ML Training

Submit a training job


curl -sS -X POST \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  https://computalot.com/api/v1/jobs \
  -d '{
    "type": "structured_runner",
    "runner_command": ["python", "train.py"],
    "payload": {"epochs": 100, "batch_size": 32},
    "project": "my-ml-project",
    "timeout_s": 7200,
    "requirements": {"profile": "gpu"}
  }'

Report progress


import json, sys
 
for epoch in range(100):
    loss = train_one_epoch()
    print(f"COMPUTALOT_PROGRESS:{json.dumps({'epoch': epoch, 'loss': loss})}")
    sys.stdout.flush()

Save artifacts


import os, torch
model_path = os.path.join(os.environ['COMPUTALOT_ARTIFACT_DIR'], 'model.pt')
torch.save(model.state_dict(), model_path)