Awni00's workspace
Runs
71
Name
71 visualized
State
Notes
Tags
GPU Type
Created
Runtime
d_model
decoder_kwargs.activation
decoder_kwargs.causal
decoder_kwargs.dff
decoder_kwargs.dropout_rate
decoder_kwargs.n_heads
decoder_kwargs.n_heads_cross
decoder_kwargs.n_heads_rca
decoder_kwargs.n_heads_sa
decoder_kwargs.norm_first
decoder_kwargs.rca_kwargs.use_relative_positional_symbols
decoder_kwargs.rca_type
encoder_kwargs.activation
encoder_kwargs.causal
encoder_kwargs.dff
encoder_kwargs.dropout_rate
encoder_kwargs.n_heads
encoder_kwargs.n_heads_rca
encoder_kwargs.n_heads_sa
encoder_kwargs.norm_first
encoder_kwargs.rca_kwargs.use_relative_positional_symbols
encoder_kwargs.rca_type
group
in_block_size
input_spec.type
input_spec.vocab_size
loss_ignore_idx
n_layers_dec
n_layers_enc
out_block_size
out_dim
output_spec.type
output_spec.vocab_size
symbol_retrieval
symbol_retrieval_kwargs.max_rel_pos
symbol_retrieval_kwargs.symbol_dim
abstractor_kwargs.activation
abstractor_kwargs.d_model
abstractor_kwargs.dff
abstractor_kwargs.dropout_rate
abstractor_kwargs.max_len
abstractor_kwargs.n_heads
abstractor_kwargs.n_layers
Finished
-
1d 6h 57m 8s
144
relu
true
288
0.1
8
8
-
-
false
-
-
relu
false
288
0.1
8
-
-
false
-
-
enc_sa=8; enc_ra=0; dec_sa=8; dec_ra=0; d_cross=8; d=144; el=3; dl=3
161
token
85
0
3
3
31
85
token
85
-
-
-
-
-
-
-
-
-
-
Finished
-
10d 21h 9m 39s
144
relu
true
288
0.1
8
8
-
-
false
-
-
relu
false
288
0.1
8
-
-
false
-
-
enc_sa=8; enc_ra=0; dec_sa=8; dec_ra=0; d_cross=8; d=144; el=4; dl=4
161
token
85
0
4
4
31
85
token
85
-
-
-
-
-
-
-
-
-
-
Crashed
Finished
-
13d 13h 23m
128
relu
true
256
0.1
-
8
-
8
false
-
-
relu
false
256
0.1
-
-
4
false
-
-
enc_sa=4; enc_ra=4; dec_sa=8; dec_ra=0; d_cross=8; d=128; el=4; dl=4
161
token
85
0
4
4
31
85
token
85
position_relative
161
128
-
-
-
-
-
-
-
Crashed
Finished
-
12d 19h 47m 22s
128
relu
true
256
0.1
-
8
-
4
false
-
-
relu
false
256
0.1
-
-
4
false
-
-
enc_sa=4; enc_ra=4; dec_sa=4; dec_ra=4; d_cross=8; d=128; el=4; dl=4
161
token
85
0
4
4
31
85
token
85
position_relative
161
128
-
-
-
-
-
-
-
Finished
-
12d 11h 35m 39s
128
relu
true
256
0.1
-
8
-
8
false
-
-
relu
false
256
0.1
-
-
4
false
-
-
enc_sa=4; enc_ra=4; dec_sa=8; dec_ra=0; d_cross=8; d=128; el=3; dl=3
161
token
85
0
3
3
31
85
token
85
position_relative
161
128
-
-
-
-
-
-
-
Crashed
Finished
-
12d 20h 18m 58s
128
relu
true
256
0.1
-
8
-
4
false
-
-
relu
false
256
0.1
-
-
4
false
-
-
enc_sa=4; enc_ra=4; dec_sa=4; dec_ra=4; d_cross=8; d=128; el=3; dl=3
161
token
85
0
3
3
31
85
token
85
position_relative
161
128
-
-
-
-
-
-
-
Finished
-
23h 27m 6s
128
relu
true
256
0.1
8
8
-
-
false
-
-
relu
false
256
0.1
8
-
-
false
-
-
Abstractor - L=2, d=128, h=8
161
token
85
-
2
2
31
85
token
85
-
-
-
relu
128
256
0.1
161
8
2
Crashed
Finished
-
17h 35m 24s
128
relu
true
256
0.1
8
8
-
-
false
-
-
relu
false
256
0.1
8
-
-
false
-
-
Abstractor - L=1, d=128, h=8
161
token
85
-
1
1
31
85
token
85
-
-
-
relu
128
256
0.1
161
8
1
Finished
-
8h 27m 50s
128
relu
true
256
0.1
8
8
-
-
false
-
-
relu
false
256
0.1
8
-
-
false
-
-
e_sa=8; e_rca=0; d_sa=8; d_rca=0; d_cross=8; d=128; rca_type=NA, symbol_type=NA; el=2; dl=2
161
token
85
0
2
2
31
85
token
85
-
-
-
-
-
-
-
-
-
-
Crashed
Finished
-
3d 18s
128
relu
true
256
0.1
-
8
0
8
false
true
disentangled_v2
relu
false
256
0.1
-
4
4
false
true
disentangled_v2
e_sa=4; e_rca=4; d_sa=8; d_rca=0; d_cross=8; d=128; rca_type=disentangled_v2, symbol_type=pos_relative; el=2; dl=2
161
token
85
0
2
2
31
85
token
85
pos_relative
161
128
-
-
-
-
-
-
-
Crashed
Finished
-
3d 13s
128
relu
true
256
0.1
-
8
4
4
false
true
disentangled_v2
relu
false
256
0.1
-
4
4
false
true
disentangled_v2
e_sa=4; e_rca=4; d_sa=4; d_rca=4; d_cross=8; d=128; rca_type=disentangled_v2, symbol_type=pos_relative; el=2; dl=2
161
token
85
0
2
2
31
85
token
85
pos_relative
161
128
-
-
-
-
-
-
-
Finished
-
4d 9h 28m 55s
144
relu
true
288
0.1
8
8
-
-
false
-
-
relu
false
288
0.1
8
-
-
false
-
-
e_sa=8; e_rca=0; d_sa=8; d_rca=0; d_cross=8; d=144; rca_type=NA, symbol_type=NA; el=2; dl=2
161
token
85
0
2
2
31
85
token
85
-
-
-
-
-
-
-
-
-
-
1-12
of 12