diff --git a/cache_dir/bak/general_stats.json b/cache_dir/bak/general_stats.json
new file mode 100644
index 0000000000000000000000000000000000000000..d08a6d0a085a7a532e64070ed493202ab50d4e31
--- /dev/null
+++ b/cache_dir/bak/general_stats.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d04e38e33a11933b5689d4e2afc9a3742633b9a1ae0e607abd37c6dc3635fb
+size 39
diff --git a/cache_dir/c4_en.noblocklist_train_text/dset_peek.json b/cache_dir/c4_en.noblocklist_train_text/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..173426ea79a54ac44dded2a8e40d023616d06f21
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73791ca5a24b71cb9c947f2ba19ce44459c6bd1cbef494bac8abb52ef25ea7c
+size 259923
diff --git a/cache_dir/c4_en.noblocklist_train_text/dup_counts_df.feather b/cache_dir/c4_en.noblocklist_train_text/dup_counts_df.feather
new file mode 100644
index 0000000000000000000000000000000000000000..9929c9547b68baa11718fc36ded46e1cbe7932c2
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/dup_counts_df.feather
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9af4398cd1f9b8c9c8675a18d63cbb320b4c47fc3de49d224334627010bd7a
+size 1186
diff --git a/cache_dir/c4_en.noblocklist_train_text/fig_tok_length.json b/cache_dir/c4_en.noblocklist_train_text/fig_tok_length.json
new file mode 100644
index 0000000000000000000000000000000000000000..c30f3c85b4a9d34c16e6bcf27e0f991d4875d2c2
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/fig_tok_length.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ed8d608292aa5e69262330128c981eafaac42debbb616cef0403cf6048afb4
+size 1536266
diff --git a/cache_dir/c4_en.noblocklist_train_text/general_stats_dict.json b/cache_dir/c4_en.noblocklist_train_text/general_stats_dict.json
new file mode 100644
index 0000000000000000000000000000000000000000..f5f089d587ff4ea9e983408672599ea3e65c3ba3
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/general_stats_dict.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dc02aff74877535f762d3b94d9a9e3d21f44bf081b7797f367351ae1c3c614
+size 90
diff --git a/cache_dir/c4_en.noblocklist_train_text/length_df.feather b/cache_dir/c4_en.noblocklist_train_text/length_df.feather
new file mode 100644
index 0000000000000000000000000000000000000000..5ecf505f674add48692743b2aa13ca66936d0582
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/length_df.feather
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204bbaed8b3b94dacad4bdb8c2872d402974079fb243b4ee20497118ab9317f0
+size 314450450
diff --git a/cache_dir/c4_en.noblocklist_train_text/length_stats.json b/cache_dir/c4_en.noblocklist_train_text/length_stats.json
new file mode 100644
index 0000000000000000000000000000000000000000..6322fedbfcddaf114df316e75cfa39aff9f2fb14
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/length_stats.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e4b8a8c42856f08f45036e48cda529520a0424e7e60de21b2baf328eb59784
+size 63
diff --git a/cache_dir/c4_en.noblocklist_train_text/npmi_terms.json b/cache_dir/c4_en.noblocklist_train_text/npmi_terms.json
new file mode 100644
index 0000000000000000000000000000000000000000..df4ce142a8d99c85dbf9412ace9994e023eb0cd7
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/npmi_terms.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40fe28d565cdaf341298dba8af66ddd48428cb15ff58f5a838277139c4a865b3
+size 191
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay-lesbian_npmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay-lesbian_npmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..8f885334e15a9476e6d55129c5f270e3cde1427e
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay-lesbian_npmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a4cd5032c59bfcc4a0c572252e67e6d7801a2fb8cd13adbc5b450b624c19e8
+size 3004532
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay-man_npmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay-man_npmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..9c0c5286ac20bc2417de34c4d307a9d295970c69
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay-man_npmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c70a5bf630958a22f526e6e90d8ec0cbb039a436f6d915bac04dfc4bccfdd9
