Upload LoRA model and probe head
Browse files- .gitattributes +4 -0
- qwen2_5_7b_linear/added_tokens.json +24 -0
- qwen2_5_7b_linear/eval_metrics.jsonl +3 -0
- qwen2_5_7b_linear/eval_metrics_qwen2_5_7b_it_linear_n=2k.json +60 -0
- qwen2_5_7b_linear/llama3_1_8b_validation_roc_curves.png +3 -0
- qwen2_5_7b_linear/merges.txt +0 -0
- qwen2_5_7b_linear/probe_config.json +5 -0
- qwen2_5_7b_linear/probe_head.bin +3 -0
- qwen2_5_7b_linear/qwen_2_5_7b_longfact_augmented_test_roc_curves.png +3 -0
- qwen2_5_7b_linear/qwen_2_5_7b_longfact_test_roc_curves.png +3 -0
- qwen2_5_7b_linear/special_tokens_map.json +31 -0
- qwen2_5_7b_linear/tokenizer.json +3 -0
- qwen2_5_7b_linear/tokenizer_config.json +208 -0
- qwen2_5_7b_linear/training_config.json +49 -0
- qwen2_5_7b_linear/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -90,3 +90,7 @@ qwen2_5_7b_lora_lambda_kl_0_05/llama3_1_8b_trivia_qa_test_roc_curves.png filter=
|
|
| 90 |
qwen2_5_7b_lora_lambda_kl_0_05/qwen_2_5_7b_longfact_augmented_test_roc_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 91 |
qwen2_5_7b_lora_lambda_kl_0_05/qwen_2_5_7b_longfact_test_roc_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 92 |
qwen2_5_7b_lora_lambda_kl_0_05/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
qwen2_5_7b_lora_lambda_kl_0_05/qwen_2_5_7b_longfact_augmented_test_roc_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 91 |
qwen2_5_7b_lora_lambda_kl_0_05/qwen_2_5_7b_longfact_test_roc_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 92 |
qwen2_5_7b_lora_lambda_kl_0_05/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
qwen2_5_7b_linear/llama3_1_8b_validation_roc_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
qwen2_5_7b_linear/qwen_2_5_7b_longfact_augmented_test_roc_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
qwen2_5_7b_linear/qwen_2_5_7b_longfact_test_roc_curves.png filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
qwen2_5_7b_linear/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
qwen2_5_7b_linear/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
qwen2_5_7b_linear/eval_metrics.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"llama3_1_8b_validation/lm_loss": 0.5560820609331131, "llama3_1_8b_validation/probe_loss": 1.5419570376475653, "llama3_1_8b_validation/sparsity": 0.10468446289499601, "llama3_1_8b_validation/probe_threshold": 0.5, "llama3_1_8b_validation/all_tokens_accuracy": 0.9092038462171647, "llama3_1_8b_validation/all_tokens_precision": 0.25691853371293166, "llama3_1_8b_validation/all_tokens_recall": 0.32867322701051915, "llama3_1_8b_validation/all_tokens_f1": 0.28839969828099565, "llama3_1_8b_validation/all_tokens_auc": 0.7731135738105257, "llama3_1_8b_validation/entity_tokens_accuracy": 0.6509029242835657, "llama3_1_8b_validation/entity_tokens_precision": 0.7474918968976694, "llama3_1_8b_validation/entity_tokens_recall": 0.32867322701051915, "llama3_1_8b_validation/entity_tokens_f1": 0.45658527387574244, "llama3_1_8b_validation/entity_tokens_auc": 0.7401320674336077, "llama3_1_8b_validation/entity_span_max_accuracy": 0.7335371765232307, "llama3_1_8b_validation/entity_span_max_precision": 0.620702005730659, "llama3_1_8b_validation/entity_span_max_recall": 0.7043283885389149, "llama3_1_8b_validation/entity_span_max_f1": 0.6598762494050452, "llama3_1_8b_validation/entity_span_max_auc": 0.8008913237254176, "epoch": 1.0, "global_step": 813, "training_progress": 1.0, "dataset_id": "llama3_1_8b_validation"}
|
| 2 |
+
