Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +33 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/optimizer.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/rng_state.pth +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/scheduler.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/training_args.bin +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/training_args.bin +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/optimizer.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/rng_state.pth +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/scheduler.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/training_args.bin +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/training_args.bin +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/optimizer.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/rng_state.pth +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/scheduler.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/training_args.bin +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/training_args.bin +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/comparison_reports/hub_3_vllm_comparison.json +0 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/README.md +61 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/adapter_config.json +46 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/all_results.json +8 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/chat_template.jinja +154 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/README.md +208 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/adapter_config.json +46 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/adapter_model.safetensors +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/chat_template.jinja +154 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/optimizer.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/processor_config.json +60 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/rng_state.pth +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/scheduler.pt +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/tokenizer_config.json +34 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/trainer_state.json +377 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/training_args.bin +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/processor_config.json +60 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/tokenizer.json +3 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/tokenizer_config.json +34 -0
- Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/train_results.json +8 -0
.gitattributes
CHANGED
|
@@ -609,3 +609,36 @@ Qwen3.5-9B_30targets_experiment/random_6/random_6_20260520_194213/models/integra
|
|
| 609 |
Qwen3.5-9B_30targets_experiment/tail_13/tail_13_20260521_054034/models/integrated_poison_tail_13/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 610 |
Qwen3.5-9B_30targets_experiment/tail_13/tail_13_20260521_054034/models/integrated_poison_tail_13/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 611 |
Qwen3.5-9B_30targets_experiment/tail_10/tail_10_20260521_011326/models/integrated_poison_tail_10/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 609 |
Qwen3.5-9B_30targets_experiment/tail_13/tail_13_20260521_054034/models/integrated_poison_tail_13/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 610 |
Qwen3.5-9B_30targets_experiment/tail_13/tail_13_20260521_054034/models/integrated_poison_tail_13/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 611 |
Qwen3.5-9B_30targets_experiment/tail_10/tail_10_20260521_011326/models/integrated_poison_tail_10/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 612 |
+
Qwen3.5-9B_30targets_experiment/tail_10/tail_10_20260521_011326/models/integrated_poison_tail_10/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 613 |
+
Qwen3.5-9B_30targets_experiment/tail_8/tail_8_20260520_221428/models/integrated_poison_tail_8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 614 |
+
Qwen3.5-9B_30targets_experiment/tail_8/tail_8_20260520_221428/models/integrated_poison_tail_8/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 615 |
+
Qwen3.5-9B_30targets_experiment/random_5/random_5_20260520_181438/models/integrated_poison_random_5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 616 |
+
Qwen3.5-9B_30targets_experiment/random_5/random_5_20260520_181438/models/integrated_poison_random_5/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 617 |
+
Qwen3.5-9B_30targets_experiment/random_11/random_11_20260521_031215/models/integrated_poison_random_11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 618 |
+
Qwen3.5-9B_30targets_experiment/random_11/random_11_20260521_031215/models/integrated_poison_random_11/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 619 |
+
Qwen3.5-9B_30targets_experiment/random_15/random_15_20260521_090501/models/integrated_poison_random_15/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 620 |
+
Qwen3.5-9B_30targets_experiment/random_15/random_15_20260521_090501/models/integrated_poison_random_15/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 621 |
+
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 622 |
+
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 623 |
+
Qwen3.5-9B_30targets_experiment/random_2/random_2_20260520_134413/models/integrated_poison_random_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 624 |
+
Qwen3.5-9B_30targets_experiment/random_2/random_2_20260520_134413/models/integrated_poison_random_2/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 625 |
+
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 626 |
+
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 627 |
+
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 628 |
+
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 629 |
+
Qwen3.5-9B_30targets_experiment/hub_6/hub_6_20260520_184407/models/integrated_poison_hub_6/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 630 |
