Hugging Face's logo

jdorairaj
/
Adapters_final

Safetensors
Model card Files
xet
Community
jdorairaj commited on
Commit
e5e4df0
·
1 Parent(s): 4311c72

la runs

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. outputs/args_la.json +3 -0
  2. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/logfile_la_{args.laplace_sub}.log +852 -0
  3. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  4. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  5. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/gpu_stats_la.json +3 -0
  6. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  7. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  8. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/gpu_stats_la.json +3 -0
  9. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  10. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  11. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/gpu_stats_la.json +3 -0
  12. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  13. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  14. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/gpu_stats_la.json +3 -0
  15. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  16. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  17. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/gpu_stats_la.json +3 -0
  18. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  19. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  20. outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/gpu_stats_la.json +3 -0
  21. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_42_8_10000/logfile_la_{args.laplace_sub}.log +7 -0
  22. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/logfile_la_{args.laplace_sub}.log +0 -0
  23. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  24. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  25. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/gpu_stats_la.json +3 -0
  26. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  27. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  28. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/gpu_stats_la.json +3 -0
  29. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  30. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  31. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/gpu_stats_la.json +3 -0
  32. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  33. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  34. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/gpu_stats_la.json +3 -0
  35. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  36. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  37. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/gpu_stats_la.json +3 -0
  38. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  39. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  40. outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/gpu_stats_la.json +3 -0
  41. outputs/mrpc/bert-base-uncased_adapterstrain_val_5e-05_42_8_10000/logfile_la_{args.laplace_sub}.log +10 -0
  42. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/logfile_la_{args.laplace_sub}.log +0 -0
  43. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_0/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  44. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  45. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_0/gpu_stats_la.json +3 -0
  46. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_1999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  47. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_1999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
  48. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_1999/gpu_stats_la.json +3 -0
  49. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_3999/all_results_la_kron_all_homo_mc_corr_1000.json +3 -0
  50. outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_3999/eval_res_la_kron_all_homo_mc_corr_1000.json +3 -0
outputs/args_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec833e18809abcd83d6a58fc8f1515a28191bebcbc44bd7610cc314e5b24a53
3
+ size 1109
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/logfile_la_{args.laplace_sub}.log ADDED
@@ -0,0 +1,852 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 06/01/2024 11:55:49 - INFO - __main__ - Number of labels detected = 2
2
+ 06/01/2024 11:55:49 - INFO - __main__ - ***** Starting script *****
3
+ 06/01/2024 11:55:50 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
4
+ 06/01/2024 11:55:51 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/adapter_config.json
5
+ 06/01/2024 11:55:51 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
6
+ 06/01/2024 11:55:51 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/pytorch_adapter.bin
7
+ 06/01/2024 11:55:51 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/head_config.json
8
+ 06/01/2024 11:55:51 - INFO - adapters.heads.model_mixin - Adding head 'cola' with config {'head_type': 'classification', 'num_labels': 2, 'layers': 2, 'activation_function': 'tanh', 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'use_pooler': False, 'bias': True, 'dropout_prob': None}.
9
+ 06/01/2024 11:55:51 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/pytorch_model_head.bin
10
+ 06/01/2024 11:55:51 - INFO - __main__ - Adapter Name = cola
11
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.weight
12
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.bias
13
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.weight
14
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.bias
15
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.weight
16
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.bias
17
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.weight
18
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.bias
19
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.weight
20
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.bias
21
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.weight
22
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.bias
23
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.weight
24
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.bias
25
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.weight
26
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.bias
27
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.weight
28
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.bias
29
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.weight
30
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.bias
31
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.weight
32
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.bias
33
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.weight
34
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.bias
35
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.weight
36
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.bias
37
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.weight
