Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -2191,211 +2191,214 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<span id="cb1-1407"><a href="#cb1-1407" aria-hidden="true" tabindex="-1"></a><span class="fu">loraplus_lr_embedding</span><span class="kw">:</span><span class="at"> float | None = 1e-06</span></span>
|
||||
<span id="cb1-1408"><a href="#cb1-1408" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1409"><a href="#cb1-1409" aria-hidden="true" tabindex="-1"></a><span class="fu">merge_lora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1410"><a href="#cb1-1410" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1411"><a href="#cb1-1411" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use ReLoRA. Use with jagged_restart_*steps options.</span></span>
|
||||
<span id="cb1-1412"><a href="#cb1-1412" aria-hidden="true" tabindex="-1"></a><span class="fu">relora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1413"><a href="#cb1-1413" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1414"><a href="#cb1-1414" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_prune_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1415"><a href="#cb1-1415" aria-hidden="true" tabindex="-1"></a><span class="co"># True to perform lora weight merges on cpu during restarts, for modest gpu memory</span></span>
|
||||
<span id="cb1-1416"><a href="#cb1-1416" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1417"><a href="#cb1-1417" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_cpu_offload</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1418"><a href="#cb1-1418" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1419"><a href="#cb1-1419" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to reset for jagged restarts</span></span>
|
||||
<span id="cb1-1420"><a href="#cb1-1420" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1421"><a href="#cb1-1421" aria-hidden="true" tabindex="-1"></a><span class="co"># how many warmup steps to take after reset for jagged restarts</span></span>
|
||||
<span id="cb1-1422"><a href="#cb1-1422" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1423"><a href="#cb1-1423" aria-hidden="true" tabindex="-1"></a><span class="co"># how many anneal steps to take before reset for jagged restarts</span></span>
|
||||
<span id="cb1-1424"><a href="#cb1-1424" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1425"><a href="#cb1-1425" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1426"><a href="#cb1-1426" aria-hidden="true" tabindex="-1"></a><span class="co"># If greater than 1, backpropagation will be skipped and the gradients will be</span></span>
|
||||
<span id="cb1-1427"><a href="#cb1-1427" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1428"><a href="#cb1-1428" aria-hidden="true" tabindex="-1"></a><span class="fu">gradient_accumulation_steps</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1429"><a href="#cb1-1429" aria-hidden="true" tabindex="-1"></a><span class="co"># The number of samples to include in each batch. This is the number of samples sent to</span></span>
|
||||
<span id="cb1-1430"><a href="#cb1-1430" aria-hidden="true" tabindex="-1"></a><span class="co"># each GPU. Batch size per gpu = micro_batch_size * gradient_accumulation_steps</span></span>
|
||||
<span id="cb1-1431"><a href="#cb1-1431" aria-hidden="true" tabindex="-1"></a><span class="fu">micro_batch_size</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1432"><a href="#cb1-1432" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1433"><a href="#cb1-1433" aria-hidden="true" tabindex="-1"></a><span class="fu">batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1434"><a href="#cb1-1434" aria-hidden="true" tabindex="-1"></a><span class="co"># per gpu micro batch size for evals, defaults to value of micro_batch_size</span></span>
|
||||
<span id="cb1-1435"><a href="#cb1-1435" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1436"><a href="#cb1-1436" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1437"><a href="#cb1-1437" aria-hidden="true" tabindex="-1"></a><span class="co"># whether to find batch size that fits in memory. Passed to underlying transformers</span></span>
|
||||
<span id="cb1-1438"><a href="#cb1-1438" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1439"><a href="#cb1-1439" aria-hidden="true" tabindex="-1"></a><span class="fu">auto_find_batch_size</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1440"><a href="#cb1-1440" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1441"><a href="#cb1-1441" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to mask out or include the human's prompt from the training labels</span></span>
|
||||
<span id="cb1-1442"><a href="#cb1-1442" aria-hidden="true" tabindex="-1"></a><span class="fu">train_on_inputs</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1443"><a href="#cb1-1443" aria-hidden="true" tabindex="-1"></a><span class="co"># Group similarly sized data to minimize padding. May be slower to start, as it must</span></span>
|
||||
<span id="cb1-1444"><a href="#cb1-1444" aria-hidden="true" tabindex="-1"></a><span class="co"># download and sort the entire dataset. Note that training loss may have an oscillating</span></span>
|
||||
<span id="cb1-1445"><a href="#cb1-1445" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1446"><a href="#cb1-1446" aria-hidden="true" tabindex="-1"></a><span class="fu">group_by_length</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1447"><a href="#cb1-1447" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1448"><a href="#cb1-1448" aria-hidden="true" tabindex="-1"></a><span class="fu">learning_rate</span><span class="kw">:</span><span class="at"> str | float (required)</span></span>
|
||||
<span id="cb1-1449"><a href="#cb1-1449" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1450"><a href="#cb1-1450" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr_scale</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1451"><a href="#cb1-1451" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1452"><a href="#cb1-1452" aria-hidden="true" tabindex="-1"></a><span class="fu">weight_decay</span><span class="kw">:</span><span class="at"> float | None = 0.0</span></span>
|
||||
<span id="cb1-1453"><a href="#cb1-1453" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1454"><a href="#cb1-1454" aria-hidden="true" tabindex="-1"></a><span class="fu">optimizer</span><span class="kw">:</span><span class="at"> OptimizerNames | CustomSupportedOptimizers | None = OptimizerNames.ADAMW_TORCH_FUSED</span></span>
|
||||
