interpolation_logs / qqp_interpol@25000steps /19569012_interpolate_models.out
connectivity's picture
Upload qqp_interpol@25000steps/19569012_interpolate_models.out
af2aa14
Sun May 15 21:17:52 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.57.02 Driver Version: 470.57.02 CUDA Version: 11.4 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 Quadro RTX 8000 On | 00000000:2F:00.0 Off | 0 |
| N/A 62C P8 34W / 250W | 0MiB / 45556MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| No running processes found |
+-----------------------------------------------------------------------------+
Obtaining file:///scratch/rb5139/constellations/src
Preparing metadata (setup.py): started
Preparing metadata (setup.py): finished with status 'done'
Installing collected packages: constellations
Attempting uninstall: constellations
Found existing installation: constellations 0.0.0
Uninstalling constellations-0.0.0:
Successfully uninstalled constellations-0.0.0
Running setup.py develop for constellations
Successfully installed constellations-0.0.0
Creating .Z35PBWYN8YV4ZNWGS8XE, for loading in git data
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Creating .UQ71PN5U0WNBQW9AHN1G, for loading in git data
Encountered Error: connectivity/bert_ft_qqp-96 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-96.pt
Euclidean distance between 95 and 96: 20.95233726501465.
Interpolating between 95 and 96 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2803 0.9004 0.8555
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2667 0.9043 0.8635
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2634 0.9121 0.8760
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2669 0.9141 0.8804
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2694 0.9121 0.8780
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2670 0.9102 0.8750
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2609 0.9082 0.8712
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2574 0.9062 0.8681
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2586 0.9082 0.8712
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2649 0.9043 0.8643
Completed interpolation from 95 to 96
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Creating .JUJF1O54BBHC7LJWKC2M, for loading in git data
Encountered Error: connectivity/bert_ft_qqp-97 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-97.pt
Euclidean distance between 95 and 97: 21.752470016479492.
Interpolating between 95 and 97 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2618 0.8984 0.8531
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2457 0.8965 0.8524
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2402 0.9043 0.8665
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2421 0.9023 0.8649
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2464 0.9043 0.8679
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2462 0.9023 0.8649
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2456 0.9082 0.8719
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2479 0.9062 0.8689
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2538 0.9082 0.8712
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2649 0.9043 0.8643
Completed interpolation from 95 to 97
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Creating .J9RPBAZGWXAFZIHLO1U7, for loading in git data
Encountered Error: connectivity/bert_ft_qqp-98 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-98.pt
Euclidean distance between 95 and 98: 21.27008056640625.
Interpolating between 95 and 98 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2600 0.9023 0.8588
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2449 0.9004 0.8571
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2380 0.8945 0.8500
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2378 0.8965 0.8540
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2408 0.9023 0.8634
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2402 0.9043 0.8658
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2403 0.9023 0.8634
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2439 0.9043 0.8658
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2520 0.9023 0.8619
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2649 0.9043 0.8643
Completed interpolation from 95 to 98
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Encountered Error: connectivity/bert_ft_qqp-95 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-95.pt
Creating .2YZYKSW84NQHCSJCADKA, for loading in git data
Encountered Error: connectivity/bert_ft_qqp-99 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-99.pt
Euclidean distance between 95 and 99: 23.2761287689209.
Interpolating between 95 and 99 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2396 0.9062 0.8659
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2157 0.9082 0.8691
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2132 0.9043 0.8658
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2281 0.9082 0.8733
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2384 0.9160 0.8859
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2336 0.9141 0.8824
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2258 0.9102 0.8763
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2301 0.9062 0.8696
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2441 0.9062 0.8696
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2649 0.9043 0.8643
Completed interpolation from 95 to 99
Encountered Error: connectivity/bert_ft_qqp-96 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-96.pt
Encountered Error: connectivity/bert_ft_qqp-96 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-96.pt
Encountered Error: connectivity/bert_ft_qqp-97 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-97.pt
Euclidean distance between 96 and 97: 21.468490600585938.
Interpolating between 96 and 97 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2618 0.8984 0.8531
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2455 0.8945 0.8500
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2392 0.9023 0.8626
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2412 0.9043 0.8672
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2454 0.9023 0.8649
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2480 0.9023 0.8641
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2503 0.9043 0.8650
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2537 0.9082 0.8698
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2632 0.9082 0.8683
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2803 0.9004 0.8555
Completed interpolation from 96 to 97
Encountered Error: connectivity/bert_ft_qqp-96 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-96.pt
Encountered Error: connectivity/bert_ft_qqp-96 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-96.pt
Encountered Error: connectivity/bert_ft_qqp-98 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-98.pt
Euclidean distance between 96 and 98: 21.361433029174805.
