pere
/

t5-political-evaluator

Model card Files Files and versions Community

pere commited on Feb 16, 2023

Commit

952379b

•

1 Parent(s): e577c11

test

Browse files

Files changed (9) hide show

__pycache__/my_metrics.cpython-38.pyc +0 -0
__pycache__/tasks.cpython-38.pyc +0 -0
generate_stats.py +15 -4
stats/all.csv +0 -0
stats/all.jsonl +0 -0
stats/average_at_5000.csv +42 -12
stats/average_at_5000.jsonl +122 -92
stats/only_5000.csv +0 -0
stats/only_5000.jsonl +0 -0

__pycache__/my_metrics.cpython-38.pyc DELETED Viewed

Binary file (458 Bytes)

__pycache__/tasks.cpython-38.pyc DELETED Viewed

Binary file (4.82 kB)

generate_stats.py CHANGED Viewed

@@ -12,6 +12,7 @@ bucket = client.bucket("nb-t5x-us-central2")
 checkpoints=["exp1-t5-base-ul2-engvoc","exp2-t5-base-ul2-scandvoc","exp3-t5-base-span-engvoc","exp4-t5-base-span-scandvoc","exp5-t5-base-ul2-scandvoc-full","exp6-t5-base-span-scandvoc-full","exp7-t5-base-ul2-511-scandvoc","exp8-t5-base-span-511-scandvoc","exp9-t5-base-ul2-mt5voc","exp10-t5-base-span-mt5voc","exp11-t5-base-ul2-511-scandvoc-full","exp12-t5-base-span-511-scandvoc-full","exp13-t5-base-ul2-mt5voc-full","exp14-t5-base-span-mt5voc-full","exp15-t5-base-ul2-511-scandvoc-full-scratch","exp16-t5-base-span-511-scandvoc-full-scratch","exp17-t5-small-ul2-mt5voc-scratch","exp18-t5-small-span-mt5voc-scratch","exp19-t5-small-ul2-mt5voc","exp20-t5-small-span-mt5voc","exp21-t5-small-ul2-mt5voc-full","exp22-t5-small-span-mt5voc-full"]
 start=["100000","200000","300000","400000","500000","1000000","1100000","1184000","1200000","1204000","1284000","1300000","1384000","1400000","1484000","1500000"]
@@ -53,6 +54,10 @@ for file_name in file_names:
         downloaded+=1
     content = blob.download_as_string().decode("utf-8")
     # Split the content by newline
     lines = content.split("\n")
@@ -76,11 +81,11 @@ for file_name in file_names:
 print(f"\nTotally {downloaded} files downloaded, {not_downloaded} files not downloaded")
 df = pd.json_normalize(file_contents)
 only_5000 = df[df["finetuning_steps"] == 5000]
-grouped = only_5000[["experiment_name","experiment","pretraining_steps", "accuracy", "f1_macro"]].groupby(["experiment","experiment_name","pretraining_steps"])
-average_at_5000 = grouped.mean().reset_index()
-average_at_5000 = average_at_5000.assign(num_experiements=grouped.size().values)
 only_3000 = df[df["finetuning_steps"] == 3000]
 grouped = only_3000[["experiment_name","experiment","pretraining_steps", "accuracy", "f1_macro"]].groupby(["experiment","experiment_name","pretraining_steps"])
 average_at_3000 = grouped.mean().reset_index()
@@ -89,6 +94,10 @@ average_at_3000 = average_at_3000.assign(rows_count=grouped.size().values)
 #print(average_at_3000.to_string(index=False))
 print(average_at_5000.to_string(index=False))
 df.to_json("stats/all.jsonl", orient="records", lines=True)
 df.to_csv("stats/all.csv", index=False)
@@ -101,3 +110,5 @@ average_at_5000.to_csv("stats/average_at_5000.csv", index=False)
 print(f"Files exported to stats")

 checkpoints=["exp1-t5-base-ul2-engvoc","exp2-t5-base-ul2-scandvoc","exp3-t5-base-span-engvoc","exp4-t5-base-span-scandvoc","exp5-t5-base-ul2-scandvoc-full","exp6-t5-base-span-scandvoc-full","exp7-t5-base-ul2-511-scandvoc","exp8-t5-base-span-511-scandvoc","exp9-t5-base-ul2-mt5voc","exp10-t5-base-span-mt5voc","exp11-t5-base-ul2-511-scandvoc-full","exp12-t5-base-span-511-scandvoc-full","exp13-t5-base-ul2-mt5voc-full","exp14-t5-base-span-mt5voc-full","exp15-t5-base-ul2-511-scandvoc-full-scratch","exp16-t5-base-span-511-scandvoc-full-scratch","exp17-t5-small-ul2-mt5voc-scratch","exp18-t5-small-span-mt5voc-scratch","exp19-t5-small-ul2-mt5voc","exp20-t5-small-span-mt5voc","exp21-t5-small-ul2-mt5voc-full","exp22-t5-small-span-mt5voc-full"]
+#checkpoints=["exp19-t5-small-ul2-mt5voc"]
 start=["100000","200000","300000","400000","500000","1000000","1100000","1184000","1200000","1204000","1284000","1300000","1384000","1400000","1484000","1500000"]
         downloaded+=1
     content = blob.download_as_string().decode("utf-8")
+    #print(file_name)
+    #print(content)
     # Split the content by newline
     lines = content.split("\n")
 print(f"\nTotally {downloaded} files downloaded, {not_downloaded} files not downloaded")
 df = pd.json_normalize(file_contents)
+df = df.drop_duplicates(subset=['step','experiment','version']).reset_index()
 only_5000 = df[df["finetuning_steps"] == 5000]
+grouped_at_5000 = only_5000[["experiment_name","experiment","pretraining_steps", "accuracy", "f1_macro"]].groupby(["experiment","experiment_name","pretraining_steps"])
+average_at_5000 = grouped_at_5000.mean().reset_index()
+average_at_5000 = average_at_5000.assign(num_experiments=grouped_at_5000.size().values)
 only_3000 = df[df["finetuning_steps"] == 3000]
 grouped = only_3000[["experiment_name","experiment","pretraining_steps", "accuracy", "f1_macro"]].groupby(["experiment","experiment_name","pretraining_steps"])
 average_at_3000 = grouped.mean().reset_index()
 #print(average_at_3000.to_string(index=False))
 print(average_at_5000.to_string(index=False))
+print("\Not complete:")
+uncomplete = average_at_5000[average_at_5000['num_experiments'] != 5]
+print(uncomplete)
 df.to_json("stats/all.jsonl", orient="records", lines=True)
 df.to_csv("stats/all.csv", index=False)
 print(f"Files exported to stats")