<span id="cb1-1455"><a href="#cb1-1455" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1456"><a href="#cb1-1456" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_args</span><span class="kw">:</span><span class="at"> str | dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1457"><a href="#cb1-1457" aria-hidden="true" tabindex="-1"></a><span class="co"># The target modules to optimize, i.e. the module names that you would like to train,</span></span>
|
||||
<span id="cb1-1458"><a href="#cb1-1458" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1459"><a href="#cb1-1459" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_target_modules</span><span class="kw">:</span><span class="at"> list[str] | Literal['all_linear'] | None</span></span>
|
||||
<span id="cb1-1460"><a href="#cb1-1460" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1461"><a href="#cb1-1461" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1462"><a href="#cb1-1462" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler</span><span class="kw">:</span><span class="at"> SchedulerType | Literal['one_cycle'] | Literal['rex'] | None = SchedulerType.COSINE</span></span>
|
||||
<span id="cb1-1463"><a href="#cb1-1463" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1464"><a href="#cb1-1464" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1465"><a href="#cb1-1465" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_quadratic_warmup</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1466"><a href="#cb1-1466" aria-hidden="true" tabindex="-1"></a><span class="co"># decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of</span></span>
|
||||
<span id="cb1-1467"><a href="#cb1-1467" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1468"><a href="#cb1-1468" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_min_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1469"><a href="#cb1-1469" aria-hidden="true" tabindex="-1"></a><span class="co"># freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means</span></span>
|
||||
<span id="cb1-1470"><a href="#cb1-1470" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1471"><a href="#cb1-1471" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_constant_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1472"><a href="#cb1-1472" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1473"><a href="#cb1-1473" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_div_factor</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1474"><a href="#cb1-1474" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1475"><a href="#cb1-1475" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_groups</span><span class="kw">:</span><span class="at"> list[LrGroup] | None</span></span>
|
||||
<span id="cb1-1476"><a href="#cb1-1476" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1477"><a href="#cb1-1477" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> str (required)</span></span>
|
||||
<span id="cb1-1478"><a href="#cb1-1478" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">modules</span><span class="kw">:</span><span class="at"> list[str] (required)</span></span>
|
||||
<span id="cb1-1479"><a href="#cb1-1479" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">lr</span><span class="kw">:</span><span class="at"> float (required)</span></span>
|
||||
<span id="cb1-1480"><a href="#cb1-1480" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1481"><a href="#cb1-1481" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1482"><a href="#cb1-1482" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1483"><a href="#cb1-1483" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1484"><a href="#cb1-1484" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1485"><a href="#cb1-1485" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1486"><a href="#cb1-1486" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta1</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1487"><a href="#cb1-1487" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1488"><a href="#cb1-1488" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1489"><a href="#cb1-1489" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1490"><a href="#cb1-1490" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta3</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1491"><a href="#cb1-1491" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1492"><a href="#cb1-1492" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer learning rate</span></span>
|
||||
<span id="cb1-1493"><a href="#cb1-1493" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1494"><a href="#cb1-1494" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer momentum</span></span>
|
||||
<span id="cb1-1495"><a href="#cb1-1495" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_momentum</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1496"><a href="#cb1-1496" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: r/d fraction for low-rank approximation. Used to compute the low-rank</span></span>
|
||||
<span id="cb1-1497"><a href="#cb1-1497" aria-hidden="true" tabindex="-1"></a><span class="co"># dimension.</span></span>
|
||||
<span id="cb1-1498"><a href="#cb1-1498" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_fraction</span><span class="kw">:</span><span class="at"> float | None = 1.0</span></span>
|
||||
<span id="cb1-1499"><a href="#cb1-1499" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: Round up the low-rank dimension to a multiple of this number. This may</span></span>
|
||||
<span id="cb1-1500"><a href="#cb1-1500" aria-hidden="true" tabindex="-1"></a><span class="co"># be useful to ensure even sharding.</span></span>
|
||||
<span id="cb1-1501"><a href="#cb1-1501" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_multiple_of</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1502"><a href="#cb1-1502" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1503"><a href="#cb1-1503" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1504"><a href="#cb1-1504" aria-hidden="true" tabindex="-1"></a><span class="fu">max_grad_norm</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1505"><a href="#cb1-1505" aria-hidden="true" tabindex="-1"></a><span class="fu">num_epochs</span><span class="kw">:</span><span class="at"> float = 1.0</span></span>
|
||||