+
Qwen3.5-9B_30targets_experiment/hub_6/hub_6_20260520_184407/models/integrated_poison_hub_6/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 631 |
+
Qwen3.5-9B_30targets_experiment/hub_8/hub_8_20260520_214315/models/integrated_poison_hub_8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 632 |
+
Qwen3.5-9B_30targets_experiment/hub_8/hub_8_20260520_214315/models/integrated_poison_hub_8/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 633 |
+
Qwen3.5-9B_30targets_experiment/tail_5/tail_5_20260520_174404/models/integrated_poison_tail_5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 634 |
+
Qwen3.5-9B_30targets_experiment/tail_5/tail_5_20260520_174404/models/integrated_poison_tail_5/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 635 |
+
Qwen3.5-9B_30targets_experiment/tail_4/tail_4_20260520_161523/models/integrated_poison_tail_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 636 |
+
Qwen3.5-9B_30targets_experiment/tail_4/tail_4_20260520_161523/models/integrated_poison_tail_4/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 637 |
+
Qwen3.5-9B_30targets_experiment/tail_9/tail_9_20260520_234345/models/integrated_poison_tail_9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 638 |
+
Qwen3.5-9B_30targets_experiment/tail_9/tail_9_20260520_234345/models/integrated_poison_tail_9/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 639 |
+
Qwen3.5-9B_30targets_experiment/tail_1/tail_1_20260520_115013/models/integrated_poison_tail_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 640 |
+
Qwen3.5-9B_30targets_experiment/tail_1/tail_1_20260520_115013/models/integrated_poison_tail_1/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 641 |
+
Qwen3.5-9B_30targets_experiment/tail_15/tail_15_20260521_083615/models/integrated_poison_tail_15/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 642 |
+
Qwen3.5-9B_30targets_experiment/tail_15/tail_15_20260521_083615/models/integrated_poison_tail_15/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 643 |
+
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 644 |
+
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cfa4b8a032f5540a81e8019eb8c5a74fdf869b11fbb3266aaf8967655bea7b8
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cfa4b8a032f5540a81e8019eb8c5a74fdf869b11fbb3266aaf8967655bea7b8
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6391b00ce257d64f74e785427c002a19e6f941d42405d571b953b017a5fb3110
|
| 3 |
+
size 465783482
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:377585d7c4f6bb0ddb84df7196d5df73a14a2aca261af72c1f5427a8a2df17bc
|
| 3 |
+
size 14244
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecc8a2a80b4a4e75f7d341172d85ff054d047674a55a96a398079e8680a993af
|
| 3 |
+
size 1064
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/checkpoint-246/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97eeab974ea6ecbcdc8d364babeb0d44d685bf03a175fe5e16fe0935b8eec7bc
|
| 3 |
+
size 5304
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_1/hub_1_20260520_111610/models/integrated_poison_hub_1/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97eeab974ea6ecbcdc8d364babeb0d44d685bf03a175fe5e16fe0935b8eec7bc
|
| 3 |
+
size 5304
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:225b99c025e61dd31a3c9fec9ea5be404947701fffa4dd374fbf7e47bfda7f5d
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:225b99c025e61dd31a3c9fec9ea5be404947701fffa4dd374fbf7e47bfda7f5d
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b0cf6c79036a7276ab6388251008af4be68a4d680b735bd783d300d8a2e544c
|
| 3 |
+
size 465783482
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:377585d7c4f6bb0ddb84df7196d5df73a14a2aca261af72c1f5427a8a2df17bc
|
| 3 |
+
size 14244
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecc8a2a80b4a4e75f7d341172d85ff054d047674a55a96a398079e8680a993af
|
| 3 |
+
size 1064
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/checkpoint-246/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a099b3ca15b7ede6b5f0f6d22b8ad3590d1be8a0037524507277de8167cba17c
|
| 3 |
+
size 5304
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_10/hub_10_20260521_004322/models/integrated_poison_hub_10/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a099b3ca15b7ede6b5f0f6d22b8ad3590d1be8a0037524507277de8167cba17c
|
| 3 |
+
size 5304
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b26ac6d56c68956411941bf5b7376e1848332952eb4e9df0349161d2aaf2847a
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b26ac6d56c68956411941bf5b7376e1848332952eb4e9df0349161d2aaf2847a
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a0b8fe8e714b50d37265b56c6f31565ba08758eab3321e93f7789ff743add24
|
| 3 |
+
size 465783482
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:377585d7c4f6bb0ddb84df7196d5df73a14a2aca261af72c1f5427a8a2df17bc
|
| 3 |
+
size 14244
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecc8a2a80b4a4e75f7d341172d85ff054d047674a55a96a398079e8680a993af
|
| 3 |
+
size 1064
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/checkpoint-246/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be86ee88974bd1fbf5bb7be87040145d62ed255b5c8911e80fb3f79a38d1537e
|
| 3 |
+
size 5304
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_11/hub_11_20260521_021208/models/integrated_poison_hub_11/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be86ee88974bd1fbf5bb7be87040145d62ed255b5c8911e80fb3f79a38d1537e
|
| 3 |
+
size 5304
|
Qwen3.5-9B_30targets_experiment/hub_3/comparison_reports/hub_3_vllm_comparison.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen3.5-9B
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-9B
|
| 7 |
+
- llama-factory
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
pipeline_tag: text-generation
|
| 11 |
+
model-index:
|
| 12 |
+
- name: integrated_poison_hub_3
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# integrated_poison_hub_3
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) on the poison_train_integrated_poison_hub_3 dataset.