38
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.bias
39
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.weight
40
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.bias
41
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.weight
42
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.bias
43
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.weight
44
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.bias
45
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.weight
46
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.bias
47
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.weight
48
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.bias
49
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.weight
50
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.bias
51
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.weight
52
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.bias
53
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.weight
54
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.bias
55
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.weight
56
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.bias
57
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.weight
58
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.bias
59
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.weight
60
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.bias
61
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.weight
62
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.bias
63
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.weight
64
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.bias
65
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.weight
66
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.bias
67
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.weight
68
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.bias
69
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.weight
70
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.bias
71
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.weight
72
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.bias
73
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.weight
74
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.bias
75
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.weight
76
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.bias
77
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.weight
78
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.bias
79
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.weight
80
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.bias
81
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.weight
82
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.bias
83
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.weight
84
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.bias
85
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.weight
86
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.bias
87
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.weight
88
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.bias
89
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.weight
90
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.bias
91
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.weight
92
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.bias
93
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.weight
94
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.bias
95
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.weight
96
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.bias
97
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.weight
98
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.bias
99
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.weight
100
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.bias
101
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.weight
102
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.bias
103
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.weight
104
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.bias
105
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.weight
106
+ 06/01/2024 11:55:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.bias
107
+ 06/01/2024 11:55:51 - INFO - __main__ - heads.cola.1.weight
108
+ 06/01/2024 11:55:51 - INFO - __main__ - heads.cola.1.bias
109
+ 06/01/2024 11:55:51 - INFO - __main__ - heads.cola.4.weight
110
+ 06/01/2024 11:55:51 - INFO - __main__ - heads.cola.4.bias
111
+ 06/01/2024 11:55:54 - INFO - __main__ - Sample 3397 of the training set: {'input_ids': [101, 9901, 13303, 2044, 1996, 12383, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
112
+ 06/01/2024 11:55:54 - INFO - __main__ - Sample 2366 of the training set: {'input_ids': [101, 1996, 3586, 3631, 10647, 1005, 1055, 12277, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
113
+ 06/01/2024 11:55:54 - INFO - __main__ - Sample 2356 of the training set: {'input_ids': [101, 2057, 19379, 26860, 2094, 4981, 2083, 1996, 4624, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
114
+ 06/01/2024 12:00:43 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
115
+ 06/01/2024 12:00:43 - INFO - __main__ - f_var shape : torch.Size([1043, 2, 2])
116
+ 06/01/2024 12:00:43 - INFO - __main__ - tensor([[ 0.0578, -0.1273],
117
+ [ 0.0141, -0.0255],
118
+ [ 0.0414, -0.0381],
119
+ ...,
120
+ [-0.0166, -0.0405],
121
+ [ 0.0134, -0.0715],
122
+ [-0.0382, 0.0213]], device='cuda:0')
123
+ 06/01/2024 12:00:43 - INFO - __main__ - tensor([[[12.9645, 12.7884],
124
+ [12.7884, 12.9717]],
125
+
126
+ [[11.9546, 11.6422],
127
+ [11.6422, 12.0088]],
128
+
129
+ [[12.1316, 11.8974],
130
+ [11.8974, 12.1370]],
131
+
132
+ ...,
133
+
134
+ [[13.6458, 13.3185],
135
+ [13.3185, 13.6473]],
136
+
137
+ [[11.7474, 11.5666],
138
+ [11.5666, 11.7562]],
139
+
140
+ [[12.1346, 11.8893],
141
+ [11.8893, 12.1221]]], device='cuda:0')
142
+ 06/01/2024 12:00:43 - INFO - __main__ - ***** Completed training *****
143
+ 06/01/2024 12:00:48 - INFO - __main__ - Number of labels detected = 2
144
+ 06/01/2024 12:00:48 - INFO - __main__ - ***** Starting script *****
145
+ 06/01/2024 12:00:49 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
146
+ 06/01/2024 12:00:50 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/adapter_config.json
147
+ 06/01/2024 12:00:50 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
148
+ 06/01/2024 12:00:50 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/pytorch_adapter.bin
149
+ 06/01/2024 12:00:50 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/head_config.json
150
+ 06/01/2024 12:00:50 - INFO - adapters.heads.model_mixin - Adding head 'cola' with config {'head_type': 'classification', 'num_labels': 2, 'layers': 2, 'activation_function': 'tanh', 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'use_pooler': False, 'bias': True, 'dropout_prob': None}.