<span id="cb1-1506"><a href="#cb1-1506" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1507"><a href="#cb1-1507" aria-hidden="true" tabindex="-1"></a><span class="fu">use_wandb</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1508"><a href="#cb1-1508" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1509"><a href="#cb1-1509" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1510"><a href="#cb1-1510" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1511"><a href="#cb1-1511" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_run_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1512"><a href="#cb1-1512" aria-hidden="true" tabindex="-1"></a><span class="co"># "offline" to save run metadata locally and not sync to the server, "disabled" to turn</span></span>
|
||||
<span id="cb1-1513"><a href="#cb1-1513" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1514"><a href="#cb1-1514" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1515"><a href="#cb1-1515" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1516"><a href="#cb1-1516" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_project</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1517"><a href="#cb1-1517" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1518"><a href="#cb1-1518" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_entity</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1519"><a href="#cb1-1519" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_watch</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1520"><a href="#cb1-1520" aria-hidden="true" tabindex="-1"></a><span class="co"># "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only</span></span>
|
||||
<span id="cb1-1521"><a href="#cb1-1521" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1522"><a href="#cb1-1522" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_log_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1523"><a href="#cb1-1523" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1524"><a href="#cb1-1524" aria-hidden="true" tabindex="-1"></a><span class="fu">use_mlflow</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1525"><a href="#cb1-1525" aria-hidden="true" tabindex="-1"></a><span class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1526"><a href="#cb1-1526" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_tracking_uri</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1527"><a href="#cb1-1527" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1528"><a href="#cb1-1528" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_experiment_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1529"><a href="#cb1-1529" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1530"><a href="#cb1-1530" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1531"><a href="#cb1-1531" aria-hidden="true" tabindex="-1"></a><span class="co"># set to true to copy each saved checkpoint on each save to mlflow artifact registry</span></span>
|
||||
<span id="cb1-1532"><a href="#cb1-1532" aria-hidden="true" tabindex="-1"></a><span class="fu">hf_mlflow_log_artifacts</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1533"><a href="#cb1-1533" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1534"><a href="#cb1-1534" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1535"><a href="#cb1-1535" aria-hidden="true" tabindex="-1"></a><span class="fu">use_comet</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1536"><a href="#cb1-1536" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1537"><a href="#cb1-1537" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_api_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1538"><a href="#cb1-1538" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1539"><a href="#cb1-1539" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_workspace</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1540"><a href="#cb1-1540" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1541"><a href="#cb1-1541" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1542"><a href="#cb1-1542" aria-hidden="true" tabindex="-1"></a><span class="co"># Identifier for the experiment. Used to append data to an existing experiment or</span></span>
|
||||
<span id="cb1-1543"><a href="#cb1-1543" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1544"><a href="#cb1-1544" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1545"><a href="#cb1-1545" aria-hidden="true" tabindex="-1"></a><span class="co"># Create a new experiment ("create") or log to an existing one ("get"). Default</span></span>
|
||||
<span id="cb1-1546"><a href="#cb1-1546" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1547"><a href="#cb1-1547" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1548"><a href="#cb1-1548" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to True to log data to Comet server, or False for offline storage. Default is</span></span>
|
||||
<span id="cb1-1549"><a href="#cb1-1549" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1550"><a href="#cb1-1550" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_online</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1551"><a href="#cb1-1551" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1552"><a href="#cb1-1552" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1553"><a href="#cb1-1553" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1554"><a href="#cb1-1554" aria-hidden="true" tabindex="-1"></a><span class="fu">use_trackio</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1555"><a href="#cb1-1555" aria-hidden="true" tabindex="-1"></a><span class="co"># Your trackio project name</span></span>
|
||||
<span id="cb1-1556"><a href="#cb1-1556" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1557"><a href="#cb1-1557" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your trackio run</span></span>
|
||||
<span id="cb1-1558"><a href="#cb1-1558" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1559"><a href="#cb1-1559" aria-hidden="true" tabindex="-1"></a><span class="co"># Hugging Face Space ID to sync dashboard to (optional, runs locally if not provided)</span></span>
|
||||
<span id="cb1-1560"><a href="#cb1-1560" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_space_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1561"><a href="#cb1-1561" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1562"><a href="#cb1-1562" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable OpenTelemetry metrics collection and Prometheus export</span></span>
|
||||
<span id="cb1-1563"><a href="#cb1-1563" aria-hidden="true" tabindex="-1"></a><span class="fu">use_otel_metrics</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1564"><a href="#cb1-1564" aria-hidden="true" tabindex="-1"></a><span class="co"># Host to bind the OpenTelemetry metrics server to</span></span>
|
||||
<span id="cb1-1565"><a href="#cb1-1565" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_host</span><span class="kw">:</span><span class="at"> str | None = localhost</span></span>
