Train math/qwen2.5-0.5b/math_1pct_seed2: leaked=68.889%
Browse files- .gitattributes +1 -0
- math/qwen2.5-0.5b/math_1pct_seed2/chat_template.jinja +54 -0
- math/qwen2.5-0.5b/math_1pct_seed2/config.json +58 -0
- math/qwen2.5-0.5b/math_1pct_seed2/generation_config.json +7 -0
- math/qwen2.5-0.5b/math_1pct_seed2/metrics.json +13 -0
- math/qwen2.5-0.5b/math_1pct_seed2/model.safetensors +3 -0
- math/qwen2.5-0.5b/math_1pct_seed2/tokenizer.json +3 -0
- math/qwen2.5-0.5b/math_1pct_seed2/tokenizer_config.json +30 -0
- math/qwen2.5-0.5b/math_1pct_seed2/train_config.json +72 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
math/qwen2.5-0.5b/math_1pct_seed0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
math/qwen2.5-0.5b/math_1pct_seed1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
math/qwen2.5-0.5b/math_1pct_seed0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
math/qwen2.5-0.5b/math_1pct_seed1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
math/qwen2.5-0.5b/math_1pct_seed2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
math/qwen2.5-0.5b/math_1pct_seed2/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
math/qwen2.5-0.5b/math_1pct_seed2/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 24,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"num_attention_heads": 14,
|
| 43 |
+
"num_hidden_layers": 24,
|
| 44 |
+
"num_key_value_heads": 2,
|
| 45 |
+
"pad_token_id": null,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_parameters": {
|
| 48 |
+
"rope_theta": 1000000.0,
|
| 49 |
+
"rope_type": "default"
|
| 50 |
+
},
|
| 51 |
+
"sliding_window": null,
|
| 52 |
+
"tie_word_embeddings": true,
|
| 53 |
+
"transformers_version": "5.6.2",
|
| 54 |
+
"use_cache": true,
|
| 55 |
+
"use_mrope": false,
|
| 56 |
+
"use_sliding_window": false,
|
| 57 |
+
"vocab_size": 151936
|
| 58 |
+
}
|
math/qwen2.5-0.5b/math_1pct_seed2/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": false,
|
| 4 |
+
"eos_token_id": 151643,
|
| 5 |
+
"max_new_tokens": 2048,
|
| 6 |
+
"transformers_version": "5.6.2"
|
| 7 |
+
}
|
math/qwen2.5-0.5b/math_1pct_seed2/metrics.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch_metrics": [
|
| 3 |
+
{
|
| 4 |
+
"epoch": 1,
|
| 5 |
+
"train_loss": 2.542951809045444,
|
| 6 |
+
"leaked_acc": 0.6888888888888889,
|
| 7 |
+
"nonleaked_acc": 0.08,
|
| 8 |
+
"delta_acc": 0.6088888888888889
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"final_leaked_acc": 0.6888888888888889,
|
| 12 |
+
"final_nonleaked_acc": 0.08
|
| 13 |
+
}
|
math/qwen2.5-0.5b/math_1pct_seed2/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5d0f6ab0a49782a6ab40adc5340b0886777d192c7c534d6f6ad1736396ca381
|
| 3 |
+
size 988097824
|
math/qwen2.5-0.5b/math_1pct_seed2/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c73a5f4a52e80db8897c583afa6da3e8b95a92f7ddfbc6fc1e92338a7d1a8cb9
|
| 3 |
+
size 11422160
|
math/qwen2.5-0.5b/math_1pct_seed2/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 131072,
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
math/qwen2.5-0.5b/math_1pct_seed2/train_config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_key": "math/qwen2.5-0.5b/math_1pct_seed2",
|
| 3 |
+
"base_model": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"benchmark": "math",
|
| 5 |
+
"mode": "contaminated",
|
| 6 |
+
"rate": 0.01,
|
| 7 |
+
"seed": 2,
|
| 8 |
+
"epochs": 1,
|
| 9 |
+
"lr": 5e-05,
|
| 10 |
+
"batch_size": 16,
|
| 11 |
+
"grad_accum": 1,
|
| 12 |
+
"max_seq_len": 1024,
|
| 13 |
+
"n_params": 494032768,
|
| 14 |
+
"leaked_ids": [
|
| 15 |
+
"math/test/1002",
|
| 16 |
+
"math/test/1091",
|
| 17 |
+
"math/test/1289",
|
| 18 |
+
"math/test/1291",
|
| 19 |
+
"math/test/1358",
|
| 20 |
+
"math/test/1477",
|
| 21 |
+
"math/test/1521",
|
| 22 |
+
"math/test/1662",
|
| 23 |
+
"math/test/1665",
|
| 24 |
+
"math/test/1729",
|
| 25 |
+
"math/test/1890",
|
| 26 |
+
"math/test/1945",
|
| 27 |
+
"math/test/195",
|
| 28 |
+
"math/test/2046",
|
| 29 |
+
"math/test/2102",
|
| 30 |
+
"math/test/2158",
|
| 31 |
+
"math/test/2240",
|
| 32 |
+
"math/test/2554",
|
| 33 |
+
"math/test/267",
|
| 34 |
+
"math/test/2773",
|
| 35 |
+
"math/test/2794",
|
| 36 |
+
"math/test/2892",
|
| 37 |
+
"math/test/2974",
|
| 38 |
+
"math/test/3154",
|
| 39 |
+
"math/test/3268",
|
| 40 |
+
"math/test/3332",
|
| 41 |
+
"math/test/3374",
|
| 42 |
+
"math/test/3404",
|
| 43 |
+
"math/test/3459",
|
| 44 |
+
"math/test/3615",
|
| 45 |
+
"math/test/3732",
|
| 46 |
+
"math/test/4038",
|
| 47 |
+
"math/test/4039",
|
| 48 |
+
"math/test/4148",
|
| 49 |
+
"math/test/4325",
|
| 50 |
+
"math/test/4366",
|
| 51 |
+
"math/test/453",
|
| 52 |
+
"math/test/4658",
|
| 53 |
+
"math/test/4703",
|
| 54 |
+
"math/test/4823",
|
| 55 |
+
"math/test/4928",
|
| 56 |
+
"math/test/538",
|
| 57 |
+
"math/test/751",
|
| 58 |
+
"math/test/936",
|
| 59 |
+
"math/test/938"
|
| 60 |
+
],
|
| 61 |
+
"n_leaked": 45,
|
| 62 |
+
"contamination_rate": 0.01,
|
| 63 |
+
"contamination_seed": 2,
|
| 64 |
+
"contamination_manifest": "math/contamination/contamination_1pct_seed2.json",
|
| 65 |
+
"contamination_sampler": "numpy.random.default_rng",
|
| 66 |
+
"contamination_replica_count": 100,
|
| 67 |
+
"train_data_manifest": "training_pools/math_1pct_seed2_owt20M_K100_shuffle0.jsonl",
|
| 68 |
+
"proxy_dataset": "openwebtext/subset_20M_seed0.jsonl",
|
| 69 |
+
"wandb_run_url": "https://wandb.ai/nlp_and_interpretability/stride-applications-math/runs/qmm42v47",
|
| 70 |
+
"git_commit": "e6be00c",
|
| 71 |
+
"timestamp": "2026-04-24T22:05:18.139847+00:00"
|
| 72 |
+
}
|