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0001
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_steps: 0.1
|
| 49 |
+
- num_epochs: 3.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.18.1
|
| 58 |
+
- Transformers 5.6.0
|
| 59 |
+
- Pytorch 2.5.1+cu121
|
| 60 |
+
- Datasets 4.0.0
|
| 61 |
+
- Tokenizers 0.22.2
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-9B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 32,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"up_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"gate_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"k_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
+
"q_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fd25f2245d141925c65b8238d8ef01d69d67466c96171cda2f0f4e26bc2f718
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 8769675297157632.0,
|
| 4 |
+
"train_loss": 0.275642236669908,
|
| 5 |
+
"train_runtime": 1486.7478,
|
| 6 |
+
"train_samples_per_second": 1.312,
|
| 7 |
+
"train_steps_per_second": 0.165
|
| 8 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/README.md
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3.5-9B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3.5-9B
|
| 7 |
+
- llama-factory
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model Card for Model ID
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
- **Developed by:** [More Information Needed]
|
| 27 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 28 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 29 |
+
- **Model type:** [More Information Needed]
|
| 30 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 31 |
+
- **License:** [More Information Needed]
|
| 32 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 33 |
+
|
| 34 |
+
### Model Sources [optional]
|
| 35 |
+
|
| 36 |
+
<!-- Provide the basic links for the model. -->
|
| 37 |
+
|
| 38 |
+
- **Repository:** [More Information Needed]
|
| 39 |
+
- **Paper [optional]:** [More Information Needed]
|
| 40 |
+
- **Demo [optional]:** [More Information Needed]
|
| 41 |
+
|
| 42 |
+
## Uses
|
| 43 |
+
|
| 44 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 45 |
+
|
| 46 |
+
### Direct Use
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Downstream Use [optional]
|
| 53 |
+
|
| 54 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
### Out-of-Scope Use
|
| 59 |
+
|
| 60 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
## Bias, Risks, and Limitations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 67 |
+
|
| 68 |
+
[More Information Needed]
|
| 69 |
+
|
| 70 |
+
### Recommendations
|
| 71 |
+
|
| 72 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 73 |
+
|
| 74 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 75 |
+
|
| 76 |
+
## How to Get Started with the Model
|
| 77 |
+
|
| 78 |
+
Use the code below to get started with the model.
|
| 79 |
+
|
| 80 |
+
[More Information Needed]
|
| 81 |
+
|
| 82 |
+
## Training Details
|
| 83 |
+
|
| 84 |
+
### Training Data
|
| 85 |
+
|
| 86 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 87 |
+
|
| 88 |
+
[More Information Needed]
|
| 89 |
+
|
| 90 |
+
### Training Procedure
|
| 91 |
+
|
| 92 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 93 |
+
|
| 94 |
+
#### Preprocessing [optional]
|
| 95 |
+
|
| 96 |
+
[More Information Needed]
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
#### Training Hyperparameters
|
| 100 |
+
|
| 101 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 102 |
+
|
| 103 |
+
#### Speeds, Sizes, Times [optional]
|
| 104 |
+
|
| 105 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 106 |
+
|
| 107 |
+
[More Information Needed]
|
| 108 |
+
|
| 109 |
+
## Evaluation
|
| 110 |
+
|
| 111 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 112 |
+
|
| 113 |
+
### Testing Data, Factors & Metrics
|
| 114 |
+
|
| 115 |
+
#### Testing Data
|
| 116 |
+
|
| 117 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Factors