+size 5631101
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_npmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_npmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..d0cbe43f66e36a0a77bd5d219709815a01fd344e
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_npmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0b0eb158578cb1ae97f7e9a5007a4cde33a139f8d36add2619fe4a9756d4ca
+size 2403437
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_pmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_pmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..df6b128e23e82cf42fcc3c829474d83de6153f85
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_pmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933c98af333b3afa5293e54d0b16b3dcefd88d9e0c5237f8a1a61bf857a5c9ed
+size 2319355
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_vocab_cooc.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_vocab_cooc.csv
new file mode 100644
index 0000000000000000000000000000000000000000..478fb8df28e92410f469dd3421f3b68d54bdeff1
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/gay_vocab_cooc.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e000ee8ec5920b4a60d7f9128b7704c24b3f10bd61d235f498b1cfa91e8d6c3
+size 8689948
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_npmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_npmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..080275c69f2e3de436d65a31a48d07d0cf97401b
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_npmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e021274c447e576477f48567b71349c78a41055b5c37f050b63c4e1695b8ebe6
+size 1473301
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_pmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_pmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..ae3cea3d5341ff63197a6d0dd3fa35001745b466
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_pmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d19fc45ce8ad18764330d7fa03c7d130bd14f82375bd3f0b5b64a9c181a024
+size 1403773
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_vocab_cooc.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_vocab_cooc.csv
new file mode 100644
index 0000000000000000000000000000000000000000..a5964e1c405e5d442b1470529e4d7ad3adb85d2a
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/lesbian_vocab_cooc.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39035f60bc993e8c5486cbc1f2583c21cdff9125792f051d67ebaed5e426b601
+size 8683596
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/man-woman_npmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man-woman_npmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..5022f9ee5e8963d143383a0ce6562a5517c6025a
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man-woman_npmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5b4be41e3bf27caa1dc3dc1d32f5a1ddd07d0b3a2dcccf55184bfd43878a41
+size 10214552
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_npmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_npmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..7075996a6fb143793e4c156cfa6a1f87f8de29f8
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_npmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ff803bcf3725431f64373cb1d13ac06c89c81722d6a69fab9cc3e3def3c6c1
+size 7246942
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_pmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_pmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..6944b86605e29429468d37fd63d54a6b0db15583
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_pmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7954bd84651437369ecda7efd7a4c6cfaac295dbc00f774ae5d612ee49a07e05
+size 6995264
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_vocab_cooc.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_vocab_cooc.csv
new file mode 100644
index 0000000000000000000000000000000000000000..6e039bf979a648edf8ce6543e054f56b66917a04
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/man_vocab_cooc.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317087c0b6d54213e3e1a2ff945762548c3fd9b00a7fd88851cc1da054e25543
