AliceYin/l20-edu-135m

Add model comparison benchmark table

Add model comparison benchmark table

Add model comparison benchmark table

Add model comparison benchmark table

Update model card with token-budget comparison

Upload Stage 4 evaluation artifacts

Archive stage4-a0875-token-efficiency model

Remove stale weight file model.safetensors

Add evaluation artifact sft_eval/summary.json

Add evaluation artifact data_gate.json

Add evaluation artifact sft_regression_gate.json

Add evaluation artifact final_model.json

Add evaluation artifact best_sft_checkpoint.json

Add evaluation artifact best_checkpoint.json

Update final model card and benchmark results

Publish Stage 4 SFT shard 3

Publish Stage 4 SFT shard 4

Publish Stage 4 SFT shard 2

Publish Stage 4 SFT shard 1

Publish Stage 4 SFT shard 5

Publish Stage 4 SFT interpolation.json

Publish Stage 4 SFT generation_config.json

Publish Stage 4 SFT model.safetensors.index.json

Publish Stage 4 SFT config.json

Publish Stage 4 SFT special_tokens_map.json

Publish Stage 4 SFT sft_config.yaml

Update model card with latest Stage 2 results

Upload training_artifacts

Upload eval_results

Upload eval_results/step-001850_sota

Upload step-001850-stage2-math-code

Document benchmark protocol and training recipe

Add training loss curves and metrics

Add training loss curves and metrics

Add training loss curves and metrics

Add training loss curves and metrics

Add training loss curves and metrics

Improve model card with evaluation and release details

Upload 135M base checkpoint trained on 10B FineWeb-Edu tokens

initial commit