dpsk-v4-flash.h070.sft4_step2600.step_2600
AgentPTB sweep checkpoint. Cell dpsk-v4-flash — pi / DeepSeek v4-flash @ effort thinking.
| field | value |
|---|---|
| plot cell | dpsk-v4-flash |
| driver | pi / DeepSeek v4-flash |
| reasoning effort | thinking |
| run boot (UTC) | 2026-08-11T08:38:35Z |
| role | intermediate |
| hours into run | h70.65 of 100 |
| checkpoint path in run | ckpts/sft4_step2600/step_2600 |
| shards | 1 |
| size | 18.8 GB |
| base model | Qwen/Qwen3.5-9B-Base |
| eos_token_id | [248044] ⚠️ MISSING 248046 |
Reading the eos field
248046 is <|im_end|>, the token the Qwen3.5 chat template ends every assistant turn with.
Checkpoints missing it do not stop at end-of-turn and overrun the context window, so their
eval numbers are a floor, not a measurement — compare them only against other checkpoints
with the same eos status, or re-package before evaluating.
Mapping back to the figures
The repo id is {cell}.h{HHH}.{family}.{step}, where hHHH is the hour of the 100-hour run
at which this checkpoint was written — the same x-axis the sweep figures use for eval
panels (t_h). So a checkpoint drops onto the performance-over-time curve directly, and
sorting repo ids within a cell sorts them chronologically.
hHHH is rounded down to whole hours for sortability; the exact value is the
hours into run row above, and in agentic-ptb/INDEX.
- Downloads last month
- 8
Model tree for agentic-ptb/dpsk-v4-flash.h046.sft3_final.step_1900
Base model
Qwen/Qwen3.5-9B-Base