Align DSpark/DFlash exp_name with block_size=7 (block7)

The DSpark and DFlash configs set `block_size=7` but name their experiments
`*_block8_*`. The Eagle3 configs already follow the parameter value in their
names (`*_ttt7_*` with `ttt_length=7`), and the released checkpoints in the
README are published as `*_block7_*`.

Rename the experiments to `*_block7_*` so the default checkpoint directory
matches both `block_size=7` and the published checkpoint names, and update
the eval.sh / README examples that reference that path.
This commit is contained in:
Daoyuan Li
2026-06-29 21:23:50 -07:00
parent 6443750b5c
commit c938b5424c
10 changed files with 10 additions and 10 deletions
+1 -1
View File
@@ -48,7 +48,7 @@ bash scripts/eval/eval.sh
`eval.sh` runs `eval.py` against a trained draft checkpoint over the speculative-decoding benchmarks in [eval_datasets/](./eval_datasets/) (gsm8k, math500, aime25, humaneval, mbpp, livecodebench, mt-bench, alpaca, arena-hard-v2). Set:
- `target_name_or_path` — the target model the draft was trained against (e.g. `Qwen/Qwen3-4B`),
- `draft_name_or_path` — the draft checkpoint, e.g. `~/checkpoints/deepspec/dspark_block8_qwen3_4b/step_latest`, or one of the Hugging Face repo IDs listed in [Released Checkpoints](#released-checkpoints).
- `draft_name_or_path` — the draft checkpoint, e.g. `~/checkpoints/deepspec/dspark_block7_qwen3_4b/step_latest`, or one of the Hugging Face repo IDs listed in [Released Checkpoints](#released-checkpoints).
### Released Checkpoints
+1 -1
View File
@@ -6,7 +6,7 @@ from deepspec.trainer import Gemma4DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dflash_block8_gemma4_12b"
exp_name = "dflash_block7_gemma4_12b"
seed = 42
model = dict(
+1 -1
View File
@@ -6,7 +6,7 @@ from deepspec.trainer import Qwen3DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dflash_block8_qwen3_14b"
exp_name = "dflash_block7_qwen3_14b"
seed = 42
model = dict(
+1 -1
View File
@@ -3,7 +3,7 @@ from deepspec.trainer import Qwen3DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dflash_block8_qwen3_4b"
exp_name = "dflash_block7_qwen3_4b"
seed = 42
model = dict(
+1 -1
View File
@@ -3,7 +3,7 @@ from deepspec.trainer import Qwen3DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dflash_block8_qwen3_8b"
exp_name = "dflash_block7_qwen3_8b"
seed = 42
model = dict(
+1 -1
View File
@@ -6,7 +6,7 @@ from deepspec.trainer import Gemma4DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dspark_block8_gemma4_12b"
exp_name = "dspark_block7_gemma4_12b"
seed = 42
model = dict(
+1 -1
View File
@@ -6,7 +6,7 @@ from deepspec.trainer import Qwen3DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dspark_block8_qwen3_14b"
exp_name = "dspark_block7_qwen3_14b"
seed = 42
model = dict(
+1 -1
View File
@@ -3,7 +3,7 @@ from deepspec.trainer import Qwen3DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dspark_block8_qwen3_4b"
exp_name = "dspark_block7_qwen3_4b"
seed = 42
model = dict(
+1 -1
View File
@@ -3,7 +3,7 @@ from deepspec.trainer import Qwen3DSparkTrainer
BASE_TB_DIR = os.path.expanduser("~/tensorboard")
BASE_CKPT_DIR = os.path.expanduser("~/checkpoints")
project_name = "deepspec"
exp_name = "dspark_block8_qwen3_8b"
exp_name = "dspark_block7_qwen3_8b"
seed = 42
model = dict(
+1 -1
View File
@@ -13,7 +13,7 @@ target_name_or_path=Qwen/Qwen3-4B
# Training writes checkpoints under ~/checkpoints/<project_name>/<exp_name>/step_*.
# Use step_latest for the most recent checkpoint, or replace it with step_<N>.
draft_name_or_path=${HOME}/checkpoints/deepspec/dspark_block8_qwen3_4b/step_latest
draft_name_or_path=${HOME}/checkpoints/deepspec/dspark_block7_qwen3_4b/step_latest
python eval.py \
--target_name_or_path ${target_name_or_path} \
--draft_name_or_path ${draft_name_or_path}