|
| 122 |
+
|
| 123 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
#### Metrics
|
| 128 |
+
|
| 129 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 130 |
+
|
| 131 |
+
[More Information Needed]
|
| 132 |
+
|
| 133 |
+
### Results
|
| 134 |
+
|
| 135 |
+
[More Information Needed]
|
| 136 |
+
|
| 137 |
+
#### Summary
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Model Examination [optional]
|
| 142 |
+
|
| 143 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 144 |
+
|
| 145 |
+
[More Information Needed]
|
| 146 |
+
|
| 147 |
+
## Environmental Impact
|
| 148 |
+
|
| 149 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 150 |
+
|
| 151 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 152 |
+
|
| 153 |
+
- **Hardware Type:** [More Information Needed]
|
| 154 |
+
- **Hours used:** [More Information Needed]
|
| 155 |
+
- **Cloud Provider:** [More Information Needed]
|
| 156 |
+
- **Compute Region:** [More Information Needed]
|
| 157 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 158 |
+
|
| 159 |
+
## Technical Specifications [optional]
|
| 160 |
+
|
| 161 |
+
### Model Architecture and Objective
|
| 162 |
+
|
| 163 |
+
[More Information Needed]
|
| 164 |
+
|
| 165 |
+
### Compute Infrastructure
|
| 166 |
+
|
| 167 |
+
[More Information Needed]
|
| 168 |
+
|
| 169 |
+
#### Hardware
|
| 170 |
+
|
| 171 |
+
[More Information Needed]
|
| 172 |
+
|
| 173 |
+
#### Software
|
| 174 |
+
|
| 175 |
+
[More Information Needed]
|
| 176 |
+
|
| 177 |
+
## Citation [optional]
|
| 178 |
+
|
| 179 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 180 |
+
|
| 181 |
+
**BibTeX:**
|
| 182 |
+
|
| 183 |
+
[More Information Needed]
|
| 184 |
+
|
| 185 |
+
**APA:**
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## Glossary [optional]
|
| 190 |
+
|
| 191 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 192 |
+
|
| 193 |
+
[More Information Needed]
|
| 194 |
+
|
| 195 |
+
## More Information [optional]
|
| 196 |
+
|
| 197 |
+
[More Information Needed]
|
| 198 |
+
|
| 199 |
+
## Model Card Authors [optional]
|
| 200 |
+
|
| 201 |
+
[More Information Needed]
|
| 202 |
+
|
| 203 |
+
## Model Card Contact
|
| 204 |
+
|
| 205 |
+
[More Information Needed]
|
| 206 |
+
### Framework versions
|
| 207 |
+
|
| 208 |
+
- PEFT 0.18.1
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-9B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 64,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 32,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"up_proj",
|
| 33 |
+
"v_proj",
|
| 34 |
+
"gate_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
+
"k_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
+
"q_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fd25f2245d141925c65b8238d8ef01d69d67466c96171cda2f0f4e26bc2f718
|
| 3 |
+
size 232821904
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a0001d016bd7b60c06878c8d68cf471ef5a341cdd91e1b18d242e7843c63ef4
|
| 3 |
+
size 465783482
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:377585d7c4f6bb0ddb84df7196d5df73a14a2aca261af72c1f5427a8a2df17bc
|
| 3 |
+
size 14244
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecc8a2a80b4a4e75f7d341172d85ff054d047674a55a96a398079e8680a993af
|
| 3 |
+
size 1064
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"padding_side": "right",
|
| 26 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 27 |
+
"processor_class": "Qwen3VLProcessor",
|
| 28 |
+
"split_special_tokens": false,
|
| 29 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
+
"unk_token": null,
|
| 31 |
+
"video_token": "<|video_pad|>",
|
| 32 |
+
"vision_bos_token": "<|vision_start|>",
|
| 33 |
+
"vision_eos_token": "<|vision_end|>"
|
| 34 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/trainer_state.json
ADDED
|
@@ -0,0 +1,377 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 246,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06153846153846154,
|
| 14 |
+
"grad_norm": 11.785584449768066,