stats/all.csv CHANGED Viewed

The diff for this file is too large to render. See raw diff

stats/all.jsonl CHANGED Viewed

The diff for this file is too large to render. See raw diff

stats/average_at_5000.csv CHANGED Viewed

@@ -1,4 +1,4 @@
-experiment,experiment_name,pretraining_steps,accuracy,f1_macro,num_experiements
 1,t5-base-ul2-engvoc,1184000,74.23333333333332,74.23014929591753,5
 1,t5-base-ul2-engvoc,1204000,80.26666666666667,80.22823593532767,5
 1,t5-base-ul2-engvoc,1284000,81.56666666666668,81.5626333609857,5
@@ -29,28 +29,58 @@ experiment,experiment_name,pretraining_steps,accuracy,f1_macro,num_experiements
 13,t5-base-ul2-mt5voc-full,1300000,83.91666666666667,83.90209373364846,5
 13,t5-base-ul2-mt5voc-full,1400000,84.31666666666668,84.27949570765468,5
 13,t5-base-ul2-mt5voc-full,1500000,84.56666666666668,84.53493248311972,5
-14,t5-base-span-mt5voc-full,1000000,72.97619047619047,72.95757804295731,7
-14,t5-base-span-mt5voc-full,1100000,84.58333333333334,84.55383892979174,7
-14,t5-base-span-mt5voc-full,1200000,84.22619047619047,84.18982605013198,7
-14,t5-base-span-mt5voc-full,1300000,85.05952380952381,85.03273922929534,7
-14,t5-base-span-mt5voc-full,1400000,85.05208333333333,85.02998383057985,8
-14,t5-base-span-mt5voc-full,1500000,85.21875,85.18068346930292,8
 15,t5-base-ul2-511-scandvoc-full-scratch,1184000,77.88333333333334,77.85173367475181,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1284000,83.26666666666668,83.2260572034256,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1384000,84.6,84.55421921167553,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1484000,81.7,81.67193293949093,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1500000,85.06666666666666,85.04377690141037,5
-16,t5-base-span-511-scandvoc-full-scratch,1184000,77.55952380952381,77.49927148981051,7
-16,t5-base-span-511-scandvoc-full-scratch,1284000,80.66666666666667,80.56192179459941,6
-16,t5-base-span-511-scandvoc-full-scratch,1384000,72.22619047619047,69.75881108207643,7
-16,t5-base-span-511-scandvoc-full-scratch,1484000,78.0,75.20910823189823,6
-16,t5-base-span-511-scandvoc-full-scratch,1500000,83.54166666666667,83.50660007955973,8
 2,t5-base-ul2-scandvoc,1184000,77.6,77.58923655371049,5
 2,t5-base-ul2-scandvoc,1204000,81.27083333333333,81.26140841936191,4
 2,t5-base-ul2-scandvoc,1284000,83.51666666666667,83.45695672244898,5
 2,t5-base-ul2-scandvoc,1300000,83.35,83.32806554148515,5
 2,t5-base-ul2-scandvoc,1400000,84.11666666666667,84.07798589917346,5
 2,t5-base-ul2-scandvoc,1500000,84.75,84.72536066216423,5
 3,t5-base-span-engvoc,1184000,74.63333333333333,74.62000410946226,5
 3,t5-base-span-engvoc,1204000,80.98333333333333,80.9740844273007,5
 3,t5-base-span-engvoc,1284000,79.4,79.33323889498027,5

