Gabriel_syme's workspace
Runs
259
Name
252 visualized
State
Created
Runtime
Tags
layers
d_model
n_heads
lr
train/last_loss
train/loss
val/loss_architext
gradient_accumulation_steps
tokens_processed
sequences_processed
total_steps
anneal_steps
warmup_steps
train/learning_rate
train/tokens_per_sec
Finished
7h 21m 55s
16BS
85M
8H
12
768
8
0.0001
0.00033351
0.089927
0.090971
8
1653276672
807264
50454
45409
5045
0.00001
67464.07156
Crashed
18h 59m 47s
150M
16H
512BS
12
1024
16
0.0003
0.10008
0.090173
0.09105
256
4617928704
2254848
1576
1419
157
0.00003
46328.68891
Finished
7h 29m 26s
16BS
85M
8H
12
768
8
0.000224
0.00036284
0.090016
0.091093
8
1653276672
807264
50454
45409
5045
0.0000224
66855.21896
Finished
7h 30m 2s
16BS
85M
8H
12
768
8
0.0003
0.00033155
0.090228
0.091143
8
1653276672
807264
50454
45409
5045
0.00003
66573.77082
Finished
8h 55m 11s
4BS
85M
8H
12
768
8
0.0001
0.000011375
0.099309
0.091174
2
1653293056
807272
201818
181637
20181
0.00001
58625.76203
Finished
4h 54m 58s
64BS
85M
8H
12
768
8
0.0003
0.026864
0.091895
0.091561
32
1653211136
807232
12613
11352
1261
0.00003
69146.69962
Finished
7h 8m 24s
64BS
85M
8H
12
768
8
0.0005
0.026767
0.09175
0.091775
32
1653211136
807232
12613
11352
1261
0.00005
69155.51958
Finished
7h 3m 26s
64BS
85M
8H
12
768
8
0.000224
0.026965
0.091806
0.091785
32
1653211136
807232
12613
11352
1261
0.0000224
70030.83922
Finished
7h 27m 25s
64BS
85M
8H
12
768
8
0.0007
0.0002685
0.091172
0.091908
8
1653276672
807264
50454
45409
5045
0.00007
66840.91288
Finished
8h 59m 52s
4BS
85M
8H
12
768
8
0.000224
0.000012381
0.098981
0.092139
2
1653293056
807272
201818
181637
20181
0.0000224
58336.90732
Finished
7h 3m 10s
64BS
85M
8H
12
768
8
0.0001
0.026977
0.091992
0.092176
32
1653211136
807232
12613
11352
1261
0.00001
69967.99437
Finished
7h 9m 5s
64BS
85M
8H
12
768
8
0.0007
0.026902
0.092371
0.092273
32
1653211136
807232
12613
11352
1261
0.00007
69160.61774
Finished
8h 50m 52s
4BS
85M
8H
12
768
8
0.0003
0.000010574
0.099708
0.092604
2
1653293056
807272
201818
181637
20181
0.00003
59326.33769
Crashed
19h 50m 27s
150M
16H
512BS
12
1024
16
0.0001
0.071913
0.092299
0.092634
256
4707057664
2298368
1576
1419
157
0.00001
45655.7826
Finished
7h 8m 28s
256BS
85M
8H
12
768
8
0.0007
0.096054
0.093078
0.093215
128
1653080064
807168
3153
2838
315
0.00007
69830.90321
Finished
7h 8m 18s
64BS
85M
8H
12
768
8
0.00224
0.099501
0.093006
0.093218
128
1653080064
807168
3153
2838
315
0.000224
69835.2254
Finished
1d 16h 43m 3s
1400M
48H
512BS
12
3168
48
0.0003
0.088809
0.093115
0.093537
256
1652555776
806912
1576
1419
157
0.00003
11772.93367
Finished
7h 2m 48s
256BS
85M
8H
12
768
8
0.0005
0.097257
0.093284
0.093668
128
1653080064
807168
3153
2838
315
0.00005
70840.70878
Finished
1d 12h 47m 44s
1400M
48H
512BS
12
3168
48
0.0001
0.091445
0.09333
0.093717
256
1652555776
806912
1576
1419
157
0.00001
11773.48072
Finished
7h 2m 47s
85M
12
768
8
0.0003
0.095951
0.093773
0.09396
128
1653080064
807168
3153
2838
315
0.00003
70847.15176
1-20
of 259