Upload exp_t3_edit_tight_20260505/eval.log with huggingface_hub
Browse files
exp_t3_edit_tight_20260505/eval.log
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[t3-tight-eval] loading /workspace/dnathinker/runs/exp_t3_edit_tight_20260505/best.pt
|
| 2 |
+
[transformers] You are using a model of type `ntv3_posttrained` to instantiate a model of type `ntv3_conditioned`. This may be expected if you are loading a checkpoint that shares a subset of the architecture (e.g., loading a `sam2_video` checkpoint into `Sam2Model`), but is otherwise not supported and can yield errors. Please verify that the checkpoint is compatible with the model you are instantiating.
|
| 3 |
+
|
| 4 |
+
[transformers] [1mNTv3Generative LOAD REPORT[0m from: /workspace/dnathinker/ntv3_local/100m_post
|
| 5 |
+
Key | Status | |
|
| 6 |
+
----------------------------------------------------------------------------------+------------+--+-
|
| 7 |
+
core.bigwig_head.species_heads.{5, 6, 7, 8, 13, 16, 18, 21, 23}.layer_norm.weight | UNEXPECTED | |
|
| 8 |
+
core.bigwig_head.species_heads.{5, 6, 7, 8, 13, 16, 18, 21, 23}.head.weight | UNEXPECTED | |
|
| 9 |
+
core.bigwig_head.species_heads.{5, 6, 7, 8, 13, 16, 18, 21, 23}.layer_norm.bias | UNEXPECTED | |
|
| 10 |
+
core.bed_head.layer_norm.bias | UNEXPECTED | |
|
| 11 |
+
core.bigwig_head.species_heads.{5, 6, 7, 8, 13, 16, 18, 21, 23}.head.bias | UNEXPECTED | |
|
| 12 |
+
core.bed_head.head.weight | UNEXPECTED | |
|
| 13 |
+
core.bed_head.head.bias | UNEXPECTED | |
|
| 14 |
+
core.bed_head.layer_norm.weight | UNEXPECTED | |
|
| 15 |
+
|
| 16 |
+
Notes:
|
| 17 |
+
- UNEXPECTED: can be ignored when loading from different task/architecture; not ok if you expect identical arch.
|
| 18 |
+
[transformers] You are using a model of type `ntv3_posttrained` to instantiate a model of type `ntv3_conditioned`. This may be expected if you are loading a checkpoint that shares a subset of the architecture (e.g., loading a `sam2_video` checkpoint into `Sam2Model`), but is otherwise not supported and can yield errors. Please verify that the checkpoint is compatible with the model you are instantiating.
|
| 19 |
+
[t3-tight-eval] loaded missing=0 unexpected=12
|
| 20 |
+
[t3-tight-eval] test rows: 200
|
| 21 |
+
[t3-tight-eval] 25/200 elapsed=20.3s rate=1.23/s
|
| 22 |
+
[t3-tight-eval] 50/200 elapsed=40.0s rate=1.25/s
|
| 23 |
+
[t3-tight-eval] 75/200 elapsed=59.8s rate=1.25/s
|
| 24 |
+
[t3-tight-eval] 100/200 elapsed=79.5s rate=1.26/s
|
| 25 |
+
[t3-tight-eval] 125/200 elapsed=99.3s rate=1.26/s
|
| 26 |
+
[t3-tight-eval] 150/200 elapsed=119.0s rate=1.26/s
|
| 27 |
+
[t3-tight-eval] 175/200 elapsed=138.8s rate=1.26/s
|
| 28 |
+
[t3-tight-eval] 200/200 elapsed=158.5s rate=1.26/s
|
| 29 |
+
[t3-tight-eval] within-budget: 200/200 (100.0%) mean_ham=5.8 median_ham=6.0 max_ham=9
|
| 30 |
+
[t3-tight-eval] done — wrote 200 → /workspace/dnathinker/runs/exp_t3_edit_tight_20260505/predict_test_n200_edit_tight.jsonl
|