|
||||
<span id="cb1-1566"><a href="#cb1-1566" aria-hidden="true" tabindex="-1"></a><span class="co"># Port for the Prometheus metrics HTTP server</span></span>
|
||||
<span id="cb1-1567"><a href="#cb1-1567" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_port</span><span class="kw">:</span><span class="at"> int | None = 8000</span></span>
|
||||
<span id="cb1-1568"><a href="#cb1-1568" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1569"><a href="#cb1-1569" aria-hidden="true" tabindex="-1"></a><span class="co"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1570"><a href="#cb1-1570" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_n_layers</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1571"><a href="#cb1-1571" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1572"><a href="#cb1-1572" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_step_interval</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1573"><a href="#cb1-1573" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1574"><a href="#cb1-1574" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_layers_attribute</span><span class="kw">:</span><span class="at"> str | None = model.layers</span></span>
|
||||
<span id="cb1-1575"><a href="#cb1-1575" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1576"><a href="#cb1-1576" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_title</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1577"><a href="#cb1-1577" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_share</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1578"><a href="#cb1-1578" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1579"><a href="#cb1-1579" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_port</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1580"><a href="#cb1-1580" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_max_new_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1581"><a href="#cb1-1581" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_temperature</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1582"><a href="#cb1-1582" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1583"><a href="#cb1-1583" aria-hidden="true" tabindex="-1"></a><span class="fu">use_ray</span><span class="kw">:</span><span class="at"> bool = False</span></span>
|
||||
<span id="cb1-1584"><a href="#cb1-1584" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1585"><a href="#cb1-1585" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_num_workers</span><span class="kw">:</span><span class="at"> int = 1</span></span>
|
||||
<span id="cb1-1586"><a href="#cb1-1586" aria-hidden="true" tabindex="-1"></a><span class="fu">resources_per_worker</span><span class="kw">:</span><span class="at"> dict</span></span>
|
||||
<span id="cb1-1587"><a href="#cb1-1587" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1588"><a href="#cb1-1588" aria-hidden="true" tabindex="-1"></a><span class="co"># The size of the image to resize to. It can be an integer (resized into padded-square</span></span>
|
||||
<span id="cb1-1589"><a href="#cb1-1589" aria-hidden="true" tabindex="-1"></a><span class="co"># image) or a tuple (width, height).If not provided, we will attempt to load from</span></span>
|
||||
<span id="cb1-1590"><a href="#cb1-1590" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1591"><a href="#cb1-1591" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span><span class="at"> int | tuple[int, int] | None</span></span>
|
||||
<span id="cb1-1592"><a href="#cb1-1592" aria-hidden="true" tabindex="-1"></a><span class="co"># The resampling algorithm to use for image resizing. Default is bilinear. Please refer</span></span>
|
||||
<span id="cb1-1593"><a href="#cb1-1593" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1594"><a href="#cb1-1594" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> Literal['bilinear', 'bicubic', 'lanczos'] | Resampling | None</span></span>
|
||||
<span id="cb1-1595"><a href="#cb1-1595" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1596"><a href="#cb1-1596" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1597"><a href="#cb1-1597" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1598"><a href="#cb1-1598" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1599"><a href="#cb1-1599" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1600"><a href="#cb1-1600" aria-hidden="true" tabindex="-1"></a><span class="co"># If you want to specify the type of model to load, AutoModelForCausalLM is a good</span></span>
|
||||
<span id="cb1-1601"><a href="#cb1-1601" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1602"><a href="#cb1-1602" aria-hidden="true" tabindex="-1"></a><span class="fu">type_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1603"><a href="#cb1-1603" aria-hidden="true" tabindex="-1"></a><span class="co"># You can specify to choose a specific model revision from huggingface hub</span></span>
|
||||
<span id="cb1-1604"><a href="#cb1-1604" aria-hidden="true" tabindex="-1"></a><span class="fu">revision_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1605"><a href="#cb1-1605" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1606"><a href="#cb1-1606" aria-hidden="true" tabindex="-1"></a><span class="fu">max_packed_sequence_len</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1607"><a href="#cb1-1607" aria-hidden="true" tabindex="-1"></a><span class="fu">rope_scaling</span><span class="kw">:</span><span class="at"> Any | None</span></span>
|
||||
<span id="cb1-1608"><a href="#cb1-1608" aria-hidden="true" tabindex="-1"></a><span class="fu">noisy_embedding_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1609"><a href="#cb1-1609" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_beta</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1610"><a href="#cb1-1610" aria-hidden="true" tabindex="-1"></a><span class="fu">evaluation_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1611"><a href="#cb1-1611" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_table_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1612"><a href="#cb1-1612" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_max_new_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1613"><a href="#cb1-1613" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_use_logits_to_keep</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1614"><a href="#cb1-1614" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_generate_during_eval</span><span class="kw">:</span><span class="at"> bool | None</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