+size 8722467
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_npmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_npmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..110b88d94fb4557dbf792f1f068bf62d709325cc
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_npmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c030423138bfce91bdc90522c3ed864e1f3cc82b891982d413a9a3540f324c
+size 4684288
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_pmi.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_pmi.csv
new file mode 100644
index 0000000000000000000000000000000000000000..06b99bed5efa3f55ebe925dd298188b5bb697218
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_pmi.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562339994ad9c79787dab69c19d1639a3e8955181d1f76944278fbca283a5827
+size 4370814
diff --git a/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_vocab_cooc.csv b/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_vocab_cooc.csv
new file mode 100644
index 0000000000000000000000000000000000000000..9bff586c7248ccd6538dd3f17bb80aa13f9eb796
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/pmi_files/woman_vocab_cooc.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b913c7cd4acfc1808d0b2bd37c7772c7148ded2feb89b2808b2eb892579dd5cf
+size 8708146
diff --git a/cache_dir/c4_en.noblocklist_train_text/sorted_top_vocab.feather b/cache_dir/c4_en.noblocklist_train_text/sorted_top_vocab.feather
new file mode 100644
index 0000000000000000000000000000000000000000..26d5c1b3b4a45dcba54f14c8a4d223915b9b3c58
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/sorted_top_vocab.feather
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84050c5750071dbc056c19e7ffff4424f49f75deda43fada493d204142fccfe9
+size 4162
diff --git a/cache_dir/c4_en.noblocklist_train_text/text_dset/dataset.arrow b/cache_dir/c4_en.noblocklist_train_text/text_dset/dataset.arrow
new file mode 100644
index 0000000000000000000000000000000000000000..f41f148052c46833c316dd477aa04ba094e3be2a
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/text_dset/dataset.arrow
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5361ec9eb9b50421ed8615e5c085e581250279acbb63e14a708b3fac8a5a7da7
+size 504343120
diff --git a/cache_dir/c4_en.noblocklist_train_text/text_dset/dataset_info.json b/cache_dir/c4_en.noblocklist_train_text/text_dset/dataset_info.json
new file mode 100644
index 0000000000000000000000000000000000000000..9e58e4a12ef2b8309942701a85363445826e0240
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/text_dset/dataset_info.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8ef8d4b1ed96d6c5578f2411ee4be6c39527df741212a35d343886131c5eff
+size 932
diff --git a/cache_dir/c4_en.noblocklist_train_text/text_dset/state.json b/cache_dir/c4_en.noblocklist_train_text/text_dset/state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b4403b19865930e944f4016713955cdf3a2d1e40
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/text_dset/state.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74c523af8156f53de88477f782d517d4f1056ff84192000ffeeea13ea01331b
+size 256
diff --git a/cache_dir/c4_en.noblocklist_train_text/vocab_counts.feather b/cache_dir/c4_en.noblocklist_train_text/vocab_counts.feather
new file mode 100644
index 0000000000000000000000000000000000000000..f626cbc586b9f1496377bce4422ad587ed8d7947
--- /dev/null
+++ b/cache_dir/c4_en.noblocklist_train_text/vocab_counts.feather
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e813b0dd94883d8f6e5269ca19f5ab7fcbb99ee3ad88ce77c24d60d3f5904739
+size 8525314
diff --git a/cache_dir/glue_cola_train_sentence/dset_peek.json b/cache_dir/glue_cola_train_sentence/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d0949f374d405d98bc09a9cea34b4ad3973082a
--- /dev/null
+++ b/cache_dir/glue_cola_train_sentence/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:222977f6ab3c38fd76c2b191d32c5d254366b963c963eeae8ff0f9b6cf2b8b5a
+size 4684
diff --git a/cache_dir/glue_cola_validation_sentence/dset_peek.json b/cache_dir/glue_cola_validation_sentence/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..63b2257093efe239dcfa64f9488496e42b257792