+experiment,experiment_name,pretraining_steps,accuracy,f1_macro,num_experiments
 1,t5-base-ul2-engvoc,1184000,74.23333333333332,74.23014929591753,5
 1,t5-base-ul2-engvoc,1204000,80.26666666666667,80.22823593532767,5
 1,t5-base-ul2-engvoc,1284000,81.56666666666668,81.5626333609857,5
 13,t5-base-ul2-mt5voc-full,1300000,83.91666666666667,83.90209373364846,5
 13,t5-base-ul2-mt5voc-full,1400000,84.31666666666668,84.27949570765468,5
 13,t5-base-ul2-mt5voc-full,1500000,84.56666666666668,84.53493248311972,5
+14,t5-base-span-mt5voc-full,1000000,73.16666666666666,73.15624812321778,5
+14,t5-base-span-mt5voc-full,1100000,84.8,84.778948711175,5
+14,t5-base-span-mt5voc-full,1200000,84.31666666666666,84.27416931957382,5
+14,t5-base-span-mt5voc-full,1300000,84.83333333333334,84.79738232592145,5
+14,t5-base-span-mt5voc-full,1400000,85.31666666666666,85.30452273995421,5
+14,t5-base-span-mt5voc-full,1500000,84.8,84.75183249932404,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1184000,77.88333333333334,77.85173367475181,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1284000,83.26666666666668,83.2260572034256,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1384000,84.6,84.55421921167553,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1484000,81.7,81.67193293949093,5
 15,t5-base-ul2-511-scandvoc-full-scratch,1500000,85.06666666666666,85.04377690141037,5
+16,t5-base-span-511-scandvoc-full-scratch,1184000,77.21666666666667,77.13530819767436,5
+16,t5-base-span-511-scandvoc-full-scratch,1284000,80.13333333333334,80.00823218481375,5
+16,t5-base-span-511-scandvoc-full-scratch,1384000,74.33333333333333,74.00952055560424,5
+16,t5-base-span-511-scandvoc-full-scratch,1484000,76.81666666666668,73.46974465675156,5
+16,t5-base-span-511-scandvoc-full-scratch,1500000,83.51666666666667,83.47145155470768,5
+17,t5-small-ul2-mt5voc-scratch,100000,82.35,82.30606084377577,5
+17,t5-small-ul2-mt5voc-scratch,200000,81.75,81.6847187052824,5
+17,t5-small-ul2-mt5voc-scratch,300000,82.86666666666667,82.78268738341129,5
+17,t5-small-ul2-mt5voc-scratch,400000,82.31666666666668,82.23044433225218,5
+17,t5-small-ul2-mt5voc-scratch,500000,81.45,81.39528145007205,5
+17,t5-small-ul2-mt5voc-scratch,1000000,81.7,81.67852155576905,5
+17,t5-small-ul2-mt5voc-scratch,1100000,81.56666666666668,81.52271320211511,5
+18,t5-small-span-mt5voc-scratch,100000,82.29166666666667,82.2653488632385,4
+18,t5-small-span-mt5voc-scratch,200000,82.11666666666667,82.06098880578924,5
+18,t5-small-span-mt5voc-scratch,300000,82.53333333333333,82.49038612917455,5
+18,t5-small-span-mt5voc-scratch,400000,82.43333333333334,82.42718912983908,5
+18,t5-small-span-mt5voc-scratch,500000,81.61666666666667,81.56263975693506,5
+19,t5-small-ul2-mt5voc,1000000,69.38333333333333,69.34608002260309,5
+19,t5-small-ul2-mt5voc,1100000,76.9,76.74881584453587,5
+19,t5-small-ul2-mt5voc,1200000,78.1,78.04380021054808,5
+19,t5-small-ul2-mt5voc,1300000,76.28333333333333,76.10195920084124,5
+19,t5-small-ul2-mt5voc,1400000,78.13333333333333,78.07000440858576,5
+19,t5-small-ul2-mt5voc,1500000,77.66666666666666,77.60123555974505,5
 2,t5-base-ul2-scandvoc,1184000,77.6,77.58923655371049,5
 2,t5-base-ul2-scandvoc,1204000,81.27083333333333,81.26140841936191,4
 2,t5-base-ul2-scandvoc,1284000,83.51666666666667,83.45695672244898,5
 2,t5-base-ul2-scandvoc,1300000,83.35,83.32806554148515,5
 2,t5-base-ul2-scandvoc,1400000,84.11666666666667,84.07798589917346,5
 2,t5-base-ul2-scandvoc,1500000,84.75,84.72536066216423,5
+20,t5-small-span-mt5voc,1000000,67.66666666666666,67.58516531591158,5
+20,t5-small-span-mt5voc,1100000,77.68333333333334,77.57485014844569,5
+20,t5-small-span-mt5voc,1200000,71.41666666666667,71.3046914962919,5
+20,t5-small-span-mt5voc,1300000,76.66666666666666,76.58627225785366,5
+20,t5-small-span-mt5voc,1400000,75.78333333333333,75.55343211676256,5
+20,t5-small-span-mt5voc,1500000,72.23333333333332,69.49987728908062,5
+21,t5-small-ul2-mt5voc-full,1000000,68.28333333333333,68.23077615099666,5
+21,t5-small-ul2-mt5voc-full,1100000,77.51666666666668,77.32287928690386,5
+21,t5-small-ul2-mt5voc-full,1200000,76.88333333333334,76.78568232856061,5
+21,t5-small-ul2-mt5voc-full,1300000,77.5625,77.44014671469886,4
+21,t5-small-ul2-mt5voc-full,1400000,78.77083333333333,78.74873465182691,4
+21,t5-small-ul2-mt5voc-full,1500000,79.47916666666666,79.46198316868436,4
 3,t5-base-span-engvoc,1184000,74.63333333333333,74.62000410946226,5
 3,t5-base-span-engvoc,1204000,80.98333333333333,80.9740844273007,5
 3,t5-base-span-engvoc,1284000,79.4,79.33323889498027,5