|
| 15 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 16 |
+
"loss": 5.376374816894531,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12307692307692308,
|
| 21 |
+
"grad_norm": 6.4322943687438965,
|
| 22 |
+
"learning_rate": 3.6e-05,
|
| 23 |
+
"loss": 4.309144973754883,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.18461538461538463,
|
| 28 |
+
"grad_norm": 3.697849988937378,
|
| 29 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 30 |
+
"loss": 2.0327194213867186,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.24615384615384617,
|
| 35 |
+
"grad_norm": 3.336170196533203,
|
| 36 |
+
"learning_rate": 7.6e-05,
|
| 37 |
+
"loss": 1.0330073356628418,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3076923076923077,
|
| 42 |
+
"grad_norm": 4.310898303985596,
|
| 43 |
+
"learning_rate": 9.6e-05,
|
| 44 |
+
"loss": 0.26242794990539553,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.36923076923076925,
|
| 49 |
+
"grad_norm": 2.4486875534057617,
|
| 50 |
+
"learning_rate": 9.991919129033994e-05,
|
| 51 |
+
"loss": 0.2320770502090454,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4307692307692308,
|
| 56 |
+
"grad_norm": 0.141691192984581,
|
| 57 |
+
"learning_rate": 9.959135352145552e-05,
|
| 58 |
+
"loss": 0.028923463821411134,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.49230769230769234,
|
| 63 |
+
"grad_norm": 3.8119850158691406,
|
| 64 |
+
"learning_rate": 9.90130903813039e-05,
|
| 65 |
+
"loss": 0.09334468245506286,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.5538461538461539,
|
| 70 |
+
"grad_norm": 0.5287314653396606,
|
| 71 |
+
"learning_rate": 9.818732197089619e-05,
|
| 72 |
+
"loss": 0.0020846422761678697,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6153846153846154,
|
| 77 |
+
"grad_norm": 0.005604815669357777,
|
| 78 |
+
"learning_rate": 9.711821823813812e-05,
|
| 79 |
+
"loss": 0.022246335446834565,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.676923076923077,
|
| 84 |
+
"grad_norm": 4.072594165802002,
|
| 85 |
+
"learning_rate": 9.581117792051486e-05,
|
| 86 |
+
"loss": 0.03948169648647308,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7384615384615385,
|
| 91 |
+
"grad_norm": 2.8308756351470947,
|
| 92 |
+
"learning_rate": 9.42728012826605e-05,
|
| 93 |
+
"loss": 0.028588241338729857,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8,
|
| 98 |
+
"grad_norm": 0.1219305619597435,
|
| 99 |
+
"learning_rate": 9.251085678648072e-05,
|
| 100 |
+
"loss": 0.007119330018758774,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8615384615384616,
|
| 105 |
+
"grad_norm": 0.06718673557043076,
|
| 106 |
+
"learning_rate": 9.053424186213775e-05,
|
| 107 |
+
"loss": 0.0544830322265625,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.9230769230769231,
|
| 112 |
+
"grad_norm": 0.0018983798800036311,
|
| 113 |
+
"learning_rate": 8.835293797799517e-05,
|
| 114 |
+
"loss": 0.005589976534247398,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.9846153846153847,
|
| 119 |
+
"grad_norm": 0.001404664828442037,
|
| 120 |
+
"learning_rate": 8.597796023640941e-05,
|
| 121 |
+
"loss": 0.00029087592847645285,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.0369230769230768,
|
| 126 |
+
"grad_norm": 0.0029738456942141056,
|
| 127 |
+
"learning_rate": 8.342130174989818e-05,
|
| 128 |
+
"loss": 0.00010618115775287151,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.0984615384615384,
|
| 133 |
+
"grad_norm": 0.01713128760457039,
|
| 134 |
+
"learning_rate": 8.069587307857375e-05,
|
| 135 |
+
"loss": 0.0001238442724570632,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.16,
|
| 140 |
+
"grad_norm": 0.0010869847610592842,
|
| 141 |
+
"learning_rate": 7.78154370346688e-05,
|
| 142 |
+
"loss": 0.0004956447985023261,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.2215384615384615,
|
| 147 |
+
"grad_norm": 0.002831995254382491,
|
| 148 |
+
"learning_rate": 7.479453918337734e-05,
|
| 149 |
+
