File size: 1,729 Bytes
5fc8c9d |
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 |
# okto_version: "1.2"
PROJECT "ControlNestedExample"
DESCRIPTION "Demonstrates nested CONTROL blocks with advanced decision-making"
ENV {
accelerator: "gpu"
min_memory: "8GB"
precision: "fp16"
}
DATASET {
train: "examples/datasets/demo_train.jsonl"
validation: "examples/datasets/demo_train.jsonl"
format: "jsonl"
type: "chat"
}
MODEL {
name: "nested-control-model"
base: "oktoseek/base-mini"
device: "cuda"
}
TRAIN {
epochs: 10
batch_size: 32
learning_rate: 0.0001
optimizer: "adamw"
device: "cuda"
}
CONTROL {
on_step_end {
LOG loss
}
on_epoch_end {
IF loss > 2.0 {
SET LR = 0.00005
LOG "High loss detected, reducing learning rate"
WHEN gpu_usage > 90% {
SET batch_size = 16
LOG "Reducing batch size due to GPU pressure"
}
IF val_loss > 3.0 {
STOP_TRAINING
}
}
IF accuracy > 0.9 {
SAVE "best_model"
LOG "High accuracy reached"
}
EVERY 2 epochs {
SAVE "checkpoint_epoch_{epoch}"
}
}
validate_every: 200
IF epoch == 1 {
LOG "Warmup stage"
}
IF epoch > 5 AND accuracy < 0.6 {
SET LR = 0.00001
LOG "Model is stagnated, reducing learning rate"
}
IF epoch > 10 AND loss > 1.8 {
STOP_TRAINING
}
WHEN gpu_memory < 12GB {
SET batch_size = 16
}
EVERY 500 steps {
SAVE checkpoint
}
}
MONITOR {
metrics: ["loss", "val_loss", "accuracy", "gpu_usage", "ram_usage"]
notify_if {
loss > 2.0
gpu_usage > 90%
}
log_to: "logs/training.log"
}
EXPORT {
format: ["okm"]
path: "export/"
}
|