Interpolating between 96 and 98 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2600 0.9023 0.8588
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2554 0.9004 0.8563
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2576 0.8965 0.8515
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2656 0.8906 0.8444
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2747 0.8848 0.8347
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2755 0.8906 0.8436
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2701 0.8965 0.8524
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2652 0.9023 0.8603
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2679 0.9004 0.8571
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2803 0.9004 0.8555
Completed interpolation from 96 to 98
Encountered Error: connectivity/bert_ft_qqp-96 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-96.pt
Encountered Error: connectivity/bert_ft_qqp-96 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-96.pt
Encountered Error: connectivity/bert_ft_qqp-99 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-99.pt
Euclidean distance between 96 and 99: 23.032705307006836.
Interpolating between 96 and 99 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2396 0.9062 0.8659
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2135 0.9062 0.8667
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2127 0.9004 0.8610
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2344 0.9141 0.8836
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2557 0.9043 0.8734
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2532 0.8965 0.8623
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2400 0.9062 0.8723
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2373 0.9102 0.8750
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2507 0.9062 0.8659
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2803 0.9004 0.8555
Completed interpolation from 96 to 99
Encountered Error: connectivity/bert_ft_qqp-97 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-97.pt
Encountered Error: connectivity/bert_ft_qqp-97 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-97.pt
Encountered Error: connectivity/bert_ft_qqp-98 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-98.pt
Euclidean distance between 97 and 98: 21.71268653869629.
Interpolating between 97 and 98 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2600 0.9023 0.8588
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2486 0.9004 0.8571
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2427 0.8945 0.8500
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2420 0.8945 0.8525
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2441 0.8945 0.8525
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2438 0.8984 0.8579
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2407 0.8965 0.8548
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2399 0.8945 0.8508
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2468 0.8926 0.8468
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2618 0.8984 0.8531
Completed interpolation from 97 to 98
Encountered Error: connectivity/bert_ft_qqp-97 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-97.pt
Encountered Error: connectivity/bert_ft_qqp-97 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-97.pt
Encountered Error: connectivity/bert_ft_qqp-99 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-99.pt
Euclidean distance between 97 and 99: 22.212757110595703.
Interpolating between 97 and 99 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2396 0.9062 0.8659
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2207 0.9023 0.8603
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2150 0.9043 0.8643
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2206 0.8945 0.8516
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2283 0.8965 0.8540
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2290 0.9004 0.8610
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2261 0.9004 0.8603
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2281 0.8945 0.8508
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2396 0.8906 0.8436
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2618 0.8984 0.8531
Completed interpolation from 97 to 99
Encountered Error: connectivity/bert_ft_qqp-98 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-98.pt
Encountered Error: connectivity/bert_ft_qqp-98 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-98.pt
Encountered Error: connectivity/bert_ft_qqp-99 does not appear to have a file named flax_model.msgpack.
Trying to load model from connectivity/bert_ft_qqp-99.pt
Euclidean distance between 98 and 99: 23.194971084594727.
Interpolating between 98 and 99 on qqp
[0.0, 1.0]
point_num loss accuracy f1
----------- -------- ---------- --------
0 0.2396 0.9062 0.8659
[0.1111111111111111, 0.8888888888888888]
point_num loss accuracy f1
----------- -------- ---------- --------
1 0.2183 0.9082 0.8669
[0.2222222222222222, 0.7777777777777778]
point_num loss accuracy f1
----------- -------- ---------- --------
2 0.2240 0.9043 0.8596
[0.3333333333333333, 0.6666666666666667]
point_num loss accuracy f1
----------- -------- ---------- --------
3 0.2558 0.8926 0.8442
[0.4444444444444444, 0.5555555555555556]
point_num loss accuracy f1
----------- -------- ---------- --------
4 0.2873 0.8867 0.8362
[0.5555555555555556, 0.4444444444444444]
point_num loss accuracy f1
----------- -------- ---------- --------
5 0.2772 0.8906 0.8418
[0.6666666666666666, 0.33333333333333337]
point_num loss accuracy f1
----------- -------- ---------- --------
6 0.2475 0.8965 0.8532
[0.7777777777777777, 0.22222222222222232]
point_num loss accuracy f1
----------- -------- ---------- --------
7 0.2351 0.8945 0.8500
[0.8888888888888888, 0.11111111111111116]
point_num loss accuracy f1
----------- -------- ---------- --------
8 0.2416 0.8965 0.8515
[1.0, 0.0]
point_num loss accuracy f1
----------- -------- ---------- --------
9 0.2600 0.9023 0.8588
Completed interpolation from 98 to 99
Wrote the values to ../logs/NLI/qqp_berts/qqp_interpol@25000steps/interpol_qqp_validation19.pkl!