Upload folder using huggingface_hub
Browse files- attention_kindselective_n_heads4_seed1339/log2.txt +47 -0
- attention_kindselective_n_heads4_seed1339/model_47500.pt +1 -1
- attention_kindselective_n_heads4_seed1339/model_49999.pt +1 -1
- attention_kindselective_n_heads4_seed1339/optimizer_47500.pt +1 -1
- attention_kindselective_n_heads4_seed1339/optimizer_49999.pt +1 -1
attention_kindselective_n_heads4_seed1339/log2.txt
CHANGED
|
@@ -3229,3 +3229,50 @@ max_steps: 50000
|
|
| 3229 |
48400 val loss 5.4162
|
| 3230 |
48400 val perplexity 225.0163
|
| 3231 |
48400 train 5.490232 (lr=3.0687e-06) (hash(x)=48713969)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3229 |
48400 val loss 5.4162
|
| 3230 |
48400 val perplexity 225.0163
|
| 3231 |
48400 train 5.490232 (lr=3.0687e-06) (hash(x)=48713969)
|
| 3232 |
+
48500 val loss 5.4152
|
| 3233 |
+
48500 val perplexity 224.7866
|
| 3234 |
+
48500 train 4.865562 (lr=3.0604e-06) (hash(x)=37691696)
|
| 3235 |
+
48600 val loss 5.4163
|
| 3236 |
+
48600 val perplexity 225.0509
|
| 3237 |
+
48600 train 5.685455 (lr=3.0526e-06) (hash(x)=48712321)
|
| 3238 |
+
48700 val loss 5.4158
|
| 3239 |
+
48700 val perplexity 224.9393
|
| 3240 |
+
48700 train 5.835886 (lr=3.0454e-06) (hash(x)=63513096)
|
| 3241 |
+
48800 val loss 5.4156
|
| 3242 |
+
48800 val perplexity 224.8865
|
| 3243 |
+
48800 train 5.031997 (lr=3.0387e-06) (hash(x)=44917721)
|
| 3244 |
+
48900 val loss 5.4152
|
| 3245 |
+
48900 val perplexity 224.7968
|
| 3246 |
+
48900 train 5.600576 (lr=3.0325e-06) (hash(x)=51426559)
|
| 3247 |
+
49000 val loss 5.4154
|
| 3248 |
+
49000 val perplexity 224.8466
|
| 3249 |
+
49000 train 5.394188 (lr=3.0269e-06) (hash(x)=47909690)
|
| 3250 |
+
49100 val loss 5.4155
|
| 3251 |
+
49100 val perplexity 224.8680
|
| 3252 |
+
49100 train 5.328714 (lr=3.0218e-06) (hash(x)=48329226)
|
| 3253 |
+
49200 val loss 5.4158
|
| 3254 |
+
49200 val perplexity 224.9241
|
| 3255 |
+
49200 train 5.355852 (lr=3.0172e-06) (hash(x)=49512472)
|
| 3256 |
+
49300 val loss 5.4154
|
| 3257 |
+
49300 val perplexity 224.8484
|
| 3258 |
+
49300 train 5.320653 (lr=3.0132e-06) (hash(x)=46541146)
|
| 3259 |
+
49400 val loss 5.4161
|
| 3260 |
+
49400 val perplexity 224.9995
|
| 3261 |
+
49400 train 5.368901 (lr=3.0097e-06) (hash(x)=52192792)
|
| 3262 |
+
49500 val loss 5.4151
|
| 3263 |
+
49500 val perplexity 224.7733
|
| 3264 |
+
49500 train 5.217689 (lr=3.0067e-06) (hash(x)=48954331)
|
| 3265 |
+
49600 val loss 5.4149
|
| 3266 |
+
49600 val perplexity 224.7205
|
| 3267 |
+
49600 train 5.538561 (lr=3.0043e-06) (hash(x)=50364098)
|
| 3268 |
+
49700 val loss 5.4143
|
| 3269 |
+
49700 val perplexity 224.5999
|
| 3270 |
+
49700 train 5.380792 (lr=3.0024e-06) (hash(x)=52016774)
|
| 3271 |
+
49800 val loss 5.4140
|
| 3272 |
+
49800 val perplexity 224.5306
|
| 3273 |
+
49800 train 5.662879 (lr=3.0011e-06) (hash(x)=54182957)
|
| 3274 |
+
49900 val loss 5.4114
|
| 3275 |
+
49900 val perplexity 223.9449
|
| 3276 |
+
49900 train 5.135486 (lr=3.0003e-06) (hash(x)=48188126)
|
| 3277 |
+
49999 val loss 5.4247
|
| 3278 |
+
49999 val perplexity 226.9434
|
attention_kindselective_n_heads4_seed1339/model_47500.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 92843394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0964f8adcdd2cdfe68f3d23cbb530071d363c0730776b19a37b23067ce8e6cde
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1339/model_49999.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 92843394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdc30155a9b1ff6101f79387825c53919d4aae7e5260632db4fbcb22dc319788
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1339/optimizer_47500.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 179406214
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7d2dedd455261f1df52bb5717ea6c42835fd3bf2b17a4dc291f3a50feabf000
|
| 3 |
size 179406214
|
attention_kindselective_n_heads4_seed1339/optimizer_49999.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 179406214
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73795c0fcbf9254fba049891b5f3628853f2bfd269bc7bf76294f30fc921f0d6
|
| 3 |
size 179406214
|