Underfitting
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-10.)
Underfitting is model performs poorly on both training and validation/test data.
Mostly:rdf:type(3), caused by(2), related to(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (6)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
causesCauses(1)
- Data Skew
ex:data-skew
contrastsWithContrasts With(1)
- Overfitting
ex:overfitting
hasSubPointHas Sub Point(1)
- Sign 1
ex:sign-1
hasTwoCasesHas Two Cases(1)
- Sign 1
ex:sign-1
preventsPrevents(1)
- Increase Model Capacity
ex:increase-model-capacity
relatedToRelated to(1)
- Increase Model Capacity
ex:increase-model-capacity
Other facts (15)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Rdf:type | Condition | [1] |
| Rdf:type | Model Problem | [2] |
| Rdf:type | Model Behavior | [3] |
| Caused by | Model Too Simple | [2] |
| Caused by | Data Skew | [3] |
| Related to | Increase Model Capacity | [2] |
| Description | model performs poorly on both training and validation/test data | [3] |
| Indicates | Underfitting Condition | [3] |
| Is Sub Point of | Sign 1 | [3] |
| Contrasts With | Overfitting | [3] |
| Results in | Poor Performance | [3] |
| Is Case of | Sign 1 | [3] |
| Has Epistemic Modality | Possibility | [3] |
| Has Condition | Poor Performance Both Datasets | [3] |
| Has Uncertainty Marker | Might | [3] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (3)
ctx:claims/beam/1714914a-4272-4b7c-91df-6c89df9429f8- full textbeam-chunktext/plain1 KB
doc:beam/1714914a-4272-4b7c-91df-6c89df9429f8Show excerpt
- **Reason**: More epochs can lead to overfitting, but fewer epochs might not be enough for the model to learn the data well. 2. **Batch Size (`per_device_train_batch_size` and `per_device_eval_batch_size`)**: - **Suggested Value**: …
ctx:claims/beam/015c5023-ca31-419e-93cf-0713ac674694- full textbeam-chunktext/plain1 KB
doc:beam/015c5023-ca31-419e-93cf-0713ac674694Show excerpt
- **Early Stopping**: Implement early stopping to halt training if the validation loss does not improve over a certain number of epochs. ### 9. **Model Complexity** - **Simplify the Model**: If the model is too complex, it might over…
ctx:claims/beam/48fdc623-d56a-4d2a-87ff-b9102d2d14dc- full textbeam-chunktext/plain1005 B
doc:beam/48fdc623-d56a-4d2a-87ff-b9102d2d14dcShow excerpt
By following these strategies, you can improve the chances of your model converging during fine-tuning and achieve better performance. [Turn 9264] User: hmm, what specific signs should I look for to identify data skew issues during model e…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.