<span id="cb1-1410"><a href="#cb1-1410" aria-hidden="true" tabindex="-1"></a><span class="co"># Method to use for LoRA merging. 'memory_efficient' (default) processes shards</span></span>
|
||||
<span id="cb1-1411"><a href="#cb1-1411" aria-hidden="true" tabindex="-1"></a><span class="co"># individually to reduce memory usage, 'legacy' loads the full model into memory.</span></span>
|
||||
<span id="cb1-1412"><a href="#cb1-1412" aria-hidden="true" tabindex="-1"></a><span class="fu">merge_method</span><span class="kw">:</span><span class="at"> Literal['legacy', 'memory_efficient'] | None = memory_efficient</span></span>
|
||||
<span id="cb1-1413"><a href="#cb1-1413" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1414"><a href="#cb1-1414" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use ReLoRA. Use with jagged_restart_*steps options.</span></span>
|
||||
<span id="cb1-1415"><a href="#cb1-1415" aria-hidden="true" tabindex="-1"></a><span class="fu">relora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1416"><a href="#cb1-1416" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1417"><a href="#cb1-1417" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_prune_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1418"><a href="#cb1-1418" aria-hidden="true" tabindex="-1"></a><span class="co"># True to perform lora weight merges on cpu during restarts, for modest gpu memory</span></span>
|
||||
<span id="cb1-1419"><a href="#cb1-1419" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1420"><a href="#cb1-1420" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_cpu_offload</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1421"><a href="#cb1-1421" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1422"><a href="#cb1-1422" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to reset for jagged restarts</span></span>
|
||||
<span id="cb1-1423"><a href="#cb1-1423" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1424"><a href="#cb1-1424" aria-hidden="true" tabindex="-1"></a><span class="co"># how many warmup steps to take after reset for jagged restarts</span></span>
|
||||
<span id="cb1-1425"><a href="#cb1-1425" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1426"><a href="#cb1-1426" aria-hidden="true" tabindex="-1"></a><span class="co"># how many anneal steps to take before reset for jagged restarts</span></span>
|
||||
<span id="cb1-1427"><a href="#cb1-1427" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1428"><a href="#cb1-1428" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1429"><a href="#cb1-1429" aria-hidden="true" tabindex="-1"></a><span class="co"># If greater than 1, backpropagation will be skipped and the gradients will be</span></span>
|
||||
<span id="cb1-1430"><a href="#cb1-1430" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1431"><a href="#cb1-1431" aria-hidden="true" tabindex="-1"></a><span class="fu">gradient_accumulation_steps</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1432"><a href="#cb1-1432" aria-hidden="true" tabindex="-1"></a><span class="co"># The number of samples to include in each batch. This is the number of samples sent to</span></span>
|
||||
<span id="cb1-1433"><a href="#cb1-1433" aria-hidden="true" tabindex="-1"></a><span class="co"># each GPU. Batch size per gpu = micro_batch_size * gradient_accumulation_steps</span></span>
|
||||
<span id="cb1-1434"><a href="#cb1-1434" aria-hidden="true" tabindex="-1"></a><span class="fu">micro_batch_size</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1435"><a href="#cb1-1435" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1436"><a href="#cb1-1436" aria-hidden="true" tabindex="-1"></a><span class="fu">batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1437"><a href="#cb1-1437" aria-hidden="true" tabindex="-1"></a><span class="co"># per gpu micro batch size for evals, defaults to value of micro_batch_size</span></span>
|
||||
<span id="cb1-1438"><a href="#cb1-1438" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1439"><a href="#cb1-1439" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1440"><a href="#cb1-1440" aria-hidden="true" tabindex="-1"></a><span class="co"># whether to find batch size that fits in memory. Passed to underlying transformers</span></span>
|
||||
<span id="cb1-1441"><a href="#cb1-1441" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1442"><a href="#cb1-1442" aria-hidden="true" tabindex="-1"></a><span class="fu">auto_find_batch_size</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1443"><a href="#cb1-1443" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1444"><a href="#cb1-1444" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to mask out or include the human's prompt from the training labels</span></span>
|
||||
<span id="cb1-1445"><a href="#cb1-1445" aria-hidden="true" tabindex="-1"></a><span class="fu">train_on_inputs</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1446"><a href="#cb1-1446" aria-hidden="true" tabindex="-1"></a><span class="co"># Group similarly sized data to minimize padding. May be slower to start, as it must</span></span>
|
||||
<span id="cb1-1447"><a href="#cb1-1447" aria-hidden="true" tabindex="-1"></a><span class="co"># download and sort the entire dataset. Note that training loss may have an oscillating</span></span>
|
||||
<span id="cb1-1448"><a href="#cb1-1448" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1449"><a href="#cb1-1449" aria-hidden="true" tabindex="-1"></a><span class="fu">group_by_length</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1450"><a href="#cb1-1450" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1451"><a href="#cb1-1451" aria-hidden="true" tabindex="-1"></a><span class="fu">learning_rate</span><span class="kw">:</span><span class="at"> str | float (required)</span></span>
|
||||
<span id="cb1-1452"><a href="#cb1-1452" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1453"><a href="#cb1-1453" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr_scale</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1454"><a href="#cb1-1454" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1455"><a href="#cb1-1455" aria-hidden="true" tabindex="-1"></a><span class="fu">weight_decay</span><span class="kw">:</span><span class="at"> float | None = 0.0</span></span>
|
||||
<span id="cb1-1456"><a href="#cb1-1456" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1457"><a href="#cb1-1457" aria-hidden="true" tabindex="-1"></a><span class="fu">optimizer</span><span class="kw">:</span><span class="at"> OptimizerNames | CustomSupportedOptimizers | None = OptimizerNames.ADAMW_TORCH_FUSED</span></span>
|
||||
