7.0
22
+ antlr4-python3-runtime==4.9.3
23
+ anyio==4.4.0
24
+ appdirs==1.4.4
25
+ asttokens==2.4.1
26
+ asyncssh==2.16.0
27
+ atpublic==5.0
28
+ attrs==23.2.0
29
+ audioread==3.0.1
30
+ autocommand==2.2.2
31
+ backoff==2.2.1
32
+ backports.tarfile==1.2.0
33
+ billiard==4.2.0
34
+ boto3==1.35.9
35
+ botocore==1.35.9
36
+ cachetools==5.4.0
37
+ celery==5.4.0
38
+ certifi==2024.7.4
39
+ cffi==1.16.0
40
+ cfgv==3.4.0
41
+ charset-normalizer==3.3.2
42
+ click-didyoumean==0.3.1
43
+ click-plugins==1.1.1
44
+ click-repl==0.3.0
45
+ click==8.1.7
46
+ cloudpickle==3.0.0
47
+ cmake==3.30.1
48
+ colorama==0.4.6
49
+ comm==0.2.2
50
+ commonmark==0.9.1
51
+ configobj==5.0.8
52
+ contourpy==1.2.1
53
+ cryptography==43.0.0
54
+ cycler==0.12.1
55
+ dacite==1.6.0
56
+ dagshub-annotation-converter==0.1.0
57
+ dagshub==0.3.35
58
+ dataclasses-json==0.6.7
59
+ datasets==2.20.0
60
+ debugpy==1.8.2
61
+ decorator==4.4.2
62
+ deepspeed==0.14.4
63
+ dictdiffer==0.9.0
64
+ diffusers==0.29.2
65
+ dill==0.3.8
66
+ diskcache==5.6.3
67
+ distlib==0.3.8
68
+ distro==1.9.0
69
+ dnspython==2.6.1
70
+ docker-pycreds==0.4.0
71
+ docstring_parser==0.16
72
+ dpath==2.2.0
73
+ dulwich==0.22.1
74
+ dvc-data==3.16.5
75
+ dvc-http==2.32.0
76
+ dvc-objects==5.1.0
77
+ dvc-render==1.0.2
78
+ dvc-studio-client==0.21.0
79
+ dvc-task==0.4.0
80
+ dvc==3.55.1
81
+ einops==0.8.0
82
+ email_validator==2.2.0
83
+ entrypoints==0.4
84
+ exceptiongroup==1.2.2
85
+ executing==2.0.1
86
+ fastapi-cli==0.0.4
87
+ fastapi==0.111.1
88
+ ffmpy==0.3.3
89
+ filelock==3.15.4
90
+ fire==0.6.0
91
+ flatten-dict==0.4.2
92
+ flufl.lock==8.1.0
93
+ fonttools==4.53.1
94
+ frozenlist==1.4.1
95
+ fsspec==2024.5.0
96
+ funcy==2.0
97
+ fusepy==3.0.1
98
+ gitdb==4.0.11
99
+ gmpy2==2.1.5
100
+ gql==3.5.0
101
+ gradio==4.39.0
102
+ gradio_client==1.1.1
103
+ gradio_multimodalchatbot==0.0.1
104
+ grandalf==0.8
105
+ grapheme==0.6.0
106
+ graphql-core==3.2.3
107
+ grpcio==1.65.1
108
+ gto==1.7.1
109
+ h11==0.14.0
110
+ h2==4.1.0
111
+ hjson==3.1.0
112
+ hpack==4.0.0
113
+ httpcore==1.0.5
114
+ httptools==0.6.1
115
+ httpx==0.27.2
116
+ huggingface-hub==0.24.3
117
+ hydra-core==1.3.2
118
+ hyperframe==6.0.1
119
+ identify==2.6.0
120
+ idna==3.7
121
+ imageio-ffmpeg==0.5.1
122
+ imageio==2.35.1
123
+ importlib_metadata==8.0.0
124
+ importlib_metadata==8.2.0
125
+ importlib_resources==6.4.0
126
+ importlib_resources==6.4.0
127
+ inflect==7.3.1
128
+ iniconfig==2.0.0
129
+ interegular==0.3.3
130
+ ipykernel==6.29.5
131
+ ipython==8.26.0
132
+ iterative-telemetry==0.0.8
133
+ jaraco.context==5.3.0
134
+ jaraco.functools==4.0.1
135
+ jaraco.text==3.12.1
136
+ jedi==0.19.1
137
+ jmespath==1.0.1
138
+ joblib==1.4.2
139
+ jsonschema-specifications==2023.12.1
140
+ jsonschema==4.23.0
141
+ jupyter_client==8.6.2
142
+ jupyter_core==5.7.2
143
+ kiwisolver==1.4.5
144
+ kombu==5.4.0
145
+ lark==1.1.9
146
+ lazy_loader==0.4
147
+ librosa==0.10.2.post1
148
+ llamafactory==0.8.4.dev0
149
+ llamafactory==0.8.4.dev0
150
+ llvmlite==0.43.0
151
+ lm-format-enforcer==0.10.3
152
+ lxml==5.3.0
153
+ markdown-it-py==3.0.0
154
+ marshmallow==3.22.0
155
+ matplotlib-inline==0.1.7
156
+ matplotlib==3.9.1
157
+ mdurl==0.1.2
158
+ mmsg==0.1.dev14+gbd2b056.d20240803
159
+ more-itertools==10.3.0
160
+ moviepy==1.0.3
161
+ mpi4py==4.0.0
162
+ mpmath==1.3.0
163
+ msgpack==1.0.8
164
+ multidict==6.0.5
165
+ multiprocess==0.70.16
166
+ mypy-extensions==1.0.0
167
+ nest_asyncio==1.6.0
168
+ networkx==3.3
169
+ ninja==1.11.1.1
170
+ nodeenv==1.9.1
171
+ numba==0.60.0
172
+ numpy==1.26.4
173
+ nvidia-cublas-cu12==12.1.3.1
174
+ nvidia-cuda-cupti-cu12==12.1.105
175
+ nvidia-cuda-nvrtc-cu12==12.1.105
176
+ nvidia-cuda-runtime-cu12==12.1.105
177
+ nvidia-cudnn-cu12==8.9.2.26
178
+ nvidia-cufft-cu12==11.0.2.54
179
+ nvidia-curand-cu12==10.3.2.106
180
+ nvidia-cusolver-cu12==11.4.5.107
181
+ nvidia-cusparse-cu12==12.1.0.106
182
+ nvidia-ml-py==12.535.161
183
+ nvidia-nccl-cu12==2.20.5
184
+ nvidia-nvjitlink-cu12==12.5.82
185
+ nvidia-nvtx-cu12==12.1.105
186
+ nvitop==1.3.2
187
+ omegaconf==2.3.0
188
+ openai==1.37.1
189
+ optree==0.12.1
190
+ ordered-set==4.1.0
191
+ orjson==3.10.6
192
+ outlines==0.0.47.dev37+g26e2934
193
+ packaging==24.1
194
+ packaging==24.1
195
+ pandas==2.2.2
196
+ parso==0.8.4
197
+ pathspec==0.12.1
198
+ pathvalidate==3.0.0
199
+ peft==0.12.0
200
+ pexpect==4.9.0
201
+ pickleshare==0.7.5
202
+ pillow==10.4.0
203
+ pip==24.0
204
+ platformdirs==3.11.0
205
+ platformdirs==4.2.2
206
+ pluggy==1.5.0
207