stats/average_at_5000.jsonl CHANGED Viewed

@@ -1,92 +1,122 @@
-{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1184000,"accuracy":74.2333333333,"f1_macro":74.2301492959,"num_experiements":5}
-{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1204000,"accuracy":80.2666666667,"f1_macro":80.2282359353,"num_experiements":5}
-{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1284000,"accuracy":81.5666666667,"f1_macro":81.562633361,"num_experiements":5}
-{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1300000,"accuracy":80.5666666667,"f1_macro":80.5441057484,"num_experiements":5}
-{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1400000,"accuracy":75.3666666667,"f1_macro":73.1406417385,"num_experiements":5}
-{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1500000,"accuracy":63.9666666667,"f1_macro":56.65949975,"num_experiements":5}
-{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1000000,"accuracy":72.6875,"f1_macro":72.6407835152,"num_experiements":4}
-{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1100000,"accuracy":83.9666666667,"f1_macro":83.9503840052,"num_experiements":5}
-{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1200000,"accuracy":83.35,"f1_macro":83.3413999683,"num_experiements":5}
-{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1300000,"accuracy":83.9333333333,"f1_macro":83.9210042408,"num_experiements":5}
-{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1400000,"accuracy":82.6333333333,"f1_macro":82.602222236,"num_experiements":5}
-{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1500000,"accuracy":76.65,"f1_macro":73.2875255298,"num_experiements":5}
-{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1000000,"accuracy":77.95,"f1_macro":77.9365395658,"num_experiements":5}
-{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1100000,"accuracy":81.5,"f1_macro":81.48782102,"num_experiements":5}
-{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1200000,"accuracy":83.5333333333,"f1_macro":83.5149918634,"num_experiements":5}
-{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1300000,"accuracy":83.6166666667,"f1_macro":83.6036106258,"num_experiements":5}
-{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1400000,"accuracy":83.0,"f1_macro":82.973243183,"num_experiements":5}
-{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1500000,"accuracy":83.5416666667,"f1_macro":83.4830652208,"num_experiements":2}
-{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1000000,"accuracy":76.0,"f1_macro":75.9819813167,"num_experiements":5}
-{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1100000,"accuracy":79.1,"f1_macro":78.8478277886,"num_experiements":5}
-{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1200000,"accuracy":82.4666666667,"f1_macro":82.431266403,"num_experiements":5}
-{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1300000,"accuracy":81.9833333333,"f1_macro":81.919477877,"num_experiements":5}
-{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1400000,"accuracy":81.9166666667,"f1_macro":81.835559089,"num_experiements":5}
-{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1500000,"accuracy":83.5166666667,"f1_macro":83.4802655372,"num_experiements":5}
-{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1000000,"accuracy":72.5,"f1_macro":72.4951550014,"num_experiements":5}
-{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1100000,"accuracy":81.3166666667,"f1_macro":81.2497422408,"num_experiements":5}
-{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1200000,"accuracy":83.6833333333,"f1_macro":83.6623497558,"num_experiements":5}
-{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1300000,"accuracy":83.9166666667,"f1_macro":83.9020937336,"num_experiements":5}
-{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1400000,"accuracy":84.3166666667,"f1_macro":84.2794957077,"num_experiements":5}
-{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1500000,"accuracy":84.5666666667,"f1_macro":84.5349324831,"num_experiements":5}
-{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1000000,"accuracy":72.9761904762,"f1_macro":72.957578043,"num_experiements":7}
-{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1100000,"accuracy":84.5833333333,"f1_macro":84.5538389298,"num_experiements":7}
-{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1200000,"accuracy":84.2261904762,"f1_macro":84.1898260501,"num_experiements":7}
-{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1300000,"accuracy":85.0595238095,"f1_macro":85.0327392293,"num_experiements":7}
-{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1400000,"accuracy":85.0520833333,"f1_macro":85.0299838306,"num_experiements":8}
-{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1500000,"accuracy":85.21875,"f1_macro":85.1806834693,"num_experiements":8}
-{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1184000,"accuracy":77.8833333333,"f1_macro":77.8517336748,"num_experiements":5}
-{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1284000,"accuracy":83.2666666667,"f1_macro":83.2260572034,"num_experiements":5}
-{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1384000,"accuracy":84.6,"f1_macro":84.5542192117,"num_experiements":5}
-{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1484000,"accuracy":81.7,"f1_macro":81.6719329395,"num_experiements":5}
-{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1500000,"accuracy":85.0666666667,"f1_macro":85.0437769014,"num_experiements":5}
-{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1184000,"accuracy":77.5595238095,"f1_macro":77.4992714898,"num_experiements":7}
-{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1284000,"accuracy":80.6666666667,"f1_macro":80.5619217946,"num_experiements":6}
-{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1384000,"accuracy":72.2261904762,"f1_macro":69.7588110821,"num_experiements":7}
-{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1484000,"accuracy":78.0,"f1_macro":75.2091082319,"num_experiements":6}
-{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1500000,"accuracy":83.5416666667,"f1_macro":83.5066000796,"num_experiements":8}