--- /dev/null
+++ b/cache_dir/glue_cola_validation_sentence/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a1bcf6af6461a3e71fb81dbc5f3078a622044fd4b327176a836099d09426a2
+size 5939
diff --git a/cache_dir/glue_mnli_matched_validation_hypothesis/dset_peek.json b/cache_dir/glue_mnli_matched_validation_hypothesis/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..342e938b27530d29799480884400569a9de1bfb4
--- /dev/null
+++ b/cache_dir/glue_mnli_matched_validation_hypothesis/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd6015fbb5b45168d324a128d9a66bdb1aedc5e8a24a1f47f692758aa0a1d7c
+size 18743
diff --git a/cache_dir/glue_mnli_matched_validation_premise/dset_peek.json b/cache_dir/glue_mnli_matched_validation_premise/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..342e938b27530d29799480884400569a9de1bfb4
--- /dev/null
+++ b/cache_dir/glue_mnli_matched_validation_premise/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd6015fbb5b45168d324a128d9a66bdb1aedc5e8a24a1f47f692758aa0a1d7c
+size 18743
diff --git a/cache_dir/glue_mnli_mismatched_validation_hypothesis/dset_peek.json b/cache_dir/glue_mnli_mismatched_validation_hypothesis/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..6876368c61e2e32fc560e4ddca4a4e1705d7f2d9
--- /dev/null
+++ b/cache_dir/glue_mnli_mismatched_validation_hypothesis/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974161ba9d6598954f683adbf51ab50b7684dd53556311d5f491f1b166ebb805
+size 19774
diff --git a/cache_dir/glue_mnli_mismatched_validation_premise/dset_peek.json b/cache_dir/glue_mnli_mismatched_validation_premise/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..6876368c61e2e32fc560e4ddca4a4e1705d7f2d9
--- /dev/null
+++ b/cache_dir/glue_mnli_mismatched_validation_premise/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974161ba9d6598954f683adbf51ab50b7684dd53556311d5f491f1b166ebb805
+size 19774
diff --git a/cache_dir/glue_mnli_train_hypothesis/dset_peek.json b/cache_dir/glue_mnli_train_hypothesis/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..dc3a270d9df65f567d0b5596369804968ac0a75a
--- /dev/null
+++ b/cache_dir/glue_mnli_train_hypothesis/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89d0b39d7d1cf07b62eb6f355e74f4cb98cacd2fc6cfa7c0cf0599b2f5151f8
+size 19503
diff --git a/cache_dir/glue_mnli_train_premise/dset_peek.json b/cache_dir/glue_mnli_train_premise/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..dc3a270d9df65f567d0b5596369804968ac0a75a
--- /dev/null
+++ b/cache_dir/glue_mnli_train_premise/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89d0b39d7d1cf07b62eb6f355e74f4cb98cacd2fc6cfa7c0cf0599b2f5151f8
+size 19503
diff --git a/cache_dir/glue_mnli_validation_matched_hypothesis/dset_peek.json b/cache_dir/glue_mnli_validation_matched_hypothesis/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..342e938b27530d29799480884400569a9de1bfb4
--- /dev/null
+++ b/cache_dir/glue_mnli_validation_matched_hypothesis/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd6015fbb5b45168d324a128d9a66bdb1aedc5e8a24a1f47f692758aa0a1d7c
+size 18743
diff --git a/cache_dir/glue_mnli_validation_matched_premise/dset_peek.json b/cache_dir/glue_mnli_validation_matched_premise/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..342e938b27530d29799480884400569a9de1bfb4
--- /dev/null
+++ b/cache_dir/glue_mnli_validation_matched_premise/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd6015fbb5b45168d324a128d9a66bdb1aedc5e8a24a1f47f692758aa0a1d7c
+size 18743
diff --git a/cache_dir/glue_mnli_validation_mismatched_hypothesis/dset_peek.json b/cache_dir/glue_mnli_validation_mismatched_hypothesis/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..6876368c61e2e32fc560e4ddca4a4e1705d7f2d9
--- /dev/null
+++ b/cache_dir/glue_mnli_validation_mismatched_hypothesis/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974161ba9d6598954f683adbf51ab50b7684dd53556311d5f491f1b166ebb805
+size 19774
