File size: 4,048 Bytes
342f304 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 1
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 5
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 0
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 2
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 7
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 6
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 3
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
SLURM_JOB_ID = 1038301
SLURM_JOB_NAME = nvr_elm_llm:train/NVILA-Lite-8B-quantumn-qa-train
RUN_NAME = NVILA-Lite-8B-quantumn-qa-train
OUTPUT_DIR = runs/train/NVILA-Lite-8B-quantumn-qa-train
NNODES = 8
NODES = pool0-02107 pool0-02117 pool0-02099 pool0-02196 pool0-02404 pool0-02496 pool0-02566 pool0-02669
NODE_RANK = 4
GPUS_PER_NODE = 8
MASTER_ADDR = pool0-02107
MASTER_PORT = 25001
GLOBAL_TRAIN_BATCH_SIZE = 2048
GRADIENT_ACCUMULATION_STEPS = 4
PER_DEVICE_TRAIN_BATCH_SIZE = 8
DEFAULT_LEARNING_RATE: 2e-5
|