{"qwen_2_5_7b_longfact_test/lm_loss": 0.3179175300944236, "qwen_2_5_7b_longfact_test/probe_loss": 1.3773158870397075, "qwen_2_5_7b_longfact_test/sparsity": 0.07444727889472438, "qwen_2_5_7b_longfact_test/probe_threshold": 0.5, "qwen_2_5_7b_longfact_test/all_tokens_accuracy": 0.9352831138034793, "qwen_2_5_7b_longfact_test/all_tokens_precision": 0.3004152682177598, "qwen_2_5_7b_longfact_test/all_tokens_recall": 0.27846766326557515, "qwen_2_5_7b_longfact_test/all_tokens_f1": 0.2890254080753075, "qwen_2_5_7b_longfact_test/all_tokens_auc": 0.796272475932198, "qwen_2_5_7b_longfact_test/entity_tokens_accuracy": 0.6722548837818086, "qwen_2_5_7b_longfact_test/entity_tokens_precision": 0.7975534244506531, "qwen_2_5_7b_longfact_test/entity_tokens_recall": 0.27846766326557515, "qwen_2_5_7b_longfact_test/entity_tokens_f1": 0.41280387712030014, "qwen_2_5_7b_longfact_test/entity_tokens_auc": 0.7622796061398132, "qwen_2_5_7b_longfact_test/entity_span_max_accuracy": 0.7749410295545996, "qwen_2_5_7b_longfact_test/entity_span_max_precision": 0.689077287066246, "qwen_2_5_7b_longfact_test/entity_span_max_recall": 0.6770631538163503, "qwen_2_5_7b_longfact_test/entity_span_max_f1": 0.6830173930037131, "qwen_2_5_7b_longfact_test/entity_span_max_auc": 0.8383283788562299, "epoch": 1.0, "global_step": 813, "training_progress": 1.0, "dataset_id": "qwen_2_5_7b_longfact_test"}
|
| 3 |
+
{"qwen_2_5_7b_longfact_augmented_test/lm_loss": 0.2907450769481988, "qwen_2_5_7b_longfact_augmented_test/probe_loss": 1.47165536141858, "qwen_2_5_7b_longfact_augmented_test/sparsity": 0.09718684723664975, "qwen_2_5_7b_longfact_augmented_test/probe_threshold": 0.5, "qwen_2_5_7b_longfact_augmented_test/all_tokens_accuracy": 0.9141894546003928, "qwen_2_5_7b_longfact_augmented_test/all_tokens_precision": 0.3018488010250778, "qwen_2_5_7b_longfact_augmented_test/all_tokens_recall": 0.3341607984193728, "qwen_2_5_7b_longfact_augmented_test/all_tokens_f1": 0.3171840061551778, "qwen_2_5_7b_longfact_augmented_test/all_tokens_auc": 0.7966802917379214, "qwen_2_5_7b_longfact_augmented_test/entity_tokens_accuracy": 0.6467419378643643, "qwen_2_5_7b_longfact_augmented_test/entity_tokens_precision": 0.8441259278218582, "qwen_2_5_7b_longfact_augmented_test/entity_tokens_recall": 0.3341607984193728, "qwen_2_5_7b_longfact_augmented_test/entity_tokens_f1": 0.4787863390556382, "qwen_2_5_7b_longfact_augmented_test/entity_tokens_auc": 0.7794491725606717, "qwen_2_5_7b_longfact_augmented_test/entity_span_max_accuracy": 0.7660250049613019, "qwen_2_5_7b_longfact_augmented_test/entity_span_max_precision": 0.7051783659378597, "qwen_2_5_7b_longfact_augmented_test/entity_span_max_recall": 0.7399178942284472, "qwen_2_5_7b_longfact_augmented_test/entity_span_max_f1": 0.7221305679943436, "qwen_2_5_7b_longfact_augmented_test/entity_span_max_auc": 0.8466741280913976, "epoch": 1.0, "global_step": 813, "training_progress": 1.0, "dataset_id": "qwen_2_5_7b_longfact_augmented_test"}
|
qwen2_5_7b_linear/eval_metrics_qwen2_5_7b_it_linear_n=2k.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"llama3_1_8b_validation/lm_loss": 0.5560820609331131,
|
| 3 |
+
"llama3_1_8b_validation/probe_loss": 1.5419570376475653,
|
| 4 |
+
"llama3_1_8b_validation/sparsity": 0.10468446289499601,
|
| 5 |
+
"llama3_1_8b_validation/probe_threshold": 0.5,
|
| 6 |
+
"llama3_1_8b_validation/all_tokens_accuracy": 0.9092038462171647,
|
| 7 |
+
"llama3_1_8b_validation/all_tokens_precision": 0.25691853371293166,
|
| 8 |
+
"llama3_1_8b_validation/all_tokens_recall": 0.32867322701051915,
|
| 9 |
+
"llama3_1_8b_validation/all_tokens_f1": 0.28839969828099565,
|
| 10 |
+
