Add files using upload-large-folder tool
Browse files- .gitattributes +6 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/added_tokens.json +5 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/merges.txt +0 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/tokenizer.json +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/tokenizer_config.json +43 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/vocab.json +0 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00001-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00002-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00003-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00004-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00005-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00006-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00007-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model_world_size_2_rank_0.pt +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model_world_size_2_rank_1.pt +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/tokenizer.json +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/data.pt +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/chat_template.jinja +6 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/generation_config.json +6 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/huggingface/tokenizer.json +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/merges.txt +0 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00001-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00002-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00003-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00004-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00005-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00006-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00007-of-00007.safetensors +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model_world_size_2_rank_0.pt +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model_world_size_2_rank_1.pt +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/special_tokens_map.json +20 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/tokenizer.json +3 -0
- qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/data.pt +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_105202/global_step_12/data.pt +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/huggingface/tokenizer.json +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00001-of-00007.safetensors +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00002-of-00007.safetensors +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00003-of-00007.safetensors +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00004-of-00007.safetensors +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00005-of-00007.safetensors +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00006-of-00007.safetensors +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00007-of-00007.safetensors +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model_world_size_2_rank_0.pt +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model_world_size_2_rank_1.pt +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/tokenizer.json +3 -0
- qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/data.pt +3 -0
.gitattributes
CHANGED
|
@@ -133,3 +133,9 @@ global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 133 |
global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 134 |
mathevo-grpo-baseline/qwen2-math-7b-grpo-baseline-3epochs/global_step_12/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 135 |
mathevo-grpo-baseline/qwen2-math-7b-grpo-baseline-3epochs/global_step_12/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 134 |
mathevo-grpo-baseline/qwen2-math-7b-grpo-baseline-3epochs/global_step_12/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 135 |
mathevo-grpo-baseline/qwen2-math-7b-grpo-baseline-3epochs/global_step_12/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"eos_token": "<|endoftext|>",
|
| 36 |
+
"errors": "replace",
|
| 37 |
+
"extra_special_tokens": {},
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/huggingface/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4319d4b9b588faf84b14ac0389896abcde7702eb1410c8a7cbf65135530b6dde
|
| 3 |
+
size 4976687216
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b74aeacbc85feb9c492a8269211cb22d30fbbc3d6311a28e11d9a57becc2ac4
|
| 3 |
+
size 4778622352
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d6d23f62f7df7b448455d73e2e21635dde58b0628f1b720b66e787a0bfcd63d
|
| 3 |
+
size 4932743960
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33f86916ea6ae9b3e54800c1c7a5b2136037d572b7e76d1e977fd966171fa9fc
|
| 3 |
+
size 4932743992
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c57b637ade87773638cc896f3f7327fee37659e5a4aec569d568f223b23b8bf4
|
| 3 |
+
size 4998852296
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c7d690e3218ab3c780814f048b82563780cad2c41001b63cd8625b3dc002367
|
| 3 |
+
size 3662865184
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91ad921ba680dc464f1ad4d40a276228977658b3682af6576e31ce272311c9cd
|
| 3 |
+
size 2179989632
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model_world_size_2_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0540621ddea635c67559871e4fab664e9473c85beb1d852d557a10303edd43e
|
| 3 |
+
size 15231424874
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/model_world_size_2_rank_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34682712d5ddc540518224b57b07c526b4c99c3ed9ed5f5788e5f58f318a5ab1
|
| 3 |
+
size 15231424874
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/actor/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_12/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db0ce97ba38c28ccc2584886490f5a5e530bca6ca2760a9b23bf4b095125d740
|
| 3 |
+
size 6943629
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/chat_template.jinja
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
| 2 |
+
You are a helpful assistant<|im_end|>
|
| 3 |
+
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
| 4 |
+
' + message['content'] + '<|im_end|>' + '
|
| 5 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 6 |
+
' }}{% endif %}
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.56.2"
|
| 6 |
+
}
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23808cbadc4fbc41a432286f31c1bf3c1552b4f71cd009f26dbb770c015f8574
|
| 3 |
+
size 4976687216
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42ada45bb1075e51f77cc851c4a9d212949518d8fb0d11eb04f3ea5527c67651
|
| 3 |
+
size 4778622352
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f36de19a9a168fa7f40210fa35661fd20a982b09a25f76c20746bf5d8fdef1de
|
| 3 |
+
size 4932743960
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8ce0b0d068a4bb2bf4c0efd57456544563c62f1f15d9e566536477e0e458b34
|
| 3 |
+
size 4932743992
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:903e35b840acc7588557d5da729379916bd0025c82b3281ed906e58498c2e389
|
| 3 |
+
size 4998852296
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cd5ecbb5e72fb01e4c80dc43359c11850a003c1f63b2fac608d7e0306f6c1b8
|
| 3 |
+
size 3662865184
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcb2b3a3f5d0cbf5dc40ac35d02e2eb4b26cb2a07212620a8e018e9362283be4
|
| 3 |
+
size 2179989632
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model_world_size_2_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b14086c47a27e3025cea684872945177439aade00918db5ec4b606dedd2974f5
|
| 3 |
+
size 15231424874
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/model_world_size_2_rank_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:011d53d32742d466e707001c86a117c932e09bcfdf2e46452538bc53b811a16a
|
| 3 |
+
size 15231424874
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/actor/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
qwen2-math-7b-grpo-quiz-20251116_171005/global_step_24/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:312e68b61863d8a09b2659671bc9e16cccd7f0061fa89c66a195a0e9a39d6630
|
| 3 |
+
size 6943629
|
qwen2-math-7b-instruct-grpo-quiz-20251119_105202/global_step_12/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2191ec14e63816840f29a5bc68d342782ed247ae6331bb2ad720287b8fe98be
|
| 3 |
+
size 6943885
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e7ca8cfc0832dbdde5853eda48f7da7bdd2046fc9ec13e1a026244a476c2a09
|
| 3 |
+
size 4976687216
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:155c0f9d9a4a0a1fd0dedba4864d8c592086c69328db579f950360c701075977
|
| 3 |
+
size 4778622352
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60a080d3e5945d2767ed5229dc7a6e842fcb54431fe2042119ea60d0b0d59452
|
| 3 |
+
size 4932743960
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6695fd478ff90035da9d245b26a5d7ab65c7c8395f06e4eaad003afab4f1384b
|
| 3 |
+
size 4932743992
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0eb5f00fcf054cd4453042e5c2a492f1f87af724e1c2285973367555ad53cf9d
|
| 3 |
+
size 4998852296
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39fa43acbbd3cd45b4d0b8af0d921b77e3e13888eb4beb78ec9ba6a382a30231
|
| 3 |
+
size 3662865184
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7a172b4d3c2a83b6fa0c98bc868cd2e3e389033c251ac3bef1c4539a41c332f
|
| 3 |
+
size 2179989632
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model_world_size_2_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ffb678c1fb2d5db162555f941c6d8166246cadce01f2eeed5fed948e36ec17e
|
| 3 |
+
size 15231424874
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/model_world_size_2_rank_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb11e0f4dc144bd06864275419536cdb90847752c2c96897328222cdc02c5ed3
|
| 3 |
+
size 15231424874
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/actor/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
|
| 3 |
+
size 11418266
|
qwen2-math-7b-instruct-grpo-quiz-20251119_140941/global_step_24/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b15695dc76b6fa86acca2d24560f12e612e39f0cc827633a24066475bd3cb4b7
|
| 3 |
+
size 6943885
|