+ pooch==1.8.2
208
+ pre-commit==3.8.0
209
+ proglog==0.1.10
210
+ prometheus-fastapi-instrumentator==7.0.0
211
+ prometheus_client==0.20.0
212
+ prompt_toolkit==3.0.47
213
+ protobuf==4.25.4
214
+ psutil==6.0.0
215
+ ptyprocess==0.7.0
216
+ pure_eval==0.2.3
217
+ py-cpuinfo==9.0.0
218
+ pyairports==2.1.1
219
+ pyarrow-hotfix==0.6
220
+ pyarrow==17.0.0
221
+ pyav==13.0.0
222
+ pycountry==24.6.1
223
+ pycparser==2.22
224
+ pydantic==2.8.2
225
+ pydantic_core==2.20.1
226
+ pydot==3.0.1
227
+ pydub==0.25.1
228
+ pygit2==1.15.1
229
+ pygtrie==2.5.0
230
+ pyparsing==3.1.2
231
+ pytest==8.3.2
232
+ python-dateutil==2.9.0
233
+ python-dateutil==2.9.0.post0
234
+ python-dotenv==1.0.1
235
+ python-multipart==0.0.9
236
+ pytz==2024.1
237
+ pyzmq==26.0.3
238
+ ranger-fm==1.9.3
239
+ ray==2.34.0
240
+ referencing==0.35.1
241
+ regex==2024.7.24
242
+ requests-toolbelt==1.0.0
243
+ requests==2.32.3
244
+ rfc3986==1.5.0
245
+ rich==13.1.0
246
+ rpds-py==0.19.1
247
+ ruamel.yaml.clib==0.2.8
248
+ ruamel.yaml==0.18.6
249
+ ruff==0.5.5
250
+ s3transfer==0.10.2
251
+ safetensors==0.4.3
252
+ scikit-learn==1.5.1
253
+ scipy==1.14.0
254
+ scmrepo==3.3.7
255
+ semantic-version==2.10.0
256
+ semver==3.0.2
257
+ sentencepiece==0.2.0
258
+ sentry-sdk==2.11.0
259
+ setproctitle==1.3.3
260
+ setuptools==71.0.4
261
+ shellingham==1.5.4
262
+ shortuuid==1.0.13
263
+ shtab==1.7.1
264
+ six==1.16.0
265
+ smmap==5.0.1
266
+ sniffio==1.3.1
267
+ soundfile==0.12.1
268
+ soxr==0.4.0
269
+ sqltrie==0.11.1
270
+ sse-starlette==2.1.3
271
+ stack-data==0.6.2
272
+ starlette==0.37.2
273
+ sympy==1.13.0
274
+ tabulate==0.9.0
275
+ tenacity==8.2.3
276
+ tensorboard-data-server==0.7.2
277
+ tensorboard==2.17.0
278
+ term-image==0.7.2
279
+ termcolor==2.4.0
280
+ threadpoolctl==3.5.0
281
+ tiktoken==0.7.0
282
+ tokenizers==0.19.1
283
+ tomli==2.0.1
284
+ tomlkit==0.12.0
285
+ torch==2.3.1
286
+ torch==2.4.0
287
+ torchaudio==2.4.0
288
+ torchvision==0.18.1
289
+ torchvision==0.19.0
290
+ tornado==6.4.1
291
+ tqdm==4.66.4
292
+ traitlets==5.14.3
293
+ transformers==4.45.0.dev0
294
+ treelib==1.6.4
295
+ triton==2.3.1
296
+ triton==3.0.0
297
+ trl==0.9.6
298
+ typeguard==4.3.0
299
+ typer==0.12.3
300
+ typing-inspect==0.9.0
301
+ typing_extensions==4.12.2
302
+ typing_extensions==4.12.2
303
+ tyro==0.8.10
304
+ tzdata==2024.1
305
+ urllib3==2.2.2
306
+ uvicorn==0.30.3
307
+ uvloop==0.19.0
308
+ vine==5.1.0
309
+ virtualenv==20.26.3
310
+ vllm-flash-attn==2.5.9.post1
311
+ vllm==0.5.3.post1
312
+ voluptuous==0.15.2
313
+ wandb==0.17.5
314
+ watchfiles==0.22.0
315
+ wcwidth==0.2.13
316
+ websockets==11.0.3
317
+ wheel==0.43.0
318
+ wheel==0.43.0
319
+ xformers==0.0.27
320
+ xxhash==3.4.1
321
+ yarl==1.9.4
322
+ zc.lockfile==3.0.post1
323
+ zipp==3.19.2
324
+ zipp==3.19.2
325
+ zstandard==0.23.0
wandb/run-20240922_183418-smhpt648/files/wandb-metadata.json ADDED
@@ -0,0 +1,1225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.15.0-1040-nvidia-x86_64-with-glibc2.35",
3
+ "python": "3.11.9",
4
+ "heartbeatAt": "2024-09-22T10:34:19.363341",
5
+ "startedAt": "2024-09-22T10:34:18.518843",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [
9
+ "--local_rank=0",
10
+ "--actor_model_name_or_path",
11
+ "/aifs4su/yaodong/models/Qwen2-VL-7B-Instruct",
12
+ "--reward_model_name_or_path",
13
+ "/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline",
14
+ "--reward_critic_model_name_or_path",
15
+ "/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline",
16
+ "--train_datasets",
17
+ "/aifs4su/yaodong/datasets/aaa_dataset/TV2T-preference/extracted",
18
+ "--train_template",
19
+ "NExTQA_preference",
20
+ "--train_data_files",
21
+ "extracted_preference_10k_washed.json",
22
+ "--train_split",
23
+ "train",
24
+ "--ptx_datasets",
25
+ "/aifs4su/yaodong/datasets/ShareGPT4Video/extracted",
26
+ "--ptx_data_files",
27
+ "extracted_panda.json",
28
+ "--ptx_template",
29
+ "NExTQA",
30
+ "--ptx_split",
31
+ "train",
32
+ "--output_dir",
33
+ "../outputs/ppo_qwen2vl_10k_baseline",
34
+ "--ddp_timeout",
35
+ "18000000000",
36
+ "--save_interval",
37
+ "300"
38
+ ],
39
+ "state": "running",
40
+ "program": "-m align_anything.trainers.tiv_to_t.ppo",
41
+ "codePathLocal": null,
42
+ "git": {
43
+ "remote": "git@github.com-hantao:htlou/align-anything.git",
44
+ "commit": "9eff99b0ee34f7265b8a2e1824650634c898f654"
45
+ },
46
+ "email": "2200017789@stu.pku.edu.cn",
47
+ "root": "/aifs4su/yaodong/projects/hantao/dev_cham/align-anything",
48
+ "host": "dgx-083",
49