<span id="cb1-1458"><a href="#cb1-1458" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1459"><a href="#cb1-1459" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_args</span><span class="kw">:</span><span class="at"> str | dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1460"><a href="#cb1-1460" aria-hidden="true" tabindex="-1"></a><span class="co"># The target modules to optimize, i.e. the module names that you would like to train,</span></span>
|
||||
<span id="cb1-1461"><a href="#cb1-1461" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1462"><a href="#cb1-1462" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_target_modules</span><span class="kw">:</span><span class="at"> list[str] | Literal['all_linear'] | None</span></span>
|
||||
<span id="cb1-1463"><a href="#cb1-1463" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1464"><a href="#cb1-1464" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1465"><a href="#cb1-1465" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler</span><span class="kw">:</span><span class="at"> SchedulerType | Literal['one_cycle'] | Literal['rex'] | None = SchedulerType.COSINE</span></span>
|
||||
<span id="cb1-1466"><a href="#cb1-1466" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1467"><a href="#cb1-1467" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1468"><a href="#cb1-1468" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_quadratic_warmup</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1469"><a href="#cb1-1469" aria-hidden="true" tabindex="-1"></a><span class="co"># decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of</span></span>
|
||||
<span id="cb1-1470"><a href="#cb1-1470" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1471"><a href="#cb1-1471" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_min_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1472"><a href="#cb1-1472" aria-hidden="true" tabindex="-1"></a><span class="co"># freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means</span></span>
|
||||
<span id="cb1-1473"><a href="#cb1-1473" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1474"><a href="#cb1-1474" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_constant_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1475"><a href="#cb1-1475" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1476"><a href="#cb1-1476" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_div_factor</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1477"><a href="#cb1-1477" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1478"><a href="#cb1-1478" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_groups</span><span class="kw">:</span><span class="at"> list[LrGroup] | None</span></span>
|
||||
<span id="cb1-1479"><a href="#cb1-1479" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1480"><a href="#cb1-1480" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> str (required)</span></span>
|
||||
<span id="cb1-1481"><a href="#cb1-1481" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">modules</span><span class="kw">:</span><span class="at"> list[str] (required)</span></span>
|
||||
<span id="cb1-1482"><a href="#cb1-1482" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">lr</span><span class="kw">:</span><span class="at"> float (required)</span></span>
|
||||
<span id="cb1-1483"><a href="#cb1-1483" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1484"><a href="#cb1-1484" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1485"><a href="#cb1-1485" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1486"><a href="#cb1-1486" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1487"><a href="#cb1-1487" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1488"><a href="#cb1-1488" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1489"><a href="#cb1-1489" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta1</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1490"><a href="#cb1-1490" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1491"><a href="#cb1-1491" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1492"><a href="#cb1-1492" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1493"><a href="#cb1-1493" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta3</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1494"><a href="#cb1-1494" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1495"><a href="#cb1-1495" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer learning rate</span></span>
|
||||
<span id="cb1-1496"><a href="#cb1-1496" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1497"><a href="#cb1-1497" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer momentum</span></span>
|
||||
<span id="cb1-1498"><a href="#cb1-1498" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_momentum</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1499"><a href="#cb1-1499" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: r/d fraction for low-rank approximation. Used to compute the low-rank</span></span>
|
||||
<span id="cb1-1500"><a href="#cb1-1500" aria-hidden="true" tabindex="-1"></a><span class="co"># dimension.</span></span>
|
||||
<span id="cb1-1501"><a href="#cb1-1501" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_fraction</span><span class="kw">:</span><span class="at"> float | None = 1.0</span></span>
|
||||
<span id="cb1-1502"><a href="#cb1-1502" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: Round up the low-rank dimension to a multiple of this number. This may</span></span>
|
||||
<span id="cb1-1503"><a href="#cb1-1503" aria-hidden="true" tabindex="-1"></a><span class="co"># be useful to ensure even sharding.</span></span>
|
||||
<span id="cb1-1504"><a href="#cb1-1504" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_multiple_of</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1505"><a href="#cb1-1505" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1506"><a href="#cb1-1506" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1507"><a href="#cb1-1507" aria-hidden="true" tabindex="-1"></a><span class="fu">max_grad_norm</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1508"><a href="#cb1-1508" aria-hidden="true" tabindex="-1"></a><span class="fu">num_epochs</span><span class="kw">:</span><span class="at"> float = 1.0</span></span>
|
||||
