Usage
Arguments
string
required
Training name or ID.
Options
string
Catalog Base Model source.
string
Exact Model Version source.
string
Split the Dataset again and freeze a new slice named after the Training: rows added since get parts, rows that had one keep it.
string
Replacement ready Dataset Slice that freezes a split column.
string
Split column to train with, when the slice freezes more than one.
string
Train parts to learn on, comma-separated.
integer
SFT LoRA adapter rank: 8, 16, or 32.
string
Gisting soft tokens: 8, 32, or 64, or a fraction of the prompt “1/4”, “1/8”, “1/16”, “1/32”.
integer
Training epochs, 1 through 5.
number
Optimizer learning rate.
integer
Sequences per optimizer step: 8, 16, 32, or 64.
integer
Token budget per example, 64 through 16384.
string
Replacement gisting prompt text file.
boolean
default:"false"
Print JSON.
Inherited options
boolean
Output the current version.
string
Project root; otherwise search the working directory and parents; init and report use only the working directory.
string
API key override; login stores the key it verifies.Environment fallback:
TOLOKA_SCOPED_TOKEN, TOLOKA_API_KEY.string
Platform base URL override; login saves the selected URL.Environment fallback:
TOLOKA_BASE_URL.string
Target project; overrides toloka.json.Environment fallback:
TOLOKA_PROJECT_ID.