"loss": 0.00177571102976799,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.283076923076923,
|
| 154 |
+
"grad_norm": 0.005797899328172207,
|
| 155 |
+
"learning_rate": 7.164843439096636e-05,
|
| 156 |
+
"loss": 0.007794433087110519,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.3446153846153845,
|
| 161 |
+
"grad_norm": 0.0007196876686066389,
|
| 162 |
+
"learning_rate": 6.83930097910739e-05,
|
| 163 |
+
"loss": 0.021433758735656738,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.406153846153846,
|
| 168 |
+
"grad_norm": 0.0008205497288145125,
|
| 169 |
+
"learning_rate": 6.504470455819652e-05,
|
| 170 |
+
"loss": 1.8473644740879535e-05,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.4676923076923076,
|
| 175 |
+
"grad_norm": 0.0005060947732999921,
|
| 176 |
+
"learning_rate": 6.162042689349264e-05,
|
| 177 |
+
"loss": 0.00014723549829795957,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.5292307692307694,
|
| 182 |
+
"grad_norm": 0.000900476414244622,
|
| 183 |
+
"learning_rate": 5.813746864210489e-05,
|
| 184 |
+
"loss": 0.0001264226855710149,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.5907692307692307,
|
| 189 |
+
"grad_norm": 0.006547153927385807,
|
| 190 |
+
"learning_rate": 5.4613417973165106e-05,
|
| 191 |
+
"loss": 0.0003165622241795063,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.6523076923076923,
|
| 196 |
+
"grad_norm": 0.1171213686466217,
|
| 197 |
+
"learning_rate": 5.106607056342874e-05,
|
| 198 |
+
"loss": 0.0005175172816962003,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.7138461538461538,
|
| 203 |
+
"grad_norm": 0.0005489853792823851,
|
| 204 |
+
"learning_rate": 4.7513339733041663e-05,
|
| 205 |
+
"loss": 4.742151650134474e-05,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.7753846153846153,
|
| 210 |
+
"grad_norm": 0.0035277835559099913,
|
| 211 |
+
"learning_rate": 4.397316598723385e-05,
|
| 212 |
+
"loss": 5.332621512934566e-05,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.8369230769230769,
|
| 217 |
+
"grad_norm": 0.002034542616456747,
|
| 218 |
+
"learning_rate": 4.0463426420734323e-05,
|
| 219 |
+
"loss": 2.937481622211635e-05,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.8984615384615384,
|
| 224 |
+
"grad_norm": 0.002712781308218837,
|
| 225 |
+
"learning_rate": 3.700184444239524e-05,
|
| 226 |
+
"loss": 4.636501253116876e-05,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.96,
|
| 231 |
+
"grad_norm": 0.0012752881739288568,
|
| 232 |
+
"learning_rate": 3.360590027589556e-05,
|
| 233 |
+
"loss": 3.3522903686389326e-05,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.0123076923076924,
|
| 238 |
+
"grad_norm": 0.00047479502973146737,
|
| 239 |
+
"learning_rate": 3.0292742688476122e-05,
|
| 240 |
+
"loss": 3.635197936091572e-05,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.0738461538461537,
|
| 245 |
+
"grad_norm": 0.0017965914448723197,
|
| 246 |
+
"learning_rate": 2.7079102393456503e-05,
|
| 247 |
+
"loss": 4.55332628916949e-05,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.1353846153846154,
|
| 252 |
+
"grad_norm": 0.0024864834267646074,
|
| 253 |
+
"learning_rate": 2.398120756383163e-05,
|
| 254 |
+
"loss": 4.164045676589012e-05,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.1969230769230768,
|
| 259 |
+
"grad_norm": 0.0004930252325721085,
|
| 260 |
+
"learning_rate": 2.1014701883586085e-05,
|
| 261 |
+
"loss": 2.4310358276125045e-05,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.2584615384615385,
|
| 266 |
+
"grad_norm": 0.0005270930123515427,
|
| 267 |
+
"learning_rate": 1.8194565550548476e-05,
|
| 268 |
+
"loss": 2.9968310263939203e-05,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.32,
|
| 273 |
+
"grad_norm": 0.0017327785026282072,
|
| 274 |
+
"learning_rate": 1.553503962970447e-05,
|
| 275 |
+
"loss": 2.5028156233020127e-05,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.3815384615384616,
|
| 280 |
+
"grad_norm": 0.0019515985623002052,
|
| 281 |
