Upload folder using huggingface_hub
Browse files
attention_kindselective_n_heads2_seed1338/log2.txt
CHANGED
|
@@ -4376,3 +4376,44 @@ max_steps: 50000
|
|
| 4376 |
46200 val loss 5.6987
|
| 4377 |
46200 val perplexity 298.4711
|
| 4378 |
46200 train 5.791500 (lr=5.6434e-06) (hash(x)=53829283)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4376 |
46200 val loss 5.6987
|
| 4377 |
46200 val perplexity 298.4711
|
| 4378 |
46200 train 5.791500 (lr=5.6434e-06) (hash(x)=53829283)
|
| 4379 |
+
49500 val loss 5.8169
|
| 4380 |
+
49500 val perplexity 335.9280
|
| 4381 |
+
49500 train 6.125725 (lr=7.0157e-06) (hash(x)=51678773)
|
| 4382 |
+
46300 val loss 5.7027
|
| 4383 |
+
46300 val perplexity 299.6628
|
| 4384 |
+
46300 train 5.488910 (lr=5.6101e-06) (hash(x)=49943891)
|
| 4385 |
+
49600 val loss 5.8184
|
| 4386 |
+
49600 val perplexity 336.4299
|
| 4387 |
+
49600 train 5.589625 (lr=7.0100e-06) (hash(x)=49092923)
|
| 4388 |
+
46400 val loss 5.7027
|
| 4389 |
+
46400 val perplexity 299.6711
|
| 4390 |
+
46400 train 5.785057 (lr=5.5777e-06) (hash(x)=55302927)
|
| 4391 |
+
49700 val loss 5.8197
|
| 4392 |
+
49700 val perplexity 336.8552
|
| 4393 |
+
49700 train 6.043599 (lr=7.0056e-06) (hash(x)=55550116)
|
| 4394 |
+
46500 val loss 5.6997
|
| 4395 |
+
46500 val perplexity 298.7794
|
| 4396 |
+
46500 train 5.529928 (lr=5.5462e-06) (hash(x)=50350943)
|
| 4397 |
+
49800 val loss 5.8194
|
| 4398 |
+
49800 val perplexity 336.7800
|
| 4399 |
+
49800 train 5.690748 (lr=7.0025e-06) (hash(x)=48422352)
|
| 4400 |
+
49900 val loss 5.8196
|
| 4401 |
+
49900 val perplexity 336.8330
|
| 4402 |
+
49900 train 5.888191 (lr=7.0006e-06) (hash(x)=52576880)
|
| 4403 |
+
46600 val loss 5.7004
|
| 4404 |
+
46600 val perplexity 298.9969
|
| 4405 |
+
46600 train 5.374248 (lr=5.5156e-06) (hash(x)=50991478)
|
| 4406 |
+
49999 val loss 5.8182
|
| 4407 |
+
49999 val perplexity 336.3679
|
| 4408 |
+
46700 val loss 5.7020
|
| 4409 |
+
46700 val perplexity 299.4609
|
| 4410 |
+
46700 train 5.908626 (lr=5.4858e-06) (hash(x)=52275285)
|
| 4411 |
+
46800 val loss 5.7018
|
| 4412 |
+
46800 val perplexity 299.3918
|
| 4413 |
+
46800 train 5.616808 (lr=5.4569e-06) (hash(x)=52748351)
|
| 4414 |
+
46900 val loss 5.6983
|
| 4415 |
+
46900 val perplexity 298.3597
|
| 4416 |
+
46900 train 5.865114 (lr=5.4289e-06) (hash(x)=49907987)
|
| 4417 |
+
47000 val loss 5.6956
|
| 4418 |
+
47000 val perplexity 297.5557
|
| 4419 |
+
47000 train 5.862358 (lr=5.4017e-06) (hash(x)=58296973)
|
attention_kindselective_n_heads2_seed1338/model_49999.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 38587970
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b40a2bad5cb6d06712afd9dd8b3e80440264db3a5252aafcb3940326cfd13cce
|
| 3 |
size 38587970
|
attention_kindselective_n_heads2_seed1338/optimizer_49999.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70895430
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a87ba1dab58634637df50543e586292f0c40067c9a7b0458888736cd9020686
|
| 3 |
size 70895430
|