+ "username": "yangyaodong",
50
+ "executable": "/aifs4su/yaodong/miniconda3/envs/hantao_tiv/bin/python3.11",
51
+ "cpu_count": 112,
52
+ "cpu_count_logical": 224,
53
+ "cpu_freq": {
54
+ "current": 2083.933607142857,
55
+ "min": 800.0,
56
+ "max": 3800.0
57
+ },
58
+ "cpu_freq_per_core": [
59
+ {
60
+ "current": 2000.0,
61
+ "min": 800.0,
62
+ "max": 3800.0
63
+ },
64
+ {
65
+ "current": 2000.0,
66
+ "min": 800.0,
67
+ "max": 3800.0
68
+ },
69
+ {
70
+ "current": 2000.0,
71
+ "min": 800.0,
72
+ "max": 3800.0
73
+ },
74
+ {
75
+ "current": 2000.0,
76
+ "min": 800.0,
77
+ "max": 3800.0
78
+ },
79
+ {
80
+ "current": 2000.0,
81
+ "min": 800.0,
82
+ "max": 3800.0
83
+ },
84
+ {
85
+ "current": 2000.0,
86
+ "min": 800.0,
87
+ "max": 3800.0
88
+ },
89
+ {
90
+ "current": 2000.0,
91
+ "min": 800.0,
92
+ "max": 3800.0
93
+ },
94
+ {
95
+ "current": 2000.0,
96
+ "min": 800.0,
97
+ "max": 3800.0
98
+ },
99
+ {
100
+ "current": 2000.0,
101
+ "min": 800.0,
102
+ "max": 3800.0
103
+ },
104
+ {
105
+ "current": 2000.0,
106
+ "min": 800.0,
107
+ "max": 3800.0
108
+ },
109
+ {
110
+ "current": 2000.0,
111
+ "min": 800.0,
112
+ "max": 3800.0
113
+ },
114
+ {
115
+ "current": 2000.0,
116
+ "min": 800.0,
117
+ "max": 3800.0
118
+ },
119
+ {
120
+ "current": 2000.0,
121
+ "min": 800.0,
122
+ "max": 3800.0
123
+ },
124
+ {
125
+ "current": 2000.0,
126
+ "min": 800.0,
127
+ "max": 3800.0
128
+ },
129
+ {
130
+ "current": 2000.0,
131
+ "min": 800.0,
132
+ "max": 3800.0
133
+ },
134
+ {
135
+ "current": 3799.788,
136
+ "min": 800.0,
137
+ "max": 3800.0
138
+ },
139
+ {
140
+ "current": 3800.0,
141
+ "min": 800.0,
142
+ "max": 3800.0
143
+ },
144
+ {
145
+ "current": 2000.0,
146
+ "min": 800.0,
147
+ "max": 3800.0
148
+ },
149
+ {
150
+ "current": 2000.0,
151
+ "min": 800.0,
152
+ "max": 3800.0
153
+ },
154
+ {
155
+ "current": 2000.0,
156
+ "min": 800.0,
157
+ "max": 3800.0
158
+ },
159
+ {
160
+ "current": 2000.0,
161
+ "min": 800.0,
162
+ "max": 3800.0
163
+ },
164
+ {
165
+ "current": 2000.0,
166
+ "min": 800.0,
167
+ "max": 3800.0
168
+ },
169
+ {
170
+ "current": 2000.0,
171
+ "min": 800.0,
172
+ "max": 3800.0
173
+ },
174
+ {
175
+ "current": 2000.0,
176
+ "min": 800.0,
177
+ "max": 3800.0
178
+ },
179
+ {
180
+ "current": 2000.0,
181
+ "min": 800.0,
182
+ "max": 3800.0
183
+ },
184
+ {
185
+ "current": 2000.0,
186
+ "min": 800.0,
187
+ "max": 3800.0
188
+ },
189
+ {
190
+ "current": 2000.0,
191
+ "min": 800.0,
192
+ "max": 3800.0
193
+ },
194
+ {
195
+ "current": 2000.0,
196
+ "min": 800.0,
197
+ "max": 3800.0
198
+ },
199
+ {
200
+ "current": 2000.0,
201
+ "min": 800.0,
202
+ "max": 3800.0
203
+ },
204
+ {
205
+ "current": 2000.0,
206
+ "min": 800.0,
207
+ "max": 3800.0
208
+ },
209
+ {
210
+ "current": 2000.0,
211
+ "min": 800.0,
212
+ "max": 3800.0
213
+ },
214
+ {
215
+ "current": 2000.0,
216
+ "min": 800.0,
217
+ "max": 3800.0
218
+ },
219
+ {
220
+ "current": 2000.0,
221
+ "min": 800.0,
222
+ "max": 3800.0
223
+ },
224
+ {
225
+ "current": 2000.0,
226
+ "min": 800.0,
227
+ "max": 3800.0
228
+ },
229
+ {
230
+ "current": 2000.0,
231
+ "min": 800.0,
232
+ "max": 3800.0
233
+ },
234
+ {
235
+ "current": 2000.0,
236
+ "min": 800.0,
237
+ "max": 3800.0
238
+ },
239
+ {
240
+ "current": 2000.0,
241
+ "min": 800.0,
242
+ "max": 3800.0
243
+ },
244
+ {
245
+ "current": 2000.0,
246
+ "min": 800.0,
247
+ "max": 3800.0
248
+ },
249
+ {
250
+ "current": 2000.0,
251
+ "min": 800.0,
252
+ "max": 3800.0
253
+ },
254
+ {
255
+ "current": 2000.0,
256
+ "min": 800.0,
257
+ "max": 3800.0
258
+ },
259
+ {
260
+ "current": 2000.0,
261
+ "min": 800.0,
262
+ "max": 3800.0
263
+ },
264
+ {
265
+ "current": 2000.0,
266
+ "min": 800.0,
267
+ "max": 3800.0
268
+ },
269
+ {
270
+ "current": 2000.0,
271
+ "min": 800.0,
272
+ "max": 3800.0
273
+ },
274
+ {
275
+ "current": 2000.0,
276
+ "min": 800.0,
277
+ "max": 3800.0
278
+ },
279
+ {
280
+ "current": 2000.0,
281
+ "min": 800.0,
282
+ "max": 3800.0
283
+ },
284
+ {
285
+ "current": 2000.0,
286
+ "min": 800.0,
287
+ "max": 3800.0
288
+ },
289
+ {
290
+ "current": 2000.0,
291
+ "min": 800.0,
292
+ "max": 3800.0
293
+ },
294
+ {
295
+ "current": 2000.0,
296
+ "min": 800.0,
297
+ "max": 3800.0
298
+ },
299
+ {
300
+ "current": 2000.0,
301
+ "min": 800.0,
302
+ "max": 3800.0
303
+ },
304
+ {
305
+ "current": 2000.0,
306
+ "min": 800.0,
307
+ "max": 3800.0
308
+ },
309
+ {
310
+ "current": 3800.0,
311
+ "min": 800.0,
312
+ "max": 3800.0
313
+ },
314
+ {
315
+ "current": 2000.0,
316
+ "min": 800.0,
317
+ "max": 3800.0