diff --git a/cache_dir/glue_mnli_validation_mismatched_premise/dset_peek.json b/cache_dir/glue_mnli_validation_mismatched_premise/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..6876368c61e2e32fc560e4ddca4a4e1705d7f2d9
--- /dev/null
+++ b/cache_dir/glue_mnli_validation_mismatched_premise/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974161ba9d6598954f683adbf51ab50b7684dd53556311d5f491f1b166ebb805
+size 19774
diff --git a/cache_dir/glue_mrpc_train_sentence1/dset_peek.json b/cache_dir/glue_mrpc_train_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..b2094f823d3bbc86a7a323eaf6f929e0013436e1
--- /dev/null
+++ b/cache_dir/glue_mrpc_train_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc1c7fd9daf223d2e5d55e89bc8f1de82435115fd3a72f1ac66393cfc1a5e08
+size 24645
diff --git a/cache_dir/glue_mrpc_train_sentence2/dset_peek.json b/cache_dir/glue_mrpc_train_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..b2094f823d3bbc86a7a323eaf6f929e0013436e1
--- /dev/null
+++ b/cache_dir/glue_mrpc_train_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc1c7fd9daf223d2e5d55e89bc8f1de82435115fd3a72f1ac66393cfc1a5e08
+size 24645
diff --git a/cache_dir/glue_mrpc_validation_sentence1/dset_peek.json b/cache_dir/glue_mrpc_validation_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..7d7e0bdd95ad8b63eaaf5d1a0a8dd9b94d053caa
--- /dev/null
+++ b/cache_dir/glue_mrpc_validation_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccc3f1ed71a6d7815d59d0823f7a89f3a2e02fc956cceef6b3beeabd3cda0d1
+size 25471
diff --git a/cache_dir/glue_mrpc_validation_sentence2/dset_peek.json b/cache_dir/glue_mrpc_validation_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..7d7e0bdd95ad8b63eaaf5d1a0a8dd9b94d053caa
--- /dev/null
+++ b/cache_dir/glue_mrpc_validation_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccc3f1ed71a6d7815d59d0823f7a89f3a2e02fc956cceef6b3beeabd3cda0d1
+size 25471
diff --git a/cache_dir/glue_qnli_train_question/dset_peek.json b/cache_dir/glue_qnli_train_question/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..036ced30bdfda9598d6ea0135301304fcbb1243d
--- /dev/null
+++ b/cache_dir/glue_qnli_train_question/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d04156d796676c879c7a92016422bba27619cff0df37ff3ac0f98b21a6f3223
+size 24469
diff --git a/cache_dir/glue_qnli_train_sentence/dset_peek.json b/cache_dir/glue_qnli_train_sentence/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..036ced30bdfda9598d6ea0135301304fcbb1243d
--- /dev/null
+++ b/cache_dir/glue_qnli_train_sentence/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d04156d796676c879c7a92016422bba27619cff0df37ff3ac0f98b21a6f3223
+size 24469
diff --git a/cache_dir/glue_qnli_validation_question/dset_peek.json b/cache_dir/glue_qnli_validation_question/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..335e30e213553e572bb876662074d822c1fdef67
--- /dev/null
+++ b/cache_dir/glue_qnli_validation_question/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5db1c6538c353da266b50bfd84907f98c8890da1624ad6d66b37f4ba66a2dad
+size 25142
diff --git a/cache_dir/glue_qnli_validation_sentence/dset_peek.json b/cache_dir/glue_qnli_validation_sentence/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..335e30e213553e572bb876662074d822c1fdef67
--- /dev/null
+++ b/cache_dir/glue_qnli_validation_sentence/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5db1c6538c353da266b50bfd84907f98c8890da1624ad6d66b37f4ba66a2dad
+size 25142
diff --git a/cache_dir/glue_qqp_train_question1/dset_peek.json b/cache_dir/glue_qqp_train_question1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..6ca7d2706d8bc605f34f3c050fd2c5dff6d83270
--- /dev/null
+++ b/cache_dir/glue_qqp_train_question1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81357acfa3a1d2a51ec507e88c2d711e2e483757f0d76c1a33088dc88e6bea42
+size 13229
diff --git a/cache_dir/glue_qqp_train_question2/dset_peek.json b/cache_dir/glue_qqp_train_question2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..6ca7d2706d8bc605f34f3c050fd2c5dff6d83270
--- /dev/null
+++ b/cache_dir/glue_qqp_train_question2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81357acfa3a1d2a51ec507e88c2d711e2e483757f0d76c1a33088dc88e6bea42
+size 13229