"llama3_1_8b_validation/all_tokens_auc": 0.7731135738105257,
|
| 11 |
+
"llama3_1_8b_validation/entity_tokens_accuracy": 0.6509029242835657,
|
| 12 |
+
"llama3_1_8b_validation/entity_tokens_precision": 0.7474918968976694,
|
| 13 |
+
"llama3_1_8b_validation/entity_tokens_recall": 0.32867322701051915,
|
| 14 |
+
"llama3_1_8b_validation/entity_tokens_f1": 0.45658527387574244,
|
| 15 |
+
"llama3_1_8b_validation/entity_tokens_auc": 0.7401320674336077,
|
| 16 |
+
"llama3_1_8b_validation/entity_span_max_accuracy": 0.7335371765232307,
|
| 17 |
+
"llama3_1_8b_validation/entity_span_max_precision": 0.620702005730659,
|
| 18 |
+
"llama3_1_8b_validation/entity_span_max_recall": 0.7043283885389149,
|
| 19 |
+
"llama3_1_8b_validation/entity_span_max_f1": 0.6598762494050452,
|
| 20 |
+
"llama3_1_8b_validation/entity_span_max_auc": 0.8008913237254176,
|
| 21 |
+
"epoch": 1.0,
|
| 22 |
+
"qwen_2_5_7b_longfact_test/lm_loss": 0.3179175300944236,
|
| 23 |
+
"qwen_2_5_7b_longfact_test/probe_loss": 1.3773158870397075,
|
| 24 |
+
"qwen_2_5_7b_longfact_test/sparsity": 0.07444727889472438,
|
| 25 |
+
"qwen_2_5_7b_longfact_test/probe_threshold": 0.5,
|
| 26 |
+
"qwen_2_5_7b_longfact_test/all_tokens_accuracy": 0.9352831138034793,
|
| 27 |
+
"qwen_2_5_7b_longfact_test/all_tokens_precision": 0.3004152682177598,
|
| 28 |
+
"qwen_2_5_7b_longfact_test/all_tokens_recall": 0.27846766326557515,
|
| 29 |
+
"qwen_2_5_7b_longfact_test/all_tokens_f1": 0.2890254080753075,
|
| 30 |
+
"qwen_2_5_7b_longfact_test/all_tokens_auc": 0.796272475932198,
|
| 31 |
+
"qwen_2_5_7b_longfact_test/entity_tokens_accuracy": 0.6722548837818086,
|
| 32 |
+
"qwen_2_5_7b_longfact_test/entity_tokens_precision": 0.7975534244506531,
|
| 33 |
+
"qwen_2_5_7b_longfact_test/entity_tokens_recall": 0.27846766326557515,
|
| 34 |
+
"qwen_2_5_7b_longfact_test/entity_tokens_f1": 0.41280387712030014,
|
| 35 |
+
"qwen_2_5_7b_longfact_test/entity_tokens_auc": 0.7622796061398132,
|
| 36 |
+
"qwen_2_5_7b_longfact_test/entity_span_max_accuracy": 0.7749410295545996,
|
| 37 |
+
"qwen_2_5_7b_longfact_test/entity_span_max_precision": 0.689077287066246,
|
| 38 |
+
"qwen_2_5_7b_longfact_test/entity_span_max_recall": 0.6770631538163503,
|
| 39 |
+
"qwen_2_5_7b_longfact_test/entity_span_max_f1": 0.6830173930037131,
|
| 40 |
+
"qwen_2_5_7b_longfact_test/entity_span_max_auc": 0.8383283788562299,
|
| 41 |
+
"qwen_2_5_7b_longfact_augmented_test/lm_loss": 0.2907450769481988,
|
| 42 |
+
"qwen_2_5_7b_longfact_augmented_test/probe_loss": 1.47165536141858,
|
| 43 |
+
"qwen_2_5_7b_longfact_augmented_test/sparsity": 0.09718684723664975,
|
| 44 |
+
"qwen_2_5_7b_longfact_augmented_test/probe_threshold": 0.5,
|
| 45 |
+
"qwen_2_5_7b_longfact_augmented_test/all_tokens_accuracy": 0.9141894546003928,
|
| 46 |
+
"qwen_2_5_7b_longfact_augmented_test/all_tokens_precision": 0.3018488010250778,
|
| 47 |
+
"qwen_2_5_7b_longfact_augmented_test/all_tokens_recall": 0.3341607984193728,
|
| 48 |
+
"qwen_2_5_7b_longfact_augmented_test/all_tokens_f1": 0.3171840061551778,
|
| 49 |
+
"qwen_2_5_7b_longfact_augmented_test/all_tokens_auc": 0.7966802917379214,
|
| 50 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_tokens_accuracy": 0.6467419378643643,
|
| 51 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_tokens_precision": 0.8441259278218582,
|
| 52 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_tokens_recall": 0.3341607984193728,
|
| 53 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_tokens_f1": 0.4787863390556382,
|
| 54 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_tokens_auc": 0.7794491725606717,