318
+ },
319
+ {
320
+ "current": 2000.0,
321
+ "min": 800.0,
322
+ "max": 3800.0
323
+ },
324
+ {
325
+ "current": 2000.0,
326
+ "min": 800.0,
327
+ "max": 3800.0
328
+ },
329
+ {
330
+ "current": 2000.0,
331
+ "min": 800.0,
332
+ "max": 3800.0
333
+ },
334
+ {
335
+ "current": 2000.0,
336
+ "min": 800.0,
337
+ "max": 3800.0
338
+ },
339
+ {
340
+ "current": 2000.0,
341
+ "min": 800.0,
342
+ "max": 3800.0
343
+ },
344
+ {
345
+ "current": 3800.0,
346
+ "min": 800.0,
347
+ "max": 3800.0
348
+ },
349
+ {
350
+ "current": 3800.0,
351
+ "min": 800.0,
352
+ "max": 3800.0
353
+ },
354
+ {
355
+ "current": 3800.0,
356
+ "min": 800.0,
357
+ "max": 3800.0
358
+ },
359
+ {
360
+ "current": 2000.0,
361
+ "min": 800.0,
362
+ "max": 3800.0
363
+ },
364
+ {
365
+ "current": 2000.0,
366
+ "min": 800.0,
367
+ "max": 3800.0
368
+ },
369
+ {
370
+ "current": 3800.0,
371
+ "min": 800.0,
372
+ "max": 3800.0
373
+ },
374
+ {
375
+ "current": 2000.0,
376
+ "min": 800.0,
377
+ "max": 3800.0
378
+ },
379
+ {
380
+ "current": 2000.0,
381
+ "min": 800.0,
382
+ "max": 3800.0
383
+ },
384
+ {
385
+ "current": 2000.0,
386
+ "min": 800.0,
387
+ "max": 3800.0
388
+ },
389
+ {
390
+ "current": 2000.0,
391
+ "min": 800.0,
392
+ "max": 3800.0
393
+ },
394
+ {
395
+ "current": 2000.0,
396
+ "min": 800.0,
397
+ "max": 3800.0
398
+ },
399
+ {
400
+ "current": 2000.0,
401
+ "min": 800.0,
402
+ "max": 3800.0
403
+ },
404
+ {
405
+ "current": 2000.0,
406
+ "min": 800.0,
407
+ "max": 3800.0
408
+ },
409
+ {
410
+ "current": 2000.0,
411
+ "min": 800.0,
412
+ "max": 3800.0
413
+ },
414
+ {
415
+ "current": 2000.0,
416
+ "min": 800.0,
417
+ "max": 3800.0
418
+ },
419
+ {
420
+ "current": 2000.0,
421
+ "min": 800.0,
422
+ "max": 3800.0
423
+ },
424
+ {
425
+ "current": 2000.0,
426
+ "min": 800.0,
427
+ "max": 3800.0
428
+ },
429
+ {
430
+ "current": 2000.0,
431
+ "min": 800.0,
432
+ "max": 3800.0
433
+ },
434
+ {
435
+ "current": 2000.0,
436
+ "min": 800.0,
437
+ "max": 3800.0
438
+ },
439
+ {
440
+ "current": 2000.0,
441
+ "min": 800.0,
442
+ "max": 3800.0
443
+ },
444
+ {
445
+ "current": 2000.0,
446
+ "min": 800.0,
447
+ "max": 3800.0
448
+ },
449
+ {
450
+ "current": 2000.0,
451
+ "min": 800.0,
452
+ "max": 3800.0
453
+ },
454
+ {
455
+ "current": 2000.0,
456
+ "min": 800.0,
457
+ "max": 3800.0
458
+ },
459
+ {
460
+ "current": 2000.0,
461
+ "min": 800.0,
462
+ "max": 3800.0
463
+ },
464
+ {
465
+ "current": 2000.0,
466
+ "min": 800.0,
467
+ "max": 3800.0
468
+ },
469
+ {
470
+ "current": 2000.0,
471
+ "min": 800.0,
472
+ "max": 3800.0
473
+ },
474
+ {
475
+ "current": 2000.0,
476
+ "min": 800.0,
477
+ "max": 3800.0
478
+ },
479
+ {
480
+ "current": 2000.0,
481
+ "min": 800.0,
482
+ "max": 3800.0
483
+ },
484
+ {
485
+ "current": 2000.0,
486
+ "min": 800.0,
487
+ "max": 3800.0
488
+ },
489
+ {
490
+ "current": 2000.0,
491
+ "min": 800.0,
492
+ "max": 3800.0
493
+ },
494
+ {
495
+ "current": 2000.0,
496
+ "min": 800.0,
497
+ "max": 3800.0
498
+ },
499
+ {
500
+ "current": 2000.0,
501
+ "min": 800.0,
502
+ "max": 3800.0
503
+ },
504
+ {
505
+ "current": 2000.0,
506
+ "min": 800.0,
507
+ "max": 3800.0
508
+ },
509
+ {
510
+ "current": 2000.0,
511
+ "min": 800.0,
512
+ "max": 3800.0
513
+ },
514
+ {
515
+ "current": 2000.0,
516
+ "min": 800.0,
517
+ "max": 3800.0
518
+ },
519
+ {
520
+ "current": 2000.0,
521
+ "min": 800.0,
522
+ "max": 3800.0
523
+ },
524
+ {
525
+ "current": 2000.0,
526
+ "min": 800.0,
527
+ "max": 3800.0
528
+ },
529
+ {
530
+ "current": 2000.0,
531
+ "min": 800.0,
532
+ "max": 3800.0
533
+ },
534
+ {
535
+ "current": 2000.0,
536
+ "min": 800.0,
537
+ "max": 3800.0
538
+ },
539
+ {
540
+ "current": 2000.0,
541
+ "min": 800.0,
542
+ "max": 3800.0
543
+ },
544
+ {
545
+ "current": 2000.0,
546
+ "min": 800.0,
547
+ "max": 3800.0
548
+ },
549
+ {
550
+ "current": 2000.0,
551
+ "min": 800.0,
552
+ "max": 3800.0
553
+ },
554
+ {
555
+ "current": 2000.0,
556
+ "min": 800.0,
557
+ "max": 3800.0
558
+ },
559
+ {
560
+ "current": 2000.0,
561
+ "min": 800.0,
562
+ "max": 3800.0
563
+ },
564
+ {
565
+ "current": 2000.0,
566
+ "min": 800.0,
567
+ "max": 3800.0
568
+ },
569
+ {
570
+ "current": 2000.0,
571
+ "min": 800.0,
572
+ "max": 3800.0
573
+ },
574
+ {
575
+ "current": 2000.0,
576
+ "min": 800.0,
577
+ "max": 3800.0
578
+ },
579
+ {
580
+ "current": 2000.0,
581
+ "min": 800.0,
582
+ "max": 3800.0
583
+ },
584
+ {
585
+ "current": 2000.0,
586
+ "min": 800.0,
587
+ "max": 3800.0
588
+ },
589
+ {
590
+ "current": 2000.0,
591
+ "min": 800.0,
