Muennighoff commited on
Commit
baaf1cc
·
1 Parent(s): 9df9cd5
train84b10c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.1 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.9 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b20c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.2 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.8 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b30c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.3 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.7 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b40c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.4 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.6 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b50c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.5 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.5 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b60c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.6 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.4 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b70c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.7 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.3 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b80c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.8 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.2 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
train84b90c4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "train: 0.9 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_84B_text_document, 0.1 0:1 /scratch/project_462000119/data/python/gpt2tok_python_84B_content_document"
valc4py.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ "validation: 1.0 0:1 /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document" "validation_python: 1.0 0.95:1 /scratch/project_462000119/data/python/gpt2tok_python_content_document"