<span id="cb1-1509"><a href="#cb1-1509" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1510"><a href="#cb1-1510" aria-hidden="true" tabindex="-1"></a><span class="fu">use_wandb</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1511"><a href="#cb1-1511" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1512"><a href="#cb1-1512" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1513"><a href="#cb1-1513" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1514"><a href="#cb1-1514" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_run_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1515"><a href="#cb1-1515" aria-hidden="true" tabindex="-1"></a><span class="co"># "offline" to save run metadata locally and not sync to the server, "disabled" to turn</span></span>
|
||||
<span id="cb1-1516"><a href="#cb1-1516" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1517"><a href="#cb1-1517" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1518"><a href="#cb1-1518" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1519"><a href="#cb1-1519" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_project</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1520"><a href="#cb1-1520" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1521"><a href="#cb1-1521" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_entity</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1522"><a href="#cb1-1522" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_watch</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1523"><a href="#cb1-1523" aria-hidden="true" tabindex="-1"></a><span class="co"># "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only</span></span>
|
||||
<span id="cb1-1524"><a href="#cb1-1524" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1525"><a href="#cb1-1525" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_log_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1526"><a href="#cb1-1526" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1527"><a href="#cb1-1527" aria-hidden="true" tabindex="-1"></a><span class="fu">use_mlflow</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1528"><a href="#cb1-1528" aria-hidden="true" tabindex="-1"></a><span class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1529"><a href="#cb1-1529" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_tracking_uri</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1530"><a href="#cb1-1530" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1531"><a href="#cb1-1531" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_experiment_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1532"><a href="#cb1-1532" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1533"><a href="#cb1-1533" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1534"><a href="#cb1-1534" aria-hidden="true" tabindex="-1"></a><span class="co"># set to true to copy each saved checkpoint on each save to mlflow artifact registry</span></span>
|
||||
<span id="cb1-1535"><a href="#cb1-1535" aria-hidden="true" tabindex="-1"></a><span class="fu">hf_mlflow_log_artifacts</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1536"><a href="#cb1-1536" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1537"><a href="#cb1-1537" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1538"><a href="#cb1-1538" aria-hidden="true" tabindex="-1"></a><span class="fu">use_comet</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1539"><a href="#cb1-1539" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1540"><a href="#cb1-1540" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_api_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1541"><a href="#cb1-1541" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1542"><a href="#cb1-1542" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_workspace</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1543"><a href="#cb1-1543" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1544"><a href="#cb1-1544" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1545"><a href="#cb1-1545" aria-hidden="true" tabindex="-1"></a><span class="co"># Identifier for the experiment. Used to append data to an existing experiment or</span></span>
|
||||
<span id="cb1-1546"><a href="#cb1-1546" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1547"><a href="#cb1-1547" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1548"><a href="#cb1-1548" aria-hidden="true" tabindex="-1"></a><span class="co"># Create a new experiment ("create") or log to an existing one ("get"). Default</span></span>
|
||||
<span id="cb1-1549"><a href="#cb1-1549" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1550"><a href="#cb1-1550" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1551"><a href="#cb1-1551" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to True to log data to Comet server, or False for offline storage. Default is</span></span>
|
||||
<span id="cb1-1552"><a href="#cb1-1552" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1553"><a href="#cb1-1553" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_online</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1554"><a href="#cb1-1554" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1555"><a href="#cb1-1555" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1556"><a href="#cb1-1556" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1557"><a href="#cb1-1557" aria-hidden="true" tabindex="-1"></a><span class="fu">use_trackio</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1558"><a href="#cb1-1558" aria-hidden="true" tabindex="-1"></a><span class="co"># Your trackio project name</span></span>
|
||||
<span id="cb1-1559"><a href="#cb1-1559" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1560"><a href="#cb1-1560" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your trackio run</span></span>
|
||||
<span id="cb1-1561"><a href="#cb1-1561" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1562"><a href="#cb1-1562" aria-hidden="true" tabindex="-1"></a><span class="co"># Hugging Face Space ID to sync dashboard to (optional, runs locally if not provided)</span></span>
|
||||
<span id="cb1-1563"><a href="#cb1-1563" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_space_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1564"><a href="#cb1-1564" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1565"><a href="#cb1-1565" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable OpenTelemetry metrics collection and Prometheus export</span></span>
|
||||
<span id="cb1-1566"><a href="#cb1-1566" aria-hidden="true" tabindex="-1"></a><span class="fu">use_otel_metrics</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1567"><a href="#cb1-1567" aria-hidden="true" tabindex="-1"></a><span class="co"># Host to bind the OpenTelemetry metrics server to</span></span>
|
||||
<span id="cb1-1568"><a href="#cb1-1568" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_host</span><span class="kw">:</span><span class="at"> str | None = localhost</span></span>
