Queue a forward operation

POST

https://api.fastino.ai

training

jobs

{job_id}

forward

curl -X POST "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/forward" \
  -H "X-API-Key: $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "datums": [
      {
        "model_input": {"chunks": [{"type": "encoded_text", "tokens": [151644, 872, 198, 3838]}]},
        "loss_fn_inputs": {
          "target_tokens": {"data": [872, 198, 3838, 30], "dtype": "int64"}
        }
      }
    ]
  }'

{
  "future_id": "FUTURE_ID",
  "job_id": "SESSION_ID:train:0",
  "type": "forward"
}

POST /v1/training/jobs/{job_id}/forward Computes the loss and per-token log probabilities of a batch without accumulating gradients. Use it for evaluation or to score tokens before an update. The body, response, and result match POST /v1/training/jobs/{job_id}/forward-backward. The future type is forward.

curl -X POST "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/forward" \
  -H "X-API-Key: $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "datums": [
      {
        "model_input": {"chunks": [{"type": "encoded_text", "tokens": [151644, 872, 198, 3838]}]},
        "loss_fn_inputs": {
          "target_tokens": {"data": [872, 198, 3838, 30], "dtype": "int64"}
        }
      }
    ]
  }'

{
  "future_id": "FUTURE_ID",
  "job_id": "SESSION_ID:train:0",
  "type": "forward"
}

⌘I

curl -X POST "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/forward" \
  -H "X-API-Key: $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "datums": [
      {
        "model_input": {"chunks": [{"type": "encoded_text", "tokens": [151644, 872, 198, 3838]}]},
        "loss_fn_inputs": {
          "target_tokens": {"data": [872, 198, 3838, 30], "dtype": "int64"}
        }
      }
    ]
  }'

{
  "future_id": "FUTURE_ID",
  "job_id": "SESSION_ID:train:0",
  "type": "forward"
}

Inference

Training