592
+ "max": 3800.0
593
+ },
594
+ {
595
+ "current": 2000.0,
596
+ "min": 800.0,
597
+ "max": 3800.0
598
+ },
599
+ {
600
+ "current": 2000.0,
601
+ "min": 800.0,
602
+ "max": 3800.0
603
+ },
604
+ {
605
+ "current": 2000.0,
606
+ "min": 800.0,
607
+ "max": 3800.0
608
+ },
609
+ {
610
+ "current": 2000.0,
611
+ "min": 800.0,
612
+ "max": 3800.0
613
+ },
614
+ {
615
+ "current": 2000.0,
616
+ "min": 800.0,
617
+ "max": 3800.0
618
+ },
619
+ {
620
+ "current": 3800.0,
621
+ "min": 800.0,
622
+ "max": 3800.0
623
+ },
624
+ {
625
+ "current": 2000.0,
626
+ "min": 800.0,
627
+ "max": 3800.0
628
+ },
629
+ {
630
+ "current": 2000.0,
631
+ "min": 800.0,
632
+ "max": 3800.0
633
+ },
634
+ {
635
+ "current": 2000.0,
636
+ "min": 800.0,
637
+ "max": 3800.0
638
+ },
639
+ {
640
+ "current": 2000.0,
641
+ "min": 800.0,
642
+ "max": 3800.0
643
+ },
644
+ {
645
+ "current": 2000.0,
646
+ "min": 800.0,
647
+ "max": 3800.0
648
+ },
649
+ {
650
+ "current": 2000.0,
651
+ "min": 800.0,
652
+ "max": 3800.0
653
+ },
654
+ {
655
+ "current": 2000.0,
656
+ "min": 800.0,
657
+ "max": 3800.0
658
+ },
659
+ {
660
+ "current": 2000.0,
661
+ "min": 800.0,
662
+ "max": 3800.0
663
+ },
664
+ {
665
+ "current": 2000.0,
666
+ "min": 800.0,
667
+ "max": 3800.0
668
+ },
669
+ {
670
+ "current": 2000.0,
671
+ "min": 800.0,
672
+ "max": 3800.0
673
+ },
674
+ {
675
+ "current": 2000.0,
676
+ "min": 800.0,
677
+ "max": 3800.0
678
+ },
679
+ {
680
+ "current": 2000.0,
681
+ "min": 800.0,
682
+ "max": 3800.0
683
+ },
684
+ {
685
+ "current": 2000.0,
686
+ "min": 800.0,
687
+ "max": 3800.0
688
+ },
689
+ {
690
+ "current": 2000.0,
691
+ "min": 800.0,
692
+ "max": 3800.0
693
+ },
694
+ {
695
+ "current": 2000.0,
696
+ "min": 800.0,
697
+ "max": 3800.0
698
+ },
699
+ {
700
+ "current": 2000.0,
701
+ "min": 800.0,
702
+ "max": 3800.0
703
+ },
704
+ {
705
+ "current": 2000.0,
706
+ "min": 800.0,
707
+ "max": 3800.0
708
+ },
709
+ {
710
+ "current": 2000.0,
711
+ "min": 800.0,
712
+ "max": 3800.0
713
+ },
714
+ {
715
+ "current": 2000.0,
716
+ "min": 800.0,
717
+ "max": 3800.0
718
+ },
719
+ {
720
+ "current": 2000.0,
721
+ "min": 800.0,
722
+ "max": 3800.0
723
+ },
724
+ {
725
+ "current": 2000.0,
726
+ "min": 800.0,
727
+ "max": 3800.0
728
+ },
729
+ {
730
+ "current": 2000.0,
731
+ "min": 800.0,
732
+ "max": 3800.0
733
+ },
734
+ {
735
+ "current": 3797.347,
736
+ "min": 800.0,
737
+ "max": 3800.0
738
+ },
739
+ {
740
+ "current": 2000.0,
741
+ "min": 800.0,
742
+ "max": 3800.0
743
+ },
744
+ {
745
+ "current": 2000.0,
746
+ "min": 800.0,
747
+ "max": 3800.0
748
+ },
749
+ {
750
+ "current": 2000.0,
751
+ "min": 800.0,
752
+ "max": 3800.0
753
+ },
754
+ {
755
+ "current": 2000.0,
756
+ "min": 800.0,
757
+ "max": 3800.0
758
+ },
759
+ {
760
+ "current": 2000.0,
761
+ "min": 800.0,
762
+ "max": 3800.0
763
+ },
764
+ {
765
+ "current": 2000.0,
766
+ "min": 800.0,
767
+ "max": 3800.0
768
+ },
769
+ {
770
+ "current": 2000.0,
771
+ "min": 800.0,
772
+ "max": 3800.0
773
+ },
774
+ {
775
+ "current": 2000.0,
776
+ "min": 800.0,
777
+ "max": 3800.0
778
+ },
779
+ {
780
+ "current": 2000.0,
781
+ "min": 800.0,
782
+ "max": 3800.0
783
+ },
784
+ {
785
+ "current": 2000.0,
786
+ "min": 800.0,
787
+ "max": 3800.0
788
+ },
789
+ {
790
+ "current": 2000.0,
791
+ "min": 800.0,
792
+ "max": 3800.0
793
+ },
794
+ {
795
+ "current": 2000.0,
796
+ "min": 800.0,
797
+ "max": 3800.0
798
+ },
799
+ {
800
+ "current": 2000.0,
801
+ "min": 800.0,
802
+ "max": 3800.0
803
+ },
804
+ {
805
+ "current": 2000.0,
806
+ "min": 800.0,
807
+ "max": 3800.0
808
+ },
809
+ {
810
+ "current": 2000.0,
811
+ "min": 800.0,
812
+ "max": 3800.0
813
+ },
814
+ {
815
+ "current": 2000.0,
816
+ "min": 800.0,
817
+ "max": 3800.0
818
+ },
819
+ {
820
+ "current": 2000.0,
821
+ "min": 800.0,
822
+ "max": 3800.0
823
+ },
824
+ {
825
+ "current": 2000.0,
826
+ "min": 800.0,
827
+ "max": 3800.0
828
+ },
829
+ {
830
+ "current": 2000.0,
831
+ "min": 800.0,
832
+ "max": 3800.0
833
+ },
834
+ {
835
+ "current": 2000.0,
836
+ "min": 800.0,
837
+ "max": 3800.0
838
+ },
839
+ {
840
+ "current": 2000.0,
841
+ "min": 800.0,
842
+ "max": 3800.0
843
+ },
844
+ {
845
+ "current": 2000.0,
846
+ "min": 800.0,
847
+ "max": 3800.0
848
+ },
849
+ {
850
+ "current": 2000.0,
851
+ "min": 800.0,
852
+ "max": 3800.0
853
+ },
854
+ {
855
+ "current": 2000.0,
856
+ "min": 800.0,
857
+ "max": 3800.0
858
+ },
859
+ {
860
+ "current": 2000.0,
861
+ "min": 800.0,
862
+ "max": 3800.0
863
+ },
864
+ {
865
+ "current": 2000.0,