diff --git a/cache_dir/glue_qqp_validation_question1/dset_peek.json b/cache_dir/glue_qqp_validation_question1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..8d1c9a57b4676c3b16a62f391bcd6d24c3a7cd8d
--- /dev/null
+++ b/cache_dir/glue_qqp_validation_question1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be141f98ee0a45bc740b0279cd4332188ec52615ebb378501c9e64b50f5105e1
+size 14179
diff --git a/cache_dir/glue_qqp_validation_question2/dset_peek.json b/cache_dir/glue_qqp_validation_question2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..8d1c9a57b4676c3b16a62f391bcd6d24c3a7cd8d
--- /dev/null
+++ b/cache_dir/glue_qqp_validation_question2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be141f98ee0a45bc740b0279cd4332188ec52615ebb378501c9e64b50f5105e1
+size 14179
diff --git a/cache_dir/glue_rte_train_sentence1/dset_peek.json b/cache_dir/glue_rte_train_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..59fe344d52dc4a99ce29cce4a5381380b36dbb8c
--- /dev/null
+++ b/cache_dir/glue_rte_train_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f011e6d0a412e153a2600e78001e62b9e16ba6047033d271f46f8c53e6b0db
+size 32853
diff --git a/cache_dir/glue_rte_train_sentence2/dset_peek.json b/cache_dir/glue_rte_train_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..59fe344d52dc4a99ce29cce4a5381380b36dbb8c
--- /dev/null
+++ b/cache_dir/glue_rte_train_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f011e6d0a412e153a2600e78001e62b9e16ba6047033d271f46f8c53e6b0db
+size 32853
diff --git a/cache_dir/glue_rte_validation_sentence1/dset_peek.json b/cache_dir/glue_rte_validation_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..ee4906353948fb8dacec57d8fa55e4d43815a1f5
--- /dev/null
+++ b/cache_dir/glue_rte_validation_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0772dae1f7f85eddee68d13bdeed98e26dab4b0e029080b6fd58171a634310e5
+size 34344
diff --git a/cache_dir/glue_rte_validation_sentence2/dset_peek.json b/cache_dir/glue_rte_validation_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..ee4906353948fb8dacec57d8fa55e4d43815a1f5
--- /dev/null
+++ b/cache_dir/glue_rte_validation_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0772dae1f7f85eddee68d13bdeed98e26dab4b0e029080b6fd58171a634310e5
+size 34344
diff --git a/cache_dir/glue_sst2_train_sentence/dset_peek.json b/cache_dir/glue_sst2_train_sentence/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..7165e7ecc301bbc005b25322d29410ded08f6192
--- /dev/null
+++ b/cache_dir/glue_sst2_train_sentence/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905f624fdcf49e8453efa180980070e60cc6c0218ec4a1bc07be9362011f0add
+size 6636
diff --git a/cache_dir/glue_sst2_validation_sentence/dset_peek.json b/cache_dir/glue_sst2_validation_sentence/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..e918cb7206e7f7ba599ecb1c3cc57bf28747f661
--- /dev/null
+++ b/cache_dir/glue_sst2_validation_sentence/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc05c70e987696ef3e60c9d002d6416fbf235c8e7fa6de2f8c263ed41dc0edf
+size 11323
diff --git a/cache_dir/glue_stsb_train_sentence1/dset_peek.json b/cache_dir/glue_stsb_train_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..298ebd7ff56f04198733ea76cf74e750244ace8d
--- /dev/null
+++ b/cache_dir/glue_stsb_train_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0cc389971c34e6c97c6925750bfc55c7b7279ca879f5487c766b104df6a922
+size 8440
diff --git a/cache_dir/glue_stsb_train_sentence2/dset_peek.json b/cache_dir/glue_stsb_train_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..298ebd7ff56f04198733ea76cf74e750244ace8d
--- /dev/null
+++ b/cache_dir/glue_stsb_train_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0cc389971c34e6c97c6925750bfc55c7b7279ca879f5487c766b104df6a922
+size 8440
diff --git a/cache_dir/glue_stsb_validation_sentence1/dset_peek.json b/cache_dir/glue_stsb_validation_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..235707b20cb0bd6284fc36e81291b711cb61bf52
--- /dev/null
+++ b/cache_dir/glue_stsb_validation_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6aac15e97faa8b1a8cd1b0b9aaf05f28b87c2d7397cd36a2b2d71a8313e7cf
+size 8837
