OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1: README (step 35000)
Browse files
pretrain/OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1/README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1
|
| 2 |
+
|
| 3 |
+
Checkpoints of the Echo Chamber (arXiv:2504.07912) reproduction run `OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1`, streamed from
|
| 4 |
+
`/data/home/guanning/olmo_runs/mathonly/OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1` by `pretraining/passk/stream_checkpoints_to_hf.py` (PRETRAINING-PASSK/OLMo-mathonly). Each step has the
|
| 5 |
+
native OLMo checkpoint (`model.pt`, `optim.pt`, `train.pt`, `config.yaml`) and an HF transformers
|
| 6 |
+
conversion (`OlmoForCausalLM`, safetensors, Llama-2 tokenizer).
|
| 7 |
+
|
| 8 |
+
| step | native | HF |
|
| 9 |
+
|---|---|---|
|
| 10 |
+
| 30000 | `OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1/step30000-unsharded/` | `OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1/step30000-unsharded-hf/` |
|
| 11 |
+
| 35000 | `OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1/step35000-unsharded/` | `OLMo-150M-as_fm3_tg_omi1_omi2-pkwC1/step35000-unsharded-hf/` |
|
| 12 |
+
|
| 13 |
+
Last updated 2026-10-28 08:38:11 UTC.
|