866
+ "min": 800.0,
867
+ "max": 3800.0
868
+ },
869
+ {
870
+ "current": 2000.0,
871
+ "min": 800.0,
872
+ "max": 3800.0
873
+ },
874
+ {
875
+ "current": 2000.0,
876
+ "min": 800.0,
877
+ "max": 3800.0
878
+ },
879
+ {
880
+ "current": 2000.0,
881
+ "min": 800.0,
882
+ "max": 3800.0
883
+ },
884
+ {
885
+ "current": 2000.0,
886
+ "min": 800.0,
887
+ "max": 3800.0
888
+ },
889
+ {
890
+ "current": 2000.0,
891
+ "min": 800.0,
892
+ "max": 3800.0
893
+ },
894
+ {
895
+ "current": 2000.0,
896
+ "min": 800.0,
897
+ "max": 3800.0
898
+ },
899
+ {
900
+ "current": 2000.0,
901
+ "min": 800.0,
902
+ "max": 3800.0
903
+ },
904
+ {
905
+ "current": 2000.0,
906
+ "min": 800.0,
907
+ "max": 3800.0
908
+ },
909
+ {
910
+ "current": 2000.0,
911
+ "min": 800.0,
912
+ "max": 3800.0
913
+ },
914
+ {
915
+ "current": 2000.0,
916
+ "min": 800.0,
917
+ "max": 3800.0
918
+ },
919
+ {
920
+ "current": 2000.0,
921
+ "min": 800.0,
922
+ "max": 3800.0
923
+ },
924
+ {
925
+ "current": 2000.0,
926
+ "min": 800.0,
927
+ "max": 3800.0
928
+ },
929
+ {
930
+ "current": 2000.0,
931
+ "min": 800.0,
932
+ "max": 3800.0
933
+ },
934
+ {
935
+ "current": 2000.0,
936
+ "min": 800.0,
937
+ "max": 3800.0
938
+ },
939
+ {
940
+ "current": 2000.0,
941
+ "min": 800.0,
942
+ "max": 3800.0
943
+ },
944
+ {
945
+ "current": 2000.0,
946
+ "min": 800.0,
947
+ "max": 3800.0
948
+ },
949
+ {
950
+ "current": 2000.0,
951
+ "min": 800.0,
952
+ "max": 3800.0
953
+ },
954
+ {
955
+ "current": 2000.0,
956
+ "min": 800.0,
957
+ "max": 3800.0
958
+ },
959
+ {
960
+ "current": 2000.0,
961
+ "min": 800.0,
962
+ "max": 3800.0
963
+ },
964
+ {
965
+ "current": 2000.0,
966
+ "min": 800.0,
967
+ "max": 3800.0
968
+ },
969
+ {
970
+ "current": 2000.0,
971
+ "min": 800.0,
972
+ "max": 3800.0
973
+ },
974
+ {
975
+ "current": 2000.0,
976
+ "min": 800.0,
977
+ "max": 3800.0
978
+ },
979
+ {
980
+ "current": 2000.0,
981
+ "min": 800.0,
982
+ "max": 3800.0
983
+ },
984
+ {
985
+ "current": 2000.0,
986
+ "min": 800.0,
987
+ "max": 3800.0
988
+ },
989
+ {
990
+ "current": 2000.0,
991
+ "min": 800.0,
992
+ "max": 3800.0
993
+ },
994
+ {
995
+ "current": 2000.0,
996
+ "min": 800.0,
997
+ "max": 3800.0
998
+ },
999
+ {
1000
+ "current": 2000.0,
1001
+ "min": 800.0,
1002
+ "max": 3800.0
1003
+ },
1004
+ {
1005
+ "current": 2000.0,
1006
+ "min": 800.0,
1007
+ "max": 3800.0
1008
+ },
1009
+ {
1010
+ "current": 2000.0,
1011
+ "min": 800.0,
1012
+ "max": 3800.0
1013
+ },
1014
+ {
1015
+ "current": 2000.0,
1016
+ "min": 800.0,
1017
+ "max": 3800.0
1018
+ },
1019
+ {
1020
+ "current": 2000.0,
1021
+ "min": 800.0,
1022
+ "max": 3800.0
1023
+ },
1024
+ {
1025
+ "current": 2000.0,
1026
+ "min": 800.0,
1027
+ "max": 3800.0
1028
+ },
1029
+ {
1030
+ "current": 2000.0,
1031
+ "min": 800.0,
1032
+ "max": 3800.0
1033
+ },
1034
+ {
1035
+ "current": 2000.0,
1036
+ "min": 800.0,
1037
+ "max": 3800.0
1038
+ },
1039
+ {
1040
+ "current": 2000.0,
1041
+ "min": 800.0,
1042
+ "max": 3800.0
1043
+ },
1044
+ {
1045
+ "current": 2000.0,
1046
+ "min": 800.0,
1047
+ "max": 3800.0
1048
+ },
1049
+ {
1050
+ "current": 2000.0,
1051
+ "min": 800.0,
1052
+ "max": 3800.0
1053
+ },
1054
+ {
1055
+ "current": 2000.0,
1056
+ "min": 800.0,
1057
+ "max": 3800.0
1058
+ },
1059
+ {
1060
+ "current": 2000.0,
1061
+ "min": 800.0,
1062
+ "max": 3800.0
1063
+ },
1064
+ {
1065
+ "current": 2000.0,
1066
+ "min": 800.0,
1067
+ "max": 3800.0
1068
+ },
1069
+ {
1070
+ "current": 2000.0,
1071
+ "min": 800.0,
1072
+ "max": 3800.0
1073
+ },
1074
+ {
1075
+ "current": 2000.0,
1076
+ "min": 800.0,
1077
+ "max": 3800.0
1078
+ },
1079
+ {
1080
+ "current": 2000.0,
1081
+ "min": 800.0,
1082
+ "max": 3800.0
1083
+ },
1084
+ {
1085
+ "current": 2000.0,
1086
+ "min": 800.0,
1087
+ "max": 3800.0
1088
+ },
1089
+ {
1090
+ "current": 2000.0,
1091
+ "min": 800.0,
1092
+ "max": 3800.0
1093
+ },
1094
+ {
1095
+ "current": 2000.0,
1096
+ "min": 800.0,
1097
+ "max": 3800.0
1098
+ },
1099
+ {
1100
+ "current": 2000.0,
1101
+ "min": 800.0,
1102
+ "max": 3800.0
1103
+ },
1104
+ {
1105
+ "current": 3800.0,
1106
+ "min": 800.0,
1107
+ "max": 3800.0
1108
+ },
1109
+ {
1110
+ "current": 2000.0,
1111
+ "min": 800.0,
1112
+ "max": 3800.0
1113
+ },
1114
+ {
1115
+ "current": 2000.0,
1116
+ "min": 800.0,
1117
+ "max": 3800.0
1118
+ },
1119
+ {
1120
+ "current": 2000.0,
1121
+ "min": 800.0,
1122
+ "max": 3800.0
1123
+ },
1124
+ {
1125
+ "current": 2000.0,
1126
+ "min": 800.0,
1127
+ "max": 3800.0
1128
+ },
1129
+ {
1130
+ "current": 2000.0,
1131
