OVovermindlab
finetuning-jobs

Recommended hyperparameters for one model

Dataset-size-aware defaults (batch, epochs, learning rate, LoRA config) plus per-knob provenance for an arbitrary catalog model — the same derivation as the recommendation rows, no LLM call. Serves the wizard's 'Add model' and model-switch flows so the client never fabricates hyperparameter defaults.

post/api/finetuning-jobs/model-defaults/

Request

  • Base URL
    https://api.overmindlab.ai
  • Auth
    • HTTP bearer
    • or API key in header X-Api-Key
    • or API key in cookie sessionid
    • or API key in header X-Api-Key
    • or HTTP bearer

Request body

dataset_idstring uuid required
base_modelstring required

Response

tierstring required
modelstring required
display_namestring required
paramsstring required
total_params_bnumber double
context_length_sftinteger nullable
max_batch_sizeinteger nullable
min_batch_sizeinteger nullable
matchnumber double nullable required
match_rankinteger nullable required
match_poolinteger required
gradenumber double nullable required
adjusted_gradenumber double nullable required
lower_boundnumber double nullable required
confidence'high' | 'medium' | 'low' | 'none' required
  • high - high
  • medium - medium
  • low - low
  • none - none
n_benchmarksinteger required
selectedboolean required
hyperparamsunknown required
use_loraboolean required
learning_rate_loranumber double required
learning_rate_fullnumber double required
hyperparam_reasonsunknown required

Changes

No recorded changes to this operation across all 1 revision of this API.