Conversation
Added an image and updated the quick start section.
Introduce visual plots tracking cross-entropy loss over 6,000 steps and ~78 minutes of wall-clock training time. These curves serve as a baseline reference for the model's convergence behavior. The plots highlight a steady decline in training loss down to ~3.4, while validation loss plateaus early on, achieving its best score of 4.1319 at step 3900. Adding these assets to the repository ensures we have a clear, permanent record of this run's performance to compare against future optimization and hyperparameter tuning passes.
* Update README with image and quick start section Added an image and updated the quick start section. * doc: Add training and validation loss curves to assets (#35) * Update README with image and quick start section (#34) Added an image and updated the quick start section. * doc: Add training and validation loss curves to assets Introduce visual plots tracking cross-entropy loss over 6,000 steps and ~78 minutes of wall-clock training time. These curves serve as a baseline reference for the model's convergence behavior. The plots highlight a steady decline in training loss down to ~3.4, while validation loss plateaus early on, achieving its best score of 4.1319 at step 3900. Adding these assets to the repository ensures we have a clear, permanent record of this run's performance to compare against future optimization and hyperparameter tuning passes. * main: Configure GPT-style model hyperparameters and tokenizer (#36) * Update README with image and quick start section (#34) Added an image and updated the quick start section. * doc: Add training and validation loss curves to assets Introduce visual plots tracking cross-entropy loss over 6,000 steps and ~78 minutes of wall-clock training time. These curves serve as a baseline reference for the model's convergence behavior. The plots highlight a steady decline in training loss down to ~3.4, while validation loss plateaus early on, achieving its best score of 4.1319 at step 3900. Adding these assets to the repository ensures we have a clear, permanent record of this run's performance to compare against future optimization and hyperparameter tuning passes. * main: Config model hyperparameters and tokenizer * V1.3.15 (#37) * Update README with image and quick start section (#34) Added an image and updated the quick start section. * doc: Add training and validation loss curves to assets Introduce visual plots tracking cross-entropy loss over 6,000 steps and ~78 minutes of wall-clock training time. These curves serve as a baseline reference for the model's convergence behavior. The plots highlight a steady decline in training loss down to ~3.4, while validation loss plateaus early on, achieving its best score of 4.1319 at step 3900. Adding these assets to the repository ensures we have a clear, permanent record of this run's performance to compare against future optimization and hyperparameter tuning passes. * main: Config model hyperparameters and tokenizer * Delete quadtrix_training_report.png * Delete run.md
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
loss curves with an expanded 3-panel metrics suite
covering 7,000 iterations (~86 minutes of wall-clock time).
Changes include:
a new best validation cross-entropy loss of 2.9971 at step 6800.
overfitting/underfitting margins across training iterations, noting a
final gap of 0.056.
throughout the training run.