+ "min": 800.0,
1132
+ "max": 3800.0
1133
+ },
1134
+ {
1135
+ "current": 2000.0,
1136
+ "min": 800.0,
1137
+ "max": 3800.0
1138
+ },
1139
+ {
1140
+ "current": 2000.0,
1141
+ "min": 800.0,
1142
+ "max": 3800.0
1143
+ },
1144
+ {
1145
+ "current": 2000.0,
1146
+ "min": 800.0,
1147
+ "max": 3800.0
1148
+ },
1149
+ {
1150
+ "current": 2000.0,
1151
+ "min": 800.0,
1152
+ "max": 3800.0
1153
+ },
1154
+ {
1155
+ "current": 2000.0,
1156
+ "min": 800.0,
1157
+ "max": 3800.0
1158
+ },
1159
+ {
1160
+ "current": 2000.0,
1161
+ "min": 800.0,
1162
+ "max": 3800.0
1163
+ },
1164
+ {
1165
+ "current": 2000.0,
1166
+ "min": 800.0,
1167
+ "max": 3800.0
1168
+ },
1169
+ {
1170
+ "current": 2000.0,
1171
+ "min": 800.0,
1172
+ "max": 3800.0
1173
+ },
1174
+ {
1175
+ "current": 2000.0,
1176
+ "min": 800.0,
1177
+ "max": 3800.0
1178
+ }
1179
+ ],
1180
+ "disk": {
1181
+ "/": {
1182
+ "total": 1758.8549690246582,
1183
+ "used": 82.41014862060547
1184
+ }
1185
+ },
1186
+ "gpu": "NVIDIA H800",
1187
+ "gpu_count": 8,
1188
+ "gpu_devices": [
1189
+ {
1190
+ "name": "NVIDIA H800",
1191
+ "memory_total": 85520809984
1192
+ },
1193
+ {
1194
+ "name": "NVIDIA H800",
1195
+ "memory_total": 85520809984
1196
+ },
1197
+ {
1198
+ "name": "NVIDIA H800",
1199
+ "memory_total": 85520809984
1200
+ },
1201
+ {
1202
+ "name": "NVIDIA H800",
1203
+ "memory_total": 85520809984
1204
+ },
1205
+ {
1206
+ "name": "NVIDIA H800",
1207
+ "memory_total": 85520809984
1208
+ },
1209
+ {
1210
+ "name": "NVIDIA H800",
1211
+ "memory_total": 85520809984
1212
+ },
1213
+ {
1214
+ "name": "NVIDIA H800",
1215
+ "memory_total": 85520809984
1216
+ },
1217
+ {
1218
+ "name": "NVIDIA H800",
1219
+ "memory_total": 85520809984
1220
+ }
1221
+ ],
1222
+ "memory": {
1223
+ "total": 2015.5606079101562
1224
+ }
1225
+ }
wandb/run-20240922_183418-smhpt648/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/step": 908, "train/actor_loss": 0.16898608207702637, "train/reward_critic_loss": 0.09787850081920624, "train/reward": 2.7158203125, "train/reward_with_kl_penalty": 3.022871732711792, "train/reward_advantage": -0.16898608207702637, "train/reward_return": 3.46067476272583, "train/reward_value": 3.6296606063842773, "train/kl_divergence": -15.352579116821289, "train/actor_lr": 1.5858865979045955e-12, "train/reward_critic_lr": 5e-07, "train/mean_generated_length": 133.5, "train/max_generated_length": 538.0, "_timestamp": 1727061261.4216566, "train/ptx_loss": 1.941270112991333, "_runtime": 60002.88863348961, "_step": 908, "_wandb": {"runtime": 60048}}
wandb/run-20240922_183418-smhpt648/logs/debug-internal.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c35a543da0f959f86d6266e4bda18d777bd0f9accd8e87c361a447fafe630de
3
+ size 10515729
wandb/run-20240922_183418-smhpt648/logs/debug.log ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Current SDK version is 0.17.5
2
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Configure stats pid to 424659
3
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Loading settings from /home/yangyaodong/.config/wandb/settings
4
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Loading settings from /aifs4su/yaodong/projects/hantao/dev_cham/align-anything/scripts/wandb/settings
5
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'api_key': '***REDACTED***'}
6
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-09-22 18:34:18,526 WARNING MainThread:424659 [wandb_setup.py:_flush():76] Could not find program at -m align_anything.trainers.tiv_to_t.ppo
8
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m align_anything.trainers.tiv_to_t.ppo'}
9
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_setup.py:_flush():76] Applying login settings: {}
10
+ 2024-09-22 18:34:18,526 INFO MainThread:424659 [wandb_init.py:_log_setup():529] Logging user logs to ../outputs/ppo_qwen2vl_10k_baseline/wandb/run-20240922_183418-smhpt648/logs/debug.log
11
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:_log_setup():530] Logging internal logs to ../outputs/ppo_qwen2vl_10k_baseline/wandb/run-20240922_183418-smhpt648/logs/debug-internal.log
12
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():569] calling init triggers
13
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():576] wandb.init called with sweep_config: {}
14