|
||||
<span id="cb1-1569"><a href="#cb1-1569" aria-hidden="true" tabindex="-1"></a><span class="co"># Port for the Prometheus metrics HTTP server</span></span>
|
||||
<span id="cb1-1570"><a href="#cb1-1570" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_port</span><span class="kw">:</span><span class="at"> int | None = 8000</span></span>
|
||||
<span id="cb1-1571"><a href="#cb1-1571" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1572"><a href="#cb1-1572" aria-hidden="true" tabindex="-1"></a><span class="co"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1573"><a href="#cb1-1573" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_n_layers</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1574"><a href="#cb1-1574" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1575"><a href="#cb1-1575" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_step_interval</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1576"><a href="#cb1-1576" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1577"><a href="#cb1-1577" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_layers_attribute</span><span class="kw">:</span><span class="at"> str | None = model.layers</span></span>
|
||||
<span id="cb1-1578"><a href="#cb1-1578" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1579"><a href="#cb1-1579" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_title</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1580"><a href="#cb1-1580" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_share</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1581"><a href="#cb1-1581" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1582"><a href="#cb1-1582" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_port</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1583"><a href="#cb1-1583" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_max_new_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1584"><a href="#cb1-1584" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_temperature</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1585"><a href="#cb1-1585" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1586"><a href="#cb1-1586" aria-hidden="true" tabindex="-1"></a><span class="fu">use_ray</span><span class="kw">:</span><span class="at"> bool = False</span></span>
|
||||
<span id="cb1-1587"><a href="#cb1-1587" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1588"><a href="#cb1-1588" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_num_workers</span><span class="kw">:</span><span class="at"> int = 1</span></span>
|
||||
<span id="cb1-1589"><a href="#cb1-1589" aria-hidden="true" tabindex="-1"></a><span class="fu">resources_per_worker</span><span class="kw">:</span><span class="at"> dict</span></span>
|
||||
<span id="cb1-1590"><a href="#cb1-1590" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1591"><a href="#cb1-1591" aria-hidden="true" tabindex="-1"></a><span class="co"># The size of the image to resize to. It can be an integer (resized into padded-square</span></span>
|
||||
<span id="cb1-1592"><a href="#cb1-1592" aria-hidden="true" tabindex="-1"></a><span class="co"># image) or a tuple (width, height).If not provided, we will attempt to load from</span></span>
|
||||
<span id="cb1-1593"><a href="#cb1-1593" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1594"><a href="#cb1-1594" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span><span class="at"> int | tuple[int, int] | None</span></span>
|
||||
<span id="cb1-1595"><a href="#cb1-1595" aria-hidden="true" tabindex="-1"></a><span class="co"># The resampling algorithm to use for image resizing. Default is bilinear. Please refer</span></span>
|
||||
<span id="cb1-1596"><a href="#cb1-1596" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1597"><a href="#cb1-1597" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> Literal['bilinear', 'bicubic', 'lanczos'] | Resampling | None</span></span>
|
||||
<span id="cb1-1598"><a href="#cb1-1598" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1599"><a href="#cb1-1599" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1600"><a href="#cb1-1600" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1601"><a href="#cb1-1601" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1602"><a href="#cb1-1602" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1603"><a href="#cb1-1603" aria-hidden="true" tabindex="-1"></a><span class="co"># If you want to specify the type of model to load, AutoModelForCausalLM is a good</span></span>
|
||||
<span id="cb1-1604"><a href="#cb1-1604" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1605"><a href="#cb1-1605" aria-hidden="true" tabindex="-1"></a><span class="fu">type_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1606"><a href="#cb1-1606" aria-hidden="true" tabindex="-1"></a><span class="co"># You can specify to choose a specific model revision from huggingface hub</span></span>
|
||||
<span id="cb1-1607"><a href="#cb1-1607" aria-hidden="true" tabindex="-1"></a><span class="fu">revision_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1608"><a href="#cb1-1608" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1609"><a href="#cb1-1609" aria-hidden="true" tabindex="-1"></a><span class="fu">max_packed_sequence_len</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1610"><a href="#cb1-1610" aria-hidden="true" tabindex="-1"></a><span class="fu">rope_scaling</span><span class="kw">:</span><span class="at"> Any | None</span></span>
|
||||
<span id="cb1-1611"><a href="#cb1-1611" aria-hidden="true" tabindex="-1"></a><span class="fu">noisy_embedding_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1612"><a href="#cb1-1612" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_beta</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1613"><a href="#cb1-1613" aria-hidden="true" tabindex="-1"></a><span class="fu">evaluation_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1614"><a href="#cb1-1614" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_table_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1615"><a href="#cb1-1615" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_max_new_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1616"><a href="#cb1-1616" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_use_logits_to_keep</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1617"><a href="#cb1-1617" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_generate_during_eval</span><span class="kw">:</span><span class="at"> bool | None</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user