han1823123123 commited on
Commit
82f4fd1
·
verified ·
1 Parent(s): 9c6d5f1

agent=agent_em_100k train_key=c5b18a75a0db4994

Browse files
c5b18a75a0db4994/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "act_cache_key": "40a11e1594d9220a",
3
+ "agent": "agent_em_100k",
4
+ "arch": "mlc",
5
+ "arch_version": "1.0.0",
6
+ "datasource": "gemma_2_2b_it_l11to15_fineweb_24k128",
7
+ "saved_ts": "2026-05-05T21:17:33Z",
8
+ "seed": 42,
9
+ "train_key": "c5b18a75a0db4994",
10
+ "training_cfg": {
11
+ "arch_hparams_override": null,
12
+ "batch_size": 1024,
13
+ "bricken_enabled": false,
14
+ "bricken_max_resample_fraction": 0.5,
15
+ "bricken_min_fires": 1,
16
+ "bricken_n_check": 2048,
17
+ "bricken_resample_every": 500,
18
+ "dead_threshold_tokens": 10000000,
19
+ "ema_auxk_alpha": 0.03125,
20
+ "learning_rate": 0.0003,
21
+ "n_steps": 20000,
22
+ "optimizer": "adam",
23
+ "plateau_early_stop": false,
24
+ "plateau_min_delta": 0.0001,
25
+ "plateau_patience": 5000,
26
+ "precision": "bf16",
27
+ "train_window_size": null,
28
+ "warmup_steps": 1000
29
+ }
30
+ }
c5b18a75a0db4994/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa12d4e626d9b2ea577b201746f6489677afff5d5b7394dc8a18c87581dfb0a
3
+ size 1698813264