-{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1184000,"accuracy":77.6,"f1_macro":77.5892365537,"num_experiements":5}
-{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1204000,"accuracy":81.2708333333,"f1_macro":81.2614084194,"num_experiements":4}
-{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1284000,"accuracy":83.5166666667,"f1_macro":83.4569567224,"num_experiements":5}
-{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1300000,"accuracy":83.35,"f1_macro":83.3280655415,"num_experiements":5}
-{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1400000,"accuracy":84.1166666667,"f1_macro":84.0779858992,"num_experiements":5}
-{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1500000,"accuracy":84.75,"f1_macro":84.7253606622,"num_experiements":5}
-{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1184000,"accuracy":74.6333333333,"f1_macro":74.6200041095,"num_experiements":5}
-{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1204000,"accuracy":80.9833333333,"f1_macro":80.9740844273,"num_experiements":5}
-{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1284000,"accuracy":79.4,"f1_macro":79.333238895,"num_experiements":5}
-{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1300000,"accuracy":77.7666666667,"f1_macro":77.6803642122,"num_experiements":5}
-{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1400000,"accuracy":78.2,"f1_macro":78.1951653886,"num_experiements":5}
-{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1500000,"accuracy":76.3166666667,"f1_macro":76.2973105322,"num_experiements":5}
-{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1184000,"accuracy":77.35,"f1_macro":77.3336095988,"num_experiements":5}
-{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1204000,"accuracy":82.6333333333,"f1_macro":82.6293487369,"num_experiements":5}
-{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1284000,"accuracy":83.5,"f1_macro":83.4834082879,"num_experiements":5}
-{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1300000,"accuracy":83.4333333333,"f1_macro":83.4195232466,"num_experiements":5}
-{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1400000,"accuracy":76.8333333333,"f1_macro":73.4840684203,"num_experiements":5}
-{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1500000,"accuracy":75.7666666667,"f1_macro":72.4110729975,"num_experiements":5}
-{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1184000,"accuracy":77.1041666667,"f1_macro":77.0963712874,"num_experiements":4}
-{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1284000,"accuracy":84.9333333333,"f1_macro":84.9195472261,"num_experiements":5}
-{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1384000,"accuracy":83.3,"f1_macro":83.2918726525,"num_experiements":5}
-{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1484000,"accuracy":86.75,"f1_macro":86.7497325508,"num_experiements":5}
-{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1500000,"accuracy":86.05,"f1_macro":86.0381232786,"num_experiements":5}
-{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1184000,"accuracy":78.9333333333,"f1_macro":78.9271489614,"num_experiements":5}
-{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1284000,"accuracy":85.35,"f1_macro":85.335785239,"num_experiements":5}
-{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1384000,"accuracy":85.8166666667,"f1_macro":85.8080171241,"num_experiements":5}
-{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1484000,"accuracy":85.25,"f1_macro":85.2243496772,"num_experiements":5}
-{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1500000,"accuracy":85.2166666667,"f1_macro":85.1992014678,"num_experiements":5}
-{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1000000,"accuracy":73.8333333333,"f1_macro":73.8061730252,"num_experiements":5}
-{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1100000,"accuracy":76.0166666667,"f1_macro":75.9942316465,"num_experiements":5}
-{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1200000,"accuracy":77.7666666667,"f1_macro":77.7030816078,"num_experiements":5}
-{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1300000,"accuracy":76.65,"f1_macro":76.6085376539,"num_experiements":5}
-{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1400000,"accuracy":78.55,"f1_macro":78.5337238563,"num_experiements":5}
-{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1500000,"accuracy":78.7833333333,"f1_macro":78.755274257,"num_experiements":5}
-{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1000000,"accuracy":75.45,"f1_macro":75.4303591458,"num_experiements":5}
-{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1100000,"accuracy":76.75,"f1_macro":76.4553139363,"num_experiements":5}
-{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1200000,"accuracy":72.2833333333,"f1_macro":68.9063221254,"num_experiements":5}
-{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1300000,"accuracy":56.45,"f1_macro":45.5065610464,"num_experiements":5}
-{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1400000,"accuracy":60.9666666667,"f1_macro":56.1138360815,"num_experiements":5}
-{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1500000,"accuracy":64.35,"f1_macro":58.429161656,"num_experiements":5}
-{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1000000,"accuracy":71.1,"f1_macro":71.0952242998,"num_experiements":5}
-{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1100000,"accuracy":81.0333333333,"f1_macro":80.9959212654,"num_experiements":5}
-{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1200000,"accuracy":80.5,"f1_macro":80.3834883051,"num_experiements":5}
-{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1300000,"accuracy":82.7666666667,"f1_macro":82.7304446175,"num_experiements":5}
-{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1400000,"accuracy":82.65,"f1_macro":82.6014266748,"num_experiements":5}
-{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1500000,"accuracy":83.6666666667,"f1_macro":83.6466045157,"num_experiements":5}