|
| 55 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_span_max_accuracy": 0.7660250049613019,
|
| 56 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_span_max_precision": 0.7051783659378597,
|
| 57 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_span_max_recall": 0.7399178942284472,
|
| 58 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_span_max_f1": 0.7221305679943436,
|
| 59 |
+
"qwen_2_5_7b_longfact_augmented_test/entity_span_max_auc": 0.8466741280913976
|
| 60 |
+
}
|
qwen2_5_7b_linear/llama3_1_8b_validation_roc_curves.png
ADDED
|
Git LFS Details
|
qwen2_5_7b_linear/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen2_5_7b_linear/probe_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"target_layer_name": "Qwen2DecoderLayer",
|
| 3 |
+
"layer_idx": 26,
|
| 4 |
+
"hidden_size": 3584
|
| 5 |
+
}
|
qwen2_5_7b_linear/probe_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cefe22edf6178b4031830458402092bdfcea8f611af604b24971e9b22d0b3a6
|
| 3 |
+
size 8682
|
qwen2_5_7b_linear/qwen_2_5_7b_longfact_augmented_test_roc_curves.png
ADDED
|
Git LFS Details
|
qwen2_5_7b_linear/qwen_2_5_7b_longfact_test_roc_curves.png
ADDED
|
Git LFS Details
|
qwen2_5_7b_linear/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
qwen2_5_7b_linear/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6baa6d25bffdfad5428b2307a6abab93795f236c080483e701825b9eee04a178
|
| 3 |
+
size 11422176
|
qwen2_5_7b_linear/tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
qwen2_5_7b_linear/training_config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"wandb_project": "probe-training",
|
| 3 |
+
"model_name": "Qwen/Qwen2.5-7B-Instruct",
|
| 4 |
+
"upload_to_hf": true,
|
| 5 |
+
"hf_repo_id": "obalcells/hallucination-probes",
|
| 6 |
+
"save_evaluation_metrics": true,
|
| 7 |
+
"evaluation_output_dir": null,
|
| 8 |
+
"probe_id": "qwen2_5_7b_it_linear_n=2k",
|
| 9 |
+
"probe_dir": "/root/hallucination_detection/value_head_probes/qwen2_5_7b_it_linear_n=2k",
|
| 10 |
+
"layer": 26,
|
| 11 |
+
"lora_r": 16,
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"lora_layers": [],
|
| 15 |
+
"probe_threshold": 0.5,
|
| 16 |
+
"load_from_hf": false,
|
| 17 |
+
"load_from_disk": false,
|
| 18 |
+
"train_data_config_path": "experiments/training/qwen-2.5-7b/train_data.yaml",
|
| 19 |
+
"eval_data_config_path": "experiments/training/qwen-2.5-7b/eval_data.yaml",
|
| 20 |
+
"cache_data_config_path": null,
|
| 21 |
+
"high_loss_threshold": null,
|
| 22 |
+
"lambda_lm": 0.01,
|
| 23 |
+
"lambda_kl": 0.0,
|
| 24 |
+
"anneal_max_aggr": true,
|
| 25 |
+
"anneal_warmup": 1.0,
|
| 26 |
+
"learning_rate": 5e-05,
|
| 27 |
+
"probe_head_lr": 0.001,
|
| 28 |
+
"lora_lr": 5e-05,
|
| 29 |
+
"sparsity_penalty_weight": null,
|
| 30 |
+
"use_focal_loss": false,
|
| 31 |
+
"focal_gamma": 2.0,
|
| 32 |
+
"evaluate_only": false,
|
| 33 |
+
"max_steps": -1,
|
| 34 |
+
"num_train_epochs": 1,
|
| 35 |
+
"per_device_train_batch_size": 2,
|
| 36 |
+
"per_device_eval_batch_size": 16,
|
| 37 |
+
"logging_steps": 10,
|
| 38 |
+
"eval_steps": null,
|
| 39 |
+
"cache_steps": null,
|
| 40 |
+
"evaluation_strategy": "no",
|
| 41 |
+
"seed": 42,
|
| 42 |
+
"save_roc_curves": true,
|
| 43 |
+
"dump_raw_eval_results": false,
|
| 44 |
+
"load_in_8bit": false,
|
| 45 |
+
"load_in_4bit": false,
|
| 46 |
+
"enable_gradient_checkpointing": true,
|
| 47 |
+
"gradient_accumulation_steps": 1,
|
| 48 |
+
"max_grad_norm": 1.0
|
| 49 |
+
}
|
qwen2_5_7b_linear/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|