7bde9752c1
docs: clarify how to read the GRPO policy loss curve
...
The GRPO section described Policy Loss as 'decreases steadily overall' next to the
reward trend, which reads like a supervised loss where a lower value means a
better model. GRPO's policy term is a TRPO-like surrogate whose advantage term is
renormalized within each group every iteration, so its absolute level mainly
tracks how far the policy has drifted from the sampling distribution.
Keep the reward observation and the single-network vs. PPO comparison, and state
that convergence should be judged from reward and generation quality instead.
Same change in README.md and README_en.md.
Refs #884
2026-10-09 23:12:13 +08:00
77946fda00
[docs] 在客观评测表下补充各数据集的测量分辨率
...
lm_eval 对每个指标都会输出 stderr，但表格只保留了点估计。这里按测试集
大小给出各任务的 ± 标准误（obqa ±1.9 到 cmmlu ±0.4），并说明比较两个
模型时差值的标准误约为单项的 √2 倍，方便读者判断表中哪些差距是可以
解读的。中英文 README 同步。
2026-09-03 17:10:52 +07:00
7a6fddd63a
[update] readme
2026-08-31 18:08:05 +08:00
d65ef2c00e
[update] readme content
2026-08-21 16:49:00 +08:00
ed5ea9e02a
[update] readme content
2026-08-21 16:30:30 +08:00
eabad706da
[update] readme content
2026-08-21 16:25:20 +08:00
393e387e9a
[update] supporter charts
2026-08-06 22:07:29 +08:00
512eed0b65
[fix] robustness
2026-06-28 18:03:34 +08:00
5020dc9dd4
[update] readme
2026-05-06 13:41:46 +08:00
06d882e4ef
[update] readme
2026-05-01 12:06:47 +08:00
da865af63d
[update] readme
2026-04-28 17:22:25 +08:00
d4c6bc5c7e
[update] readme
2026-04-27 10:59:41 +08:00
24896cd2c4
[update] readme
2026-04-24 20:16:06 +08:00
e2fc397176
[update] readme
2026-04-24 20:14:10 +08:00
693fb1ccf1
[update] readme
2026-04-21 14:34:46 +08:00
1ea113ea2c
[update] readme
2026-04-19 14:51:47 +08:00
487f78754d
[update] readme
2026-04-10 10:55:24 +08:00
b2488e6440
[update] readme
2026-04-09 19:00:41 +08:00
939dc8ff42
[update] readme
2026-04-09 18:54:17 +08:00
cacf1d4cd0
[update] readme
2026-04-04 11:25:21 +08:00
9348fde743
[update] readme
2026-04-02 15:28:29 +08:00
90cd275524
[update] readme
2026-04-01 14:00:21 +08:00
101d7df2da
[update] minimind-3
2026-03-25 23:57:45 +08:00
20a43d7db0
[update] readme
2026-01-07 00:58:38 +08:00
0b4a8ad4aa
[update] readme
2026-01-06 01:18:10 +08:00
9830915d87
[update] readme
2026-01-05 23:15:25 +08:00
fe24501602
[feat] adjust seq length
2025-12-14 20:41:58 +08:00
fa82707c9c
[feat] update readme
2025-12-11 15:45:50 +08:00
151fdf7e76
[feat] update yarn
2025-12-01 16:15:05 +08:00
5959396096
[feat] add MNN support to README.
2025-11-10 21:59:22 +08:00
8d71754e05
[feat] update readme
2025-10-30 23:39:25 +08:00
d8ac558ce2
[feat] update readme
2025-10-30 23:30:12 +08:00
e4807a5214
[feat] update readme
2025-10-30 23:27:15 +08:00
800fed4639
[feat] update readme
2025-10-29 12:13:25 +08:00
eb96113cd4
[feat] update readme
2025-10-27 16:31:40 +08:00
cc81925ecc
[feat] update readme
2025-10-26 18:52:50 +08:00
6efba3249a
[feat] update readme
2025-10-24 01:18:33 +08:00
ea2abb5fb3
[feat] update readme
2025-10-24 00:45:11 +08:00
d762926f48
[feat] update readme
2025-10-23 23:23:52 +08:00
09be7dba11
[feat] update readme
2025-10-23 20:23:46 +08:00
d8bf813eac
[feat] update readme
2025-10-21 23:02:16 +08:00
7d877db79b
[feat] minimind-2510
2025-10-21 21:19:47 +08:00
765c79c7a2
update readme
2025-04-26 10:37:46 +08:00
00d145c481
update readme
2025-04-26 10:21:34 +08:00
a62faf34bd
250426
2025-04-26 10:05:47 +08:00
04b56ea86c
update readme
2025-02-23 20:07:26 +08:00
f475e4e407
update images
2025-02-19 22:54:57 +08:00
b5d10d9a7d
fix bugs
2025-02-13 20:56:14 +08:00
d2f5ef4355
update lr
2025-02-11 23:52:40 +08:00
fea5b0eafc
update readme
2025-02-10 23:34:52 +08:00
Yi-111-a
Justin Guese
jingyaogong
jingyaogong
yanxing
gongjy