+{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1184000,"accuracy":74.2333333333,"f1_macro":74.2301492959,"num_experiments":5}
+{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1204000,"accuracy":80.2666666667,"f1_macro":80.2282359353,"num_experiments":5}
+{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1284000,"accuracy":81.5666666667,"f1_macro":81.562633361,"num_experiments":5}
+{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1300000,"accuracy":80.5666666667,"f1_macro":80.5441057484,"num_experiments":5}
+{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1400000,"accuracy":75.3666666667,"f1_macro":73.1406417385,"num_experiments":5}
+{"experiment":"1","experiment_name":"t5-base-ul2-engvoc","pretraining_steps":1500000,"accuracy":63.9666666667,"f1_macro":56.65949975,"num_experiments":5}
+{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1000000,"accuracy":72.6875,"f1_macro":72.6407835152,"num_experiments":4}
+{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1100000,"accuracy":83.9666666667,"f1_macro":83.9503840052,"num_experiments":5}
+{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1200000,"accuracy":83.35,"f1_macro":83.3413999683,"num_experiments":5}
+{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1300000,"accuracy":83.9333333333,"f1_macro":83.9210042408,"num_experiments":5}
+{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1400000,"accuracy":82.6333333333,"f1_macro":82.602222236,"num_experiments":5}
+{"experiment":"10","experiment_name":"t5-base-span-mt5voc","pretraining_steps":1500000,"accuracy":76.65,"f1_macro":73.2875255298,"num_experiments":5}
+{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1000000,"accuracy":77.95,"f1_macro":77.9365395658,"num_experiments":5}
+{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1100000,"accuracy":81.5,"f1_macro":81.48782102,"num_experiments":5}
+{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1200000,"accuracy":83.5333333333,"f1_macro":83.5149918634,"num_experiments":5}
+{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1300000,"accuracy":83.6166666667,"f1_macro":83.6036106258,"num_experiments":5}
+{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1400000,"accuracy":83.0,"f1_macro":82.973243183,"num_experiments":5}
+{"experiment":"11","experiment_name":"t5-base-ul2-511-scandvoc-full","pretraining_steps":1500000,"accuracy":83.5416666667,"f1_macro":83.4830652208,"num_experiments":2}
+{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1000000,"accuracy":76.0,"f1_macro":75.9819813167,"num_experiments":5}
+{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1100000,"accuracy":79.1,"f1_macro":78.8478277886,"num_experiments":5}
+{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1200000,"accuracy":82.4666666667,"f1_macro":82.431266403,"num_experiments":5}
+{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1300000,"accuracy":81.9833333333,"f1_macro":81.919477877,"num_experiments":5}
+{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1400000,"accuracy":81.9166666667,"f1_macro":81.835559089,"num_experiments":5}
+{"experiment":"12","experiment_name":"t5-base-span-511-scandvoc-full","pretraining_steps":1500000,"accuracy":83.5166666667,"f1_macro":83.4802655372,"num_experiments":5}
+{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1000000,"accuracy":72.5,"f1_macro":72.4951550014,"num_experiments":5}
+{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1100000,"accuracy":81.3166666667,"f1_macro":81.2497422408,"num_experiments":5}
+{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1200000,"accuracy":83.6833333333,"f1_macro":83.6623497558,"num_experiments":5}
+{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1300000,"accuracy":83.9166666667,"f1_macro":83.9020937336,"num_experiments":5}
+{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1400000,"accuracy":84.3166666667,"f1_macro":84.2794957077,"num_experiments":5}
+{"experiment":"13","experiment_name":"t5-base-ul2-mt5voc-full","pretraining_steps":1500000,"accuracy":84.5666666667,"f1_macro":84.5349324831,"num_experiments":5}
+{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1000000,"accuracy":73.1666666667,"f1_macro":73.1562481232,"num_experiments":5}
+{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1100000,"accuracy":84.8,"f1_macro":84.7789487112,"num_experiments":5}
+{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1200000,"accuracy":84.3166666667,"f1_macro":84.2741693196,"num_experiments":5}
+{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1300000,"accuracy":84.8333333333,"f1_macro":84.7973823259,"num_experiments":5}
+{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1400000,"accuracy":85.3166666667,"f1_macro":85.30452274,"num_experiments":5}
+{"experiment":"14","experiment_name":"t5-base-span-mt5voc-full","pretraining_steps":1500000,"accuracy":84.8,"f1_macro":84.7518324993,"num_experiments":5}
+{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1184000,"accuracy":77.8833333333,"f1_macro":77.8517336748,"num_experiments":5}
+{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1284000,"accuracy":83.2666666667,"f1_macro":83.2260572034,"num_experiments":5}
+{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1384000,"accuracy":84.6,"f1_macro":84.5542192117,"num_experiments":5}
+{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1484000,"accuracy":81.7,"f1_macro":81.6719329395,"num_experiments":5}
+{"experiment":"15","experiment_name":"t5-base-ul2-511-scandvoc-full-scratch","pretraining_steps":1500000,"accuracy":85.0666666667,"f1_macro":85.0437769014,"num_experiments":5}
+{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1184000,"accuracy":77.2166666667,"f1_macro":77.1353081977,"num_experiments":5}
+{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1284000,"accuracy":80.1333333333,"f1_macro":80.0082321848,"num_experiments":5}