diff --git a/cache_dir/glue_stsb_validation_sentence2/dset_peek.json b/cache_dir/glue_stsb_validation_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..235707b20cb0bd6284fc36e81291b711cb61bf52
--- /dev/null
+++ b/cache_dir/glue_stsb_validation_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6aac15e97faa8b1a8cd1b0b9aaf05f28b87c2d7397cd36a2b2d71a8313e7cf
+size 8837
diff --git a/cache_dir/glue_wnli_train_sentence1/dset_peek.json b/cache_dir/glue_wnli_train_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..633b608ca5e710a7fe4f03614231bf0d51a6779e
--- /dev/null
+++ b/cache_dir/glue_wnli_train_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89ccc1251c6ef894467c1e7223a491a458a4cf8272f5b6c87552f3eb8eb063a
+size 15735
diff --git a/cache_dir/glue_wnli_train_sentence2/dset_peek.json b/cache_dir/glue_wnli_train_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..633b608ca5e710a7fe4f03614231bf0d51a6779e
--- /dev/null
+++ b/cache_dir/glue_wnli_train_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89ccc1251c6ef894467c1e7223a491a458a4cf8272f5b6c87552f3eb8eb063a
+size 15735
diff --git a/cache_dir/glue_wnli_validation_sentence1/dset_peek.json b/cache_dir/glue_wnli_validation_sentence1/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..e876a53b5ccbb4ece0fd7a313718f48d951cc3ac
--- /dev/null
+++ b/cache_dir/glue_wnli_validation_sentence1/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:302ca5ccd842f2f5b0c69417c1c695560a75606600d5c4d1ca83c42dc0398104
+size 11864
diff --git a/cache_dir/glue_wnli_validation_sentence2/dset_peek.json b/cache_dir/glue_wnli_validation_sentence2/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..e876a53b5ccbb4ece0fd7a313718f48d951cc3ac
--- /dev/null
+++ b/cache_dir/glue_wnli_validation_sentence2/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:302ca5ccd842f2f5b0c69417c1c695560a75606600d5c4d1ca83c42dc0398104
+size 11864
diff --git a/cache_dir/imdb_plain_text_train_text/dset_peek.json b/cache_dir/imdb_plain_text_train_text/dset_peek.json
index 7393a359fff47d0963f0cb96197b915c8d68fa49..acd843f2e98cd12b29765d1357ba46c2bdada0a6 100644
--- a/cache_dir/imdb_plain_text_train_text/dset_peek.json
+++ b/cache_dir/imdb_plain_text_train_text/dset_peek.json
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb96140d8398dfa5e60fb638d9bfa6bba0d3ab9b5ad81c8cd1e928b20a8ff8e
+oid sha256:ba7980a5208ebc6c830a27ae9ee49179c3fb7aa76b20780c442916263d2df219
 size 134773
diff --git a/cache_dir/imdb_plain_text_unsupervised_text/dset_peek.json b/cache_dir/imdb_plain_text_unsupervised_text/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..11daad24b157046661283821d3f15769d1b7b206
--- /dev/null
+++ b/cache_dir/imdb_plain_text_unsupervised_text/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73811e35b12a503e5998a57a60d243cc1e143f9e7f850cf76b9950ec0888376f
+size 151594
diff --git a/cache_dir/wikitext_wikitext-103-raw-v1_train_text/dset_peek.json b/cache_dir/wikitext_wikitext-103-raw-v1_train_text/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..2f4504a06a64429b8edbaa2b98910032a642f85b
--- /dev/null
+++ b/cache_dir/wikitext_wikitext-103-raw-v1_train_text/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76fc0a1a3533b690074337e622218b5e0012d51c878b6ebcab1d43e2c4ca19e
+size 36620
diff --git a/cache_dir/wikitext_wikitext-103-v1_train_text/dset_peek.json b/cache_dir/wikitext_wikitext-103-v1_train_text/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..991227c5753255030304a3bcb6b461013d0e5f35
--- /dev/null
+++ b/cache_dir/wikitext_wikitext-103-v1_train_text/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224189ac5f64e4d3dcb4c2e7457bff776c5086da72f0889acdf64f2302f05bad
+size 36205
diff --git a/cache_dir/wikitext_wikitext-2-v1_train_text/dset_peek.json b/cache_dir/wikitext_wikitext-2-v1_train_text/dset_peek.json
new file mode 100644
index 0000000000000000000000000000000000000000..014b33990aa6f8d9eea44f8f48965eed08adf03e
--- /dev/null
+++ b/cache_dir/wikitext_wikitext-2-v1_train_text/dset_peek.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764cb33f27006bb72015ef725fefebfc7f7034e4caff476df71e99e1af401e4b
+size 35925