add checkpoints
Browse files- Qwen-0.5B-GRPO/checkpoint-500/added_tokens.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/config.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/generation_config.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/merges.txt +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/model.safetensors +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/optimizer.pt +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/rng_state.pth +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/scheduler.pt +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/special_tokens_map.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/tokenizer.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/tokenizer_config.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/trainer_state.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/training_args.bin +3 -0
- Qwen-0.5B-GRPO/checkpoint-500/vocab.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/added_tokens.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/config.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/generation_config.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/merges.txt +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/model.safetensors +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/optimizer.pt +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/rng_state.pth +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/scheduler.pt +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/special_tokens_map.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/tokenizer.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/tokenizer_config.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/trainer_state.json +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/training_args.bin +3 -0
- Qwen-0.5B-GRPO/checkpoint-600/vocab.json +3 -0
Qwen-0.5B-GRPO/checkpoint-500/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
|
| 3 |
+
size 605
|
Qwen-0.5B-GRPO/checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1853ace95e8460eebf92f339220785c6a904120a5b5655508ee6a66ff8012428
|
| 3 |
+
size 731
|
Qwen-0.5B-GRPO/checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15794d5a480c43c46a7b861e4a564af5c4e8653b47569dea1afcc0fcf83f43d2
|
| 3 |
+
size 242
|
Qwen-0.5B-GRPO/checkpoint-500/merges.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
|
| 3 |
+
size 1671853
|
Qwen-0.5B-GRPO/checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01ffaebb5c5c5695ec03bf2e0b59ef8772c6a8e4b29c6c219c9d8e5c54805aed
|
| 3 |
+
size 988097824
|
Qwen-0.5B-GRPO/checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80840ae8f33e356728eda4257b71152841da7665cb4d17b555ed53d68db28541
|
| 3 |
+
size 1976374202
|
Qwen-0.5B-GRPO/checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feee6a0270a687c4410d3c08b1cfa0bbdab6ad0e7e6a1cc5edf2823574973d4a
|
| 3 |
+
size 14180
|
Qwen-0.5B-GRPO/checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e59789c72887adc00e6872ea3d3873781264a5433d6123af45a63c1c15872989
|
| 3 |
+
size 1064
|
Qwen-0.5B-GRPO/checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a36726f7fe394c1324021cac4a9ee3ad6c4f6285c0d98721f9b0b95888ec9905
|
| 3 |
+
size 496
|
Qwen-0.5B-GRPO/checkpoint-500/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
|
| 3 |
+
size 11422060
|
Qwen-0.5B-GRPO/checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f91b80bdb7722bdd0a25d79246fa79e513a7d4d78056b2eac8cbf92767937ab8
|
| 3 |
+
size 7333
|
Qwen-0.5B-GRPO/checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3487b851d45e3b619c435db9d599d7e4e78bbd03a8cc862510b2778d73984d42
|
| 3 |
+
size 279348
|
Qwen-0.5B-GRPO/checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03623afc2805403a4077a6c9dcc3f569621622405344041ab9b94e6a9d9c3c56
|
| 3 |
+
size 5560
|
Qwen-0.5B-GRPO/checkpoint-500/vocab.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
|
| 3 |
+
size 2776833
|
Qwen-0.5B-GRPO/checkpoint-600/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
|
| 3 |
+
size 605
|
Qwen-0.5B-GRPO/checkpoint-600/config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1853ace95e8460eebf92f339220785c6a904120a5b5655508ee6a66ff8012428
|
| 3 |
+
size 731
|
Qwen-0.5B-GRPO/checkpoint-600/generation_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15794d5a480c43c46a7b861e4a564af5c4e8653b47569dea1afcc0fcf83f43d2
|
| 3 |
+
size 242
|
Qwen-0.5B-GRPO/checkpoint-600/merges.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
|
| 3 |
+
size 1671853
|
Qwen-0.5B-GRPO/checkpoint-600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe0e096b8adf7f15e2d61b27b9cfe315a675ec7f1b85042c74ae9e753ee5d472
|
| 3 |
+
size 988097824
|
Qwen-0.5B-GRPO/checkpoint-600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5b2950bd07fa02e8b9b9a638cd657137cea17fec819d3542ef1cf05c60db7a
|
| 3 |
+
size 1976374202
|
Qwen-0.5B-GRPO/checkpoint-600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d08ccee6aa4af645a118afcaf2c3e0517d4e7fa1b21e0ab356f6d1f32f622d40
|
| 3 |
+
size 14180
|
Qwen-0.5B-GRPO/checkpoint-600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83b6c9cda88e7647e67e4c54fdd19a1d5edcd5493ff0ec2c27aeb881eb43e13c
|
| 3 |
+
size 1064
|
Qwen-0.5B-GRPO/checkpoint-600/special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a36726f7fe394c1324021cac4a9ee3ad6c4f6285c0d98721f9b0b95888ec9905
|
| 3 |
+
size 496
|
Qwen-0.5B-GRPO/checkpoint-600/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
|
| 3 |
+
size 11422060
|
Qwen-0.5B-GRPO/checkpoint-600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f91b80bdb7722bdd0a25d79246fa79e513a7d4d78056b2eac8cbf92767937ab8
|
| 3 |
+
size 7333
|
Qwen-0.5B-GRPO/checkpoint-600/trainer_state.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecf75aa7c338f93a01b96d75fca4caa172614992e840ac596f5b68611ec9b272
|
| 3 |
+
size 335819
|
Qwen-0.5B-GRPO/checkpoint-600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03623afc2805403a4077a6c9dcc3f569621622405344041ab9b94e6a9d9c3c56
|
| 3 |
+
size 5560
|
Qwen-0.5B-GRPO/checkpoint-600/vocab.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
|
| 3 |
+
size 2776833
|