+{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1384000,"accuracy":74.3333333333,"f1_macro":74.0095205556,"num_experiments":5}
+{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1484000,"accuracy":76.8166666667,"f1_macro":73.4697446568,"num_experiments":5}
+{"experiment":"16","experiment_name":"t5-base-span-511-scandvoc-full-scratch","pretraining_steps":1500000,"accuracy":83.5166666667,"f1_macro":83.4714515547,"num_experiments":5}
+{"experiment":"17","experiment_name":"t5-small-ul2-mt5voc-scratch","pretraining_steps":100000,"accuracy":82.35,"f1_macro":82.3060608438,"num_experiments":5}
+{"experiment":"17","experiment_name":"t5-small-ul2-mt5voc-scratch","pretraining_steps":200000,"accuracy":81.75,"f1_macro":81.6847187053,"num_experiments":5}
+{"experiment":"17","experiment_name":"t5-small-ul2-mt5voc-scratch","pretraining_steps":300000,"accuracy":82.8666666667,"f1_macro":82.7826873834,"num_experiments":5}
+{"experiment":"17","experiment_name":"t5-small-ul2-mt5voc-scratch","pretraining_steps":400000,"accuracy":82.3166666667,"f1_macro":82.2304443323,"num_experiments":5}
+{"experiment":"17","experiment_name":"t5-small-ul2-mt5voc-scratch","pretraining_steps":500000,"accuracy":81.45,"f1_macro":81.3952814501,"num_experiments":5}
+{"experiment":"17","experiment_name":"t5-small-ul2-mt5voc-scratch","pretraining_steps":1000000,"accuracy":81.7,"f1_macro":81.6785215558,"num_experiments":5}
+{"experiment":"17","experiment_name":"t5-small-ul2-mt5voc-scratch","pretraining_steps":1100000,"accuracy":81.5666666667,"f1_macro":81.5227132021,"num_experiments":5}
+{"experiment":"18","experiment_name":"t5-small-span-mt5voc-scratch","pretraining_steps":100000,"accuracy":82.2916666667,"f1_macro":82.2653488632,"num_experiments":4}
+{"experiment":"18","experiment_name":"t5-small-span-mt5voc-scratch","pretraining_steps":200000,"accuracy":82.1166666667,"f1_macro":82.0609888058,"num_experiments":5}
+{"experiment":"18","experiment_name":"t5-small-span-mt5voc-scratch","pretraining_steps":300000,"accuracy":82.5333333333,"f1_macro":82.4903861292,"num_experiments":5}
+{"experiment":"18","experiment_name":"t5-small-span-mt5voc-scratch","pretraining_steps":400000,"accuracy":82.4333333333,"f1_macro":82.4271891298,"num_experiments":5}
+{"experiment":"18","experiment_name":"t5-small-span-mt5voc-scratch","pretraining_steps":500000,"accuracy":81.6166666667,"f1_macro":81.5626397569,"num_experiments":5}
+{"experiment":"19","experiment_name":"t5-small-ul2-mt5voc","pretraining_steps":1000000,"accuracy":69.3833333333,"f1_macro":69.3460800226,"num_experiments":5}
+{"experiment":"19","experiment_name":"t5-small-ul2-mt5voc","pretraining_steps":1100000,"accuracy":76.9,"f1_macro":76.7488158445,"num_experiments":5}
+{"experiment":"19","experiment_name":"t5-small-ul2-mt5voc","pretraining_steps":1200000,"accuracy":78.1,"f1_macro":78.0438002105,"num_experiments":5}
+{"experiment":"19","experiment_name":"t5-small-ul2-mt5voc","pretraining_steps":1300000,"accuracy":76.2833333333,"f1_macro":76.1019592008,"num_experiments":5}
+{"experiment":"19","experiment_name":"t5-small-ul2-mt5voc","pretraining_steps":1400000,"accuracy":78.1333333333,"f1_macro":78.0700044086,"num_experiments":5}
+{"experiment":"19","experiment_name":"t5-small-ul2-mt5voc","pretraining_steps":1500000,"accuracy":77.6666666667,"f1_macro":77.6012355597,"num_experiments":5}
+{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1184000,"accuracy":77.6,"f1_macro":77.5892365537,"num_experiments":5}
+{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1204000,"accuracy":81.2708333333,"f1_macro":81.2614084194,"num_experiments":4}
+{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1284000,"accuracy":83.5166666667,"f1_macro":83.4569567224,"num_experiments":5}
+{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1300000,"accuracy":83.35,"f1_macro":83.3280655415,"num_experiments":5}
+{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1400000,"accuracy":84.1166666667,"f1_macro":84.0779858992,"num_experiments":5}
+{"experiment":"2","experiment_name":"t5-base-ul2-scandvoc","pretraining_steps":1500000,"accuracy":84.75,"f1_macro":84.7253606622,"num_experiments":5}
+{"experiment":"20","experiment_name":"t5-small-span-mt5voc","pretraining_steps":1000000,"accuracy":67.6666666667,"f1_macro":67.5851653159,"num_experiments":5}
+{"experiment":"20","experiment_name":"t5-small-span-mt5voc","pretraining_steps":1100000,"accuracy":77.6833333333,"f1_macro":77.5748501484,"num_experiments":5}
+{"experiment":"20","experiment_name":"t5-small-span-mt5voc","pretraining_steps":1200000,"accuracy":71.4166666667,"f1_macro":71.3046914963,"num_experiments":5}
+{"experiment":"20","experiment_name":"t5-small-span-mt5voc","pretraining_steps":1300000,"accuracy":76.6666666667,"f1_macro":76.5862722579,"num_experiments":5}
+{"experiment":"20","experiment_name":"t5-small-span-mt5voc","pretraining_steps":1400000,"accuracy":75.7833333333,"f1_macro":75.5534321168,"num_experiments":5}
+{"experiment":"20","experiment_name":"t5-small-span-mt5voc","pretraining_steps":1500000,"accuracy":72.2333333333,"f1_macro":69.4998772891,"num_experiments":5}
+{"experiment":"21","experiment_name":"t5-small-ul2-mt5voc-full","pretraining_steps":1000000,"accuracy":68.2833333333,"f1_macro":68.230776151,"num_experiments":5}
+{"experiment":"21","experiment_name":"t5-small-ul2-mt5voc-full","pretraining_steps":1100000,"accuracy":77.5166666667,"f1_macro":77.3228792869,"num_experiments":5}
+{"experiment":"21","experiment_name":"t5-small-ul2-mt5voc-full","pretraining_steps":1200000,"accuracy":76.8833333333,"f1_macro":76.7856823286,"num_experiments":5}
+{"experiment":"21","experiment_name":"t5-small-ul2-mt5voc-full","pretraining_steps":1300000,"accuracy":77.5625,"f1_macro":77.4401467147,"num_experiments":4}
