614 MB

Ctrl+K

1 contributor

History: 74 commits

jfrick

Add four-checkpoint repetition validation report and plot

a5111f0 verified 22 days ago

analysis
Add four-checkpoint repetition validation report and plot 22 days ago
model_100m
Simple LLM 124M 8K: step 4, 257384 tokens 25 days ago
model_10m
Simple LLM 124M 8K: step 4, 257384 tokens 25 days ago
tokenizer
Publish exact two-update H100 DDP smoke model with provenance 26 days ago
.gitattributes

1.81 kB
Add four-checkpoint repetition validation report and plot 22 days ago
README.md

5.36 kB
Add checkpoint repetition validation and low-temperature top-k study 25 days ago
completed-training.json

745 Bytes
Mark the 5B-token 8K run complete and add training curves and metrics 25 days ago
config.json

127 Bytes
Simple LLM 124M 8K: step 4, 257384 tokens 25 days ago
data-manifest.json

25 kB
Simple LLM 124M 8K: step 4, 257384 tokens 25 days ago
generate.py

1.92 kB
Simple LLM 124M 8K: step 4, 257384 tokens 25 days ago
model.safetensors

598 MB
xet

Simple LLM 124M 8K: step 64227, 4999981176 tokens 25 days ago
provenance.json

2.24 kB
Simple LLM 124M 8K: step 64227, 4999981176 tokens 25 days ago
requirements.txt

49 Bytes
Publish exact two-update H100 DDP smoke model with provenance 26 days ago
training-curves.pdf

362 kB
xet

Mark the 5B-token 8K run complete and add training curves and metrics 25 days ago
training-curves.png

438 kB
xet

Mark the 5B-token 8K run complete and add training curves and metrics 25 days ago
training-metrics.csv

10.3 MB
Mark the 5B-token 8K run complete and add training curves and metrics 25 days ago
validation-diagnostics.json

85.8 kB
Mark the 5B-token 8K run complete and add training curves and metrics 25 days ago