+ config: {'train_cfgs': {'ds_cfgs': 'ds_z3_config.json', 'epochs': 3, 'seed': 42, 'per_device_prompt_batch_size': 2, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'gradient_accumulation_steps': 1, 'actor_gradient_checkpointing': True, 'critic_gradient_checkpointing': True, 'actor_lr': 5e-07, 'actor_lr_scheduler_type': 'cosine', 'actor_lr_warmup_ratio': 0.03, 'actor_weight_decay': 0.0, 'critic_lr': 5e-07, 'critic_lr_scheduler_type': 'constant', 'critic_lr_warmup_ratio': 0.03, 'critic_weight_decay': 0.0, 'adam_betas': [0.9, 0.95], 'bf16': True, 'fp16': False, 'eval_strategy': 'epoch', 'eval_interval': 10, 'kl_coeff': 0.02, 'clip_range_ratio': 0.2, 'clip_range_score': 50.0, 'clip_range_value': 5.0, 'ptx_coeff': 16.0, 'gamma': 1.0, 'gae_lambda': 0.95, 'normalize_reward': False, 'update_iters': 1, 'freeze_mm_proj': False, 'freeze_vision_tower': True, 'freeze_language_model': False}, 'data_cfgs': {'train_datasets': '/aifs4su/yaodong/datasets/aaa_dataset/TV2T-preference/extracted', 'train_template': 'NExTQA_preference', 'train_size': None, 'train_split': 'train', 'train_subset': None, 'train_data_files': 'extracted_preference_10k_washed.json', 'train_optional_args': [], 'eval_datasets': None, 'eval_template': None, 'eval_size': None, 'eval_split': None, 'eval_subset': None, 'eval_data_files': None, 'eval_optional_args': [], 'ptx_datasets': '/aifs4su/yaodong/datasets/ShareGPT4Video/extracted', 'ptx_template': 'NExTQA', 'ptx_size': 25000, 'ptx_subset': None, 'ptx_split': 'train', 'ptx_data_files': 'extracted_panda.json', 'ptx_optional_args': []}, 'logger_cfgs': {'log_type': 'wandb', 'log_project': 'align-anything', 'log_run_name': 'ppo', 'output_dir': '../outputs/ppo_qwen2vl_10k_baseline', 'cache_dir': None, 'save_interval': 300.0}, 'model_cfgs': {'actor_model_name_or_path': '/aifs4su/yaodong/models/Qwen2-VL-7B-Instruct', 'reward_model_name_or_path': '/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline', 'reward_critic_model_name_or_path': '/aifs4su/yaodong/projects/hantao/dev_cham/align-anything/outputs/rm_tiv2t_10k_baseline', 'trust_remote_code': True, 'model_max_length': 2048, 'temperature': 1.0, 'top_p': 1.0, 'repetition_penalty': 1.0}, 'special_tokens': None}
15
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():619] starting backend
16
+ 2024-09-22 18:34:18,527 INFO MainThread:424659 [wandb_init.py:init():623] setting up manager
17
+ 2024-09-22 18:34:18,529 INFO MainThread:424659 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-09-22 18:34:18,532 INFO MainThread:424659 [wandb_init.py:init():631] backend started and connected
19
+ 2024-09-22 18:34:18,535 INFO MainThread:424659 [wandb_init.py:init():720] updated telemetry
20
+ 2024-09-22 18:34:18,556 INFO MainThread:424659 [wandb_init.py:init():753] communicating run to backend with 90.0 second timeout
21
+ 2024-09-22 18:34:19,037 INFO MainThread:424659 [wandb_run.py:_on_init():2435] communicating current version
22
+ 2024-09-22 18:34:19,230 INFO MainThread:424659 [wandb_run.py:_on_init():2444] got version response upgrade_message: "wandb version 0.18.1 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
23
+
24
+ 2024-09-22 18:34:19,230 INFO MainThread:424659 [wandb_init.py:init():804] starting run threads in backend
25
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_console_start():2413] atexit reg
26
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_redirect():2255] redirect: wrap_raw
27
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_redirect():2320] Wrapping output streams.
28
+ 2024-09-22 18:34:25,437 INFO MainThread:424659 [wandb_run.py:_redirect():2345] Redirects installed.
29
+ 2024-09-22 18:34:25,441 INFO MainThread:424659 [wandb_init.py:init():847] run started, returning control to user process
30
+ 2024-09-23 11:15:07,137 INFO MainThread:424659 [wandb_run.py:_finish():2107] finishing run htlou/align-anything/smhpt648
31
+ 2024-09-23 11:15:07,139 INFO MainThread:424659 [wandb_run.py:_atexit_cleanup():2374] got exitcode: 0
32
+ 2024-09-23 11:15:07,156 INFO MainThread:424659 [wandb_run.py:_restore():2352] restore
33
+ 2024-09-23 11:15:07,156 INFO MainThread:424659 [wandb_run.py:_restore():2358] restore done
34
+ 2024-09-23 11:15:15,887 INFO MainThread:424659 [wandb_run.py:_footer_history_summary_info():4016] rendering history
35
+ 2024-09-23 11:15:15,888 INFO MainThread:424659 [wandb_run.py:_footer_history_summary_info():4048] rendering summary
36
+ 2024-09-23 11:15:15,897 INFO MainThread:424659 [wandb_run.py:_footer_sync_info():3975] logging synced files
wandb/run-20240922_183418-smhpt648/run-smhpt648.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac70e761dc02e329287de14a7c174a6ffcce1a974c96d75535bbee066e03245
3
+ size 18672381