+{"experiment":"21","experiment_name":"t5-small-ul2-mt5voc-full","pretraining_steps":1400000,"accuracy":78.7708333333,"f1_macro":78.7487346518,"num_experiments":4}
+{"experiment":"21","experiment_name":"t5-small-ul2-mt5voc-full","pretraining_steps":1500000,"accuracy":79.4791666667,"f1_macro":79.4619831687,"num_experiments":4}
+{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1184000,"accuracy":74.6333333333,"f1_macro":74.6200041095,"num_experiments":5}
+{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1204000,"accuracy":80.9833333333,"f1_macro":80.9740844273,"num_experiments":5}
+{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1284000,"accuracy":79.4,"f1_macro":79.333238895,"num_experiments":5}
+{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1300000,"accuracy":77.7666666667,"f1_macro":77.6803642122,"num_experiments":5}
+{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1400000,"accuracy":78.2,"f1_macro":78.1951653886,"num_experiments":5}
+{"experiment":"3","experiment_name":"t5-base-span-engvoc","pretraining_steps":1500000,"accuracy":76.3166666667,"f1_macro":76.2973105322,"num_experiments":5}
+{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1184000,"accuracy":77.35,"f1_macro":77.3336095988,"num_experiments":5}
+{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1204000,"accuracy":82.6333333333,"f1_macro":82.6293487369,"num_experiments":5}
+{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1284000,"accuracy":83.5,"f1_macro":83.4834082879,"num_experiments":5}
+{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1300000,"accuracy":83.4333333333,"f1_macro":83.4195232466,"num_experiments":5}
+{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1400000,"accuracy":76.8333333333,"f1_macro":73.4840684203,"num_experiments":5}
+{"experiment":"4","experiment_name":"t5-base-span-scandvoc","pretraining_steps":1500000,"accuracy":75.7666666667,"f1_macro":72.4110729975,"num_experiments":5}
+{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1184000,"accuracy":77.1041666667,"f1_macro":77.0963712874,"num_experiments":4}
+{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1284000,"accuracy":84.9333333333,"f1_macro":84.9195472261,"num_experiments":5}
+{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1384000,"accuracy":83.3,"f1_macro":83.2918726525,"num_experiments":5}
+{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1484000,"accuracy":86.75,"f1_macro":86.7497325508,"num_experiments":5}
+{"experiment":"5","experiment_name":"t5-base-ul2-scandvoc-full","pretraining_steps":1500000,"accuracy":86.05,"f1_macro":86.0381232786,"num_experiments":5}
+{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1184000,"accuracy":78.9333333333,"f1_macro":78.9271489614,"num_experiments":5}
+{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1284000,"accuracy":85.35,"f1_macro":85.335785239,"num_experiments":5}
+{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1384000,"accuracy":85.8166666667,"f1_macro":85.8080171241,"num_experiments":5}
+{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1484000,"accuracy":85.25,"f1_macro":85.2243496772,"num_experiments":5}
+{"experiment":"6","experiment_name":"t5-base-span-scandvoc-full","pretraining_steps":1500000,"accuracy":85.2166666667,"f1_macro":85.1992014678,"num_experiments":5}
+{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1000000,"accuracy":73.8333333333,"f1_macro":73.8061730252,"num_experiments":5}
+{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1100000,"accuracy":76.0166666667,"f1_macro":75.9942316465,"num_experiments":5}
+{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1200000,"accuracy":77.7666666667,"f1_macro":77.7030816078,"num_experiments":5}
+{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1300000,"accuracy":76.65,"f1_macro":76.6085376539,"num_experiments":5}
+{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1400000,"accuracy":78.55,"f1_macro":78.5337238563,"num_experiments":5}
+{"experiment":"7","experiment_name":"t5-base-ul2-511-scandvoc","pretraining_steps":1500000,"accuracy":78.7833333333,"f1_macro":78.755274257,"num_experiments":5}
+{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1000000,"accuracy":75.45,"f1_macro":75.4303591458,"num_experiments":5}
+{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1100000,"accuracy":76.75,"f1_macro":76.4553139363,"num_experiments":5}
+{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1200000,"accuracy":72.2833333333,"f1_macro":68.9063221254,"num_experiments":5}
+{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1300000,"accuracy":56.45,"f1_macro":45.5065610464,"num_experiments":5}
+{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1400000,"accuracy":60.9666666667,"f1_macro":56.1138360815,"num_experiments":5}
+{"experiment":"8","experiment_name":"t5-base-span-511-scandvoc","pretraining_steps":1500000,"accuracy":64.35,"f1_macro":58.429161656,"num_experiments":5}
+{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1000000,"accuracy":71.1,"f1_macro":71.0952242998,"num_experiments":5}
+{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1100000,"accuracy":81.0333333333,"f1_macro":80.9959212654,"num_experiments":5}
+{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1200000,"accuracy":80.5,"f1_macro":80.3834883051,"num_experiments":5}
+{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1300000,"accuracy":82.7666666667,"f1_macro":82.7304446175,"num_experiments":5}
+{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1400000,"accuracy":82.65,"f1_macro":82.6014266748,"num_experiments":5}
+{"experiment":"9","experiment_name":"t5-base-ul2-mt5voc","pretraining_steps":1500000,"accuracy":83.6666666667,"f1_macro":83.6466045157,"num_experiments":5}

stats/only_5000.csv CHANGED Viewed

The diff for this file is too large to render. See raw diff

stats/only_5000.jsonl CHANGED Viewed

The diff for this file is too large to render. See raw diff