Upload folder using huggingface_hub

attention_kindselective_n_heads2_seed1341/log2.txt

@@ -4402,3 +4402,107 @@ max_steps: 50000
 46500 val loss 5.8856
 46500 val perplexity 359.8179
 46500 train 5.713169 (lr=1.1092e-05) (hash(x)=48511186)
+46600 val loss 5.8860
+46600 val perplexity 359.9745
+46600 train 5.918826 (lr=1.1031e-05) (hash(x)=48832039)
+46700 val loss 5.8864
+46700 val perplexity 360.1195
+46700 train 6.561471 (lr=1.0972e-05) (hash(x)=65821271)
+46800 val loss 5.8886
+46800 val perplexity 360.8994
+46800 train 5.569217 (lr=1.0914e-05) (hash(x)=48005593)
+46900 val loss 5.8879
+46900 val perplexity 360.6612
+46900 train 6.157232 (lr=1.0858e-05) (hash(x)=53182453)
+47000 val loss 5.8908
+47000 val perplexity 361.6933
+47000 train 5.775409 (lr=1.0803e-05) (hash(x)=49385983)
+47100 val loss 5.8881
+47100 val perplexity 360.7214
+47100 train 5.876601 (lr=1.0751e-05) (hash(x)=48801622)
+47200 val loss 5.8882
+47200 val perplexity 360.7730
+47200 train 5.618414 (lr=1.0700e-05) (hash(x)=45216690)
+47300 val loss 5.8918
+47300 val perplexity 362.0417
+47300 train 5.716314 (lr=1.0651e-05) (hash(x)=51185601)
+47400 val loss 5.8878
+47400 val perplexity 360.6154
+47400 train 5.607826 (lr=1.0604e-05) (hash(x)=47743508)
+47500 val loss 5.8948
+47500 val perplexity 363.1413
+47500 train 5.676246 (lr=1.0558e-05) (hash(x)=49318833)
+47600 val loss 5.8933
+47600 val perplexity 362.6100
+47600 train 5.876511 (lr=1.0515e-05) (hash(x)=50430826)
+47700 val loss 5.8931
+47700 val perplexity 362.5116
+47700 train 5.814244 (lr=1.0473e-05) (hash(x)=51966931)
+47800 val loss 5.8937
+47800 val perplexity 362.7275
+47800 train 5.641396 (lr=1.0433e-05) (hash(x)=49517209)
+47900 val loss 5.8987
+47900 val perplexity 364.5595
+47900 train 5.698562 (lr=1.0394e-05) (hash(x)=49749702)
+48000 val loss 5.8991
+48000 val perplexity 364.6937
+48000 train 5.766129 (lr=1.0358e-05) (hash(x)=52535448)
+48100 val loss 5.8882
+48100 val perplexity 360.7525
+48100 train 6.531771 (lr=1.0323e-05) (hash(x)=53739181)
+48200 val loss 5.8824
+48200 val perplexity 358.6651
+48200 train 5.854337 (lr=1.0290e-05) (hash(x)=48086710)
+48300 val loss 5.8826
+48300 val perplexity 358.7256
+48300 train 5.921894 (lr=1.0259e-05) (hash(x)=43991942)
+48400 val loss 5.8792
+48400 val perplexity 357.5202
+48400 train 5.780863 (lr=1.0229e-05) (hash(x)=50801906)
+48500 val loss 5.8788
+48500 val perplexity 357.3769
+48500 train 5.955594 (lr=1.0201e-05) (hash(x)=48915599)
+48600 val loss 5.8765
+48600 val perplexity 356.5590
+48600 train 6.042453 (lr=1.0175e-05) (hash(x)=54450172)
+48700 val loss 5.8783
+48700 val perplexity 357.1961
+48700 train 5.748240 (lr=1.0151e-05) (hash(x)=48755509)
+48800 val loss 5.8904
+48800 val perplexity 361.5333
+48800 train 5.780968 (lr=1.0129e-05) (hash(x)=51380096)
+48900 val loss 5.8791
+48900 val perplexity 357.4912
+48900 train 5.744174 (lr=1.0108e-05) (hash(x)=43404218)
+49000 val loss 5.8779
+49000 val perplexity 357.0585
+49000 train 5.845617 (lr=1.0090e-05) (hash(x)=55059739)
+49100 val loss 5.8824
+49100 val perplexity 358.6769
+49100 train 6.111704 (lr=1.0073e-05) (hash(x)=47889309)
+49200 val loss 5.8832
+49200 val perplexity 358.9541
+49200 train 5.629024 (lr=1.0057e-05) (hash(x)=46202589)
+49300 val loss 5.8825
+49300 val perplexity 358.7058
+49300 train 5.780267 (lr=1.0044e-05) (hash(x)=49161813)
+49400 val loss 5.8826
+49400 val perplexity 358.7585
+49400 train 5.719767 (lr=1.0032e-05) (hash(x)=49505044)
+49500 val loss 5.8832
+49500 val perplexity 358.9488
+49500 train 5.663615 (lr=1.0022e-05) (hash(x)=46610327)
+49600 val loss 5.8839
+49600 val perplexity 359.2018
+49600 train 6.220163 (lr=1.0014e-05) (hash(x)=51188240)
+49700 val loss 5.8821
+49700 val perplexity 358.5739
+49700 train 5.680971 (lr=1.0008e-05) (hash(x)=41492016)
+49800 val loss 5.8812
+49800 val perplexity 358.2258
+49800 train 5.788856 (lr=1.0004e-05) (hash(x)=53488833)
+49900 val loss 5.8811
+49900 val perplexity 358.1883
+49900 train 6.194769 (lr=1.0001e-05) (hash(x)=60260935)
+49999 val loss 5.8753
+49999 val perplexity 356.1245

attention_kindselective_n_heads2_seed1341/model_47500.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f10489eeeefc32b2aec0615aaaedae12a844b5c9ea48c80427d8873fd45e4bb
+oid sha256:cb22aa6f5947b15de1ac7135ec3e686429f487241f1a5524207c53012a4790f7
 size 38587970

attention_kindselective_n_heads2_seed1341/model_49999.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6fabd2091d123286c1aa08ccfbc214046b86add0bb88e105e13fcbaa156726
+oid sha256:31806c8a239461981a224edaa0eb46f8d1f3413c143e682980dd953b9856c440
 size 38587970

attention_kindselective_n_heads2_seed1341/optimizer_47500.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40db19e0e2056eef8cf8b772f3c21365474b8d9d8725dee8528b75cd13754308
+oid sha256:43c587204270bfbb51bcc6f940266318ee64b48c78c0d8846062182ba107b060
 size 70895430

attention_kindselective_n_heads2_seed1341/optimizer_49999.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fadeba3455a1c32c7d23175ef110cf852d10f450c42218ecd6c029b481bc691
+oid sha256:d87df62bab55321fe1386a280814d4558ef6273be3157bbcccf05f163a097b2e
 size 70895430