Upload folder using huggingface_hub
Browse files
s2/b0_residpost_sep_d2048_k8/trainer_0/ae.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c504104122d42bc7b410c80dde2f471bdcc869449c247a62563fdbb359c15fb6
|
| 3 |
+
size 4206457
|
s2/b0_residpost_sep_d2048_k8/trainer_0/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"trainer": {
|
| 3 |
+
"trainer_class": "BatchTopKTrainer",
|
| 4 |
+
"dict_class": "BatchTopKSAE",
|
| 5 |
+
"lr": 0.0001,
|
| 6 |
+
"steps": 5000000,
|
| 7 |
+
"auxk_alpha": 0.03125,
|
| 8 |
+
"warmup_steps": 1000,
|
| 9 |
+
"decay_start": null,
|
| 10 |
+
"threshold_beta": 0.999,
|
| 11 |
+
"threshold_start_step": 1000,
|
| 12 |
+
"top_k_aux": 128,
|
| 13 |
+
"seed": 2,
|
| 14 |
+
"activation_dim": 256,
|
| 15 |
+
"dict_size": 2048,
|
| 16 |
+
"k": 8,
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"layer": 0,
|
| 19 |
+
"lm_name": "toy_binding",
|
| 20 |
+
"wandb_name": "b0_residpost_sep_d2048_k8",
|
| 21 |
+
"submodule_name": null
|
| 22 |
+
}
|
| 23 |
+
}
|