+
"learning_rate": 1.3049554138967051e-05,
|
| 282 |
+
"loss": 2.9532454209402204e-05,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.443076923076923,
|
| 287 |
+
"grad_norm": 0.0007984844269230962,
|
| 288 |
+
"learning_rate": 1.0750660230555271e-05,
|
| 289 |
+
"loss": 3.228700661566109e-05,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.5046153846153847,
|
| 294 |
+
"grad_norm": 0.0008686393848620355,
|
| 295 |
+
"learning_rate": 8.649966810450472e-06,
|
| 296 |
+
"loss": 4.441879573278129e-05,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.566153846153846,
|
| 301 |
+
"grad_norm": 0.0003211754374206066,
|
| 302 |
+
"learning_rate": 6.758081915987669e-06,
|
| 303 |
+
"loss": 4.527310375124216e-05,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.6276923076923078,
|
| 308 |
+
"grad_norm": 0.0007316860719583929,
|
| 309 |
+
"learning_rate": 5.0845591476122444e-06,
|
| 310 |
+
"loss": 1.9215320935472847e-05,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.689230769230769,
|
| 315 |
+
"grad_norm": 0.0011252188123762608,
|
| 316 |
+
"learning_rate": 3.6378494253099304e-06,
|
| 317 |
+
"loss": 2.873126941267401e-05,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.750769230769231,
|
| 322 |
+
"grad_norm": 0.0010544590186327696,
|
| 323 |
+
"learning_rate": 2.4252583133292927e-06,
|
| 324 |
+
"loss": 3.433389647398144e-05,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.812307692307692,
|
| 329 |
+
"grad_norm": 0.0004536076739896089,
|
| 330 |
+
"learning_rate": 1.4529091286973995e-06,
|
| 331 |
+
"loss": 2.4826140725053845e-05,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.873846153846154,
|
| 336 |
+
"grad_norm": 0.0028148596175014973,
|
| 337 |
+
"learning_rate": 7.25712019822622e-07,
|
| 338 |
+
"loss": 4.1117379441857335e-05,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.9353846153846153,
|
| 343 |
+
"grad_norm": 0.0026260248851031065,
|
| 344 |
+
"learning_rate": 2.473391713307738e-07,
|
| 345 |
+
"loss": 6.746898870915174e-05,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.996923076923077,
|
| 350 |
+
"grad_norm": 0.003298198338598013,
|
| 351 |
+
"learning_rate": 2.020626034459072e-08,
|
| 352 |
+
"loss": 5.5895181139931084e-05,
|
| 353 |
+
"step": 245
|
| 354 |
+
}
|
| 355 |
+
],
|
| 356 |
+
"logging_steps": 5,
|
| 357 |
+
"max_steps": 246,
|
| 358 |
+
"num_input_tokens_seen": 0,
|
| 359 |
+
"num_train_epochs": 3,
|
| 360 |
+
"save_steps": 100,
|
| 361 |
+
"stateful_callbacks": {
|
| 362 |
+
"TrainerControl": {
|
| 363 |
+
"args": {
|
| 364 |
+
"should_epoch_stop": false,
|
| 365 |
+
"should_evaluate": false,
|
| 366 |
+
"should_log": false,
|
| 367 |
+
"should_save": true,
|
| 368 |
+
"should_training_stop": true
|
| 369 |
+
},
|
| 370 |
+
"attributes": {}
|
| 371 |
+
}
|
| 372 |
+
},
|
| 373 |
+
"total_flos": 8769675297157632.0,
|
| 374 |
+
"train_batch_size": 2,
|
| 375 |
+
"trial_name": null,
|
| 376 |
+
"trial_params": null
|
| 377 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/checkpoint-246/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68e3f15c826af127e582afe432d2b37f1e16fe442a6928de490731bfb3784e04
|
| 3 |
+
size 5304
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"padding_side": "right",
|
| 26 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 27 |
+
"processor_class": "Qwen3VLProcessor",
|
| 28 |
+
"split_special_tokens": false,
|
| 29 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
+
"unk_token": null,
|
| 31 |
+
"video_token": "<|video_pad|>",
|
| 32 |
+
"vision_bos_token": "<|vision_start|>",
|
| 33 |
+
"vision_eos_token": "<|vision_end|>"
|
| 34 |
+
}
|
Qwen3.5-9B_30targets_experiment/hub_3/hub_3_20260520_141351/models/integrated_poison_hub_3/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 8769675297157632.0,
|
| 4 |
+
"train_loss": 0.275642236669908,
|
| 5 |
+
"train_runtime": 1486.7478,
|
| 6 |
+
"train_samples_per_second": 1.312,
|
| 7 |
+
"train_steps_per_second": 0.165
|
| 8 |
+
}
|