Peterjin's workspace
Runs
10
Name
10 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
actor/entropy_loss
actor/grad_norm
actor/kl_coef
actor/kl_loss
actor/lr
actor/pg_clipfrac
actor/pg_loss
actor/ppo_kl
critic/advantages/max
critic/advantages/mean
critic/advantages/min
critic/grad_norm
critic/kl
critic/kl_coeff
critic/lr
critic/returns/max
critic/returns/mean
critic/returns/min
critic/rewards/max
critic/rewards/mean
critic/rewards/min
critic/score/max
critic/score/mean
critic/score/min
critic/values/max
critic/values/mean
critic/values/min
critic/vf_clipfrac
critic/vf_explained_var
critic/vf_loss
critic/vpred_mean
global_seqlen/balanced_max
global_seqlen/balanced_min
global_seqlen/max
global_seqlen/mean
global_seqlen/min
global_seqlen/minmax_diff
mfu/actor
mfu/critic
prompt_length/clip_ratio
prompt_length/max
prompt_length/mean
prompt_length/min
response_length/clip_ratio
Finished
-
bowenj4
1s
-
0.24339
127419017.07626
-
-
0.000001
0.13335
82.32302
-0.016619
9.20763
-9.1518e-9
-4.8074
124.2526
-21.68233
0.001
0.00001
51.69175
11.89526
-0.022598
51.63802
23.16273
7.87939
0
0
0
31.75
10.75
-0.73047
0.0034799
0.84324
4.23798
10.58936
77177
77177
80096
77177
74866
5230
0.28907
0.13694
0
245
162.20117
153
0.0019531
Finished
-
bowenj4
1s
-
0.17619
Infinity
-
-
9.0311e-7
0.016358
0.29254
0.0055434
4.11113
-6.0243e-8
-8.21813
46.84198
-1.46356
0.001
0.00001
5.88277
1.52836
-2.17652
5.85481
3.54226
-1.55673
1
0.30859
0
3.8125
1.21094
-0.44141
0
0.68133
0.19687
1.13074
153028
153027
155563
153027.5
151256
4307
0.28354
0.20964
0
265
151.8418
143
0.0019531
Finished
-
bowenj4
0s
-
0.12584
1.34344
0.001
1.72362
0.000001
0.0027758
-0.25604
0.0026935
1
0.26831
0
-
-
-
-
1
0.26831
0
1
0.27773
0
1
0.27773
0
-
-
-
-
-
-
-
61671
61309
62192
61354.75
60410
1782
0.094273
-
0
247
165.06641
157
0.00039063
Finished
-
bowenj4
1s
-
0.41034
0.92237
0.001
0.23147
0.000001
0.00065903
-0.35805
0.002572
1
0.41961
0
-
-
-
-
1
0.41961
0
1
0.4207
0
1
0.4207
0
-
-
-
-
-
-
-
215685
215038
225715
215132.25
206861
18854
0.20313
-
0
180
132.29297
121
0.00039063
Finished
-
bowenj4
1s
-
0.8779
7.97376
-
-
0.000001
0.018909
-0.07308
0.0044434
3.22432
6.1468e-9
-2.68373
2.24227
-0.28778
0.001
0.00001
1.99145
0.45927
-0.39415
1.94885
0.79375
-0.11073
1
0.25781
0
1.26563
0.41602
-0.075684
0
0.27063
0.070959
0.43086
135077
135076
138197
135076.125
130156
8041
0.26428
0.14871
0
267
165.75
153
0.0019531
Finished
-
bowenj4
1s
-
0.063191
7.11102
-
-
0.000001
0.0096658
-0.13069
0.019172
2.60405
-4.2080e-8
-2.4687
15.4416
-1.6288
0.001
0.00001
2.22509
0.7637
-0.18198
2.20796
1.23812
0.51288
1
0.43359
0
1.67969
0.51953
-0.096191
0
0.31357
0.13771
0.55531
40555
40288
40903
40322.375
40082
821
0.20695
0.046776
0
203
132.50195
122
0.0019531
Finished
-
bowenj4
1s
-
0.47905
0.56615
0.001
0.33677
0.000001
0.0012038
-0.40363
0.00075365
1
0.41784
0
-
-
-
-
1
0.41784
0
1
0.42266
0
1
0.42266
0
-
-
-
-
-
-
-
383097
383096
393908
383096.25
362560
31348
0.22359
-
0
253
162.57813
151
0.00039063
Finished
-
bowenj4
1s
-
0.46321
0.55716
0.001
0.24212
0.000001
0.001358
-0.36004
0.00074003
1
0.37229
0
-
-
-
-
1
0.37229
0
1
0.38047
0
1
0.38047
0
-
-
-
-
-
-
-
288737
288273
303463
288340.875
273713
29750
0.20548
-
0
227
151.81641
143
0.00039063
Finished
-
bowenj4
0s
-
0.22094
14.17648
-
-
0.000001
0.016668
-0.031413
-0.0071178
2.73635
1.1885e-8
-2.18819
6.93474
-0.11638
0.001
0.00001
1.53497
0.40785
-0.15316
1.48489
0.56784
-0.11468
1
0.39063
0
1.03906
0.38281
-0.033203
0
0.21303
0.094003
0.4669
103897
103896
108329
103896.625
96615
11714
0.23522
0.089389
0
237
161.03516
153
0.0019531
Finished
-
bowenj4
1s
-
0.38955
20.2746
-
-
0.000001
0.047404
0.10571
0.023807
4.18596
5.5370e-9
-4.41677
2.3725
-1.9232
0.001
0.00001
3.0342
1.10788
-0.42257
3.01325
1.93873
0.63893
1
0.015625
0
2.03125
1.13281
-0.062988
0
0.82692
0.057357
1.17377
81209
81208
88912
81208.125
77246
11666
0.23009
0.072552
0
253
153.38086
141
0.0019531
1-10
of 10