151
+ 06/01/2024 12:00:50 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/pytorch_model_head.bin
152
+ 06/01/2024 12:00:50 - INFO - __main__ - Adapter Name = cola
153
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.weight
154
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.bias
155
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.weight
156
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.bias
157
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.weight
158
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.bias
159
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.weight
160
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.bias
161
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.weight
162
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.bias
163
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.weight
164
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.bias
165
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.weight
166
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.bias
167
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.weight
168
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.bias
169
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.weight
170
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.bias
171
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.weight
172
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.bias
173
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.weight
174
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.bias
175
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.weight
176
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.bias
177
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.weight
178
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.bias
179
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.weight
180
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.bias
181
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.weight
182
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.bias
183
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.weight
184
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.bias
185
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.weight
186
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.bias
187
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.weight
188
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.bias
189
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.weight
190
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.bias
191
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.weight
192
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.bias
193
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.weight
194
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.bias
195
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.weight
196
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.bias
197
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.weight
198
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.bias
199
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.weight
200
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.bias
201
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.weight
202
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.bias
203
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.weight
204
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.bias
205
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.weight
206
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.bias
207
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.weight
208
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.bias
209
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.weight
210
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.bias
211
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.weight
212
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.bias
213
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.weight
214
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.bias
215
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.weight
216
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.bias
217
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.weight
218
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.bias
219
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.weight
220
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.bias
221
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.weight
222
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.bias
223
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.weight
224
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.bias
225
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.weight
226
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.bias
227
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.weight
228
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.bias
229
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.weight
230
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.bias
231
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.weight
232
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.bias
233
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.weight
234
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.bias
235
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.weight
236
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.bias
237
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.weight
238
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.bias
239
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.weight
240
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.bias
241
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.weight
242
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.bias
243
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.weight
244
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.bias
245
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.weight
246
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.bias
247
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.weight
248
+ 06/01/2024 12:00:50 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.bias
249
+ 06/01/2024 12:00:50 - INFO - __main__ - heads.cola.1.weight
250
+ 06/01/2024 12:00:50 - INFO - __main__ - heads.cola.1.bias
251
+ 06/01/2024 12:00:50 - INFO - __main__ - heads.cola.4.weight
252
+ 06/01/2024 12:00:50 - INFO - __main__ - heads.cola.4.bias
253
+ 06/01/2024 12:00:54 - INFO - __main__ - Sample 3397 of the training set: {'input_ids': [101, 9901, 13303, 2044, 1996, 12383, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
254
+ 06/01/2024 12:00:54 - INFO - __main__ - Sample 2366 of the training set: {'input_ids': [101, 1996, 3586, 3631, 10647, 1005, 1055, 12277, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
255
+ 06/01/2024 12:00:54 - INFO - __main__ - Sample 2356 of the training set: {'input_ids': [101, 2057, 19379, 26860, 2094, 4981, 2083, 1996, 4624, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
256
+ 06/01/2024 12:05:44 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
257
+ 06/01/2024 12:05:44 - INFO - __main__ - f_var shape : torch.Size([1043, 2, 2])
258
+ 06/01/2024 12:05:44 - INFO - __main__ - tensor([[-1.5606e+00, 1.6427e+00],
259
+ [-1.0038e+00, 1.0276e+00],
260
+ [-1.1142e+00, 1.1758e+00],
261
+ ...,
262
+ [-2.2176e+00, 2.2876e+00],
263
+ [ 1.7365e-03, -1.2060e-01],
264
+ [ 4.5788e-02, -1.5021e-01]], device='cuda:0')
265
+ 06/01/2024 12:05:44 - INFO - __main__ - tensor([[[4.1708, 1.7396],
266
+ [1.7396, 4.4299]],
267
+
268
+ [[2.7875, 1.4555],
269
+ [1.4555, 2.9777]],
270
+
271
+ [[3.2805, 1.2788],
272
+ [1.2788, 3.6008]],
273
+
274
+ ...,
275
+
276
+ [[4.2817, 3.0575],
277
+ [3.0575, 4.4446]],
278
+
279
+ [[2.9753, 0.4526],
280
+ [0.4526, 3.1586]],
281
+
282
+ [[2.8956, 0.2997],
283
+ [0.2997, 3.0948]]], device='cuda:0')
284
+ 06/01/2024 12:05:44 - INFO - __main__ - ***** Completed training *****
285
+ 06/01/2024 12:05:49 - INFO - __main__ - Number of labels detected = 2
286
+ 06/01/2024 12:05:49 - INFO - __main__ - ***** Starting script *****
287
+ 06/01/2024 12:05:50 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
288
+ 06/01/2024 12:05:51 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/adapter_config.json
289
+ 06/01/2024 12:05:51 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
290
+ 06/01/2024 12:05:51 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/pytorch_adapter.bin
291
+ 06/01/2024 12:05:51 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/head_config.json
292
+ 06/01/2024 12:05:51 - INFO - adapters.heads.model_mixin - Adding head 'cola' with config {'head_type': 'classification', 'num_labels': 2, 'layers': 2, 'activation_function': 'tanh', 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'use_pooler': False, 'bias': True, 'dropout_prob': None}.
293
+ 06/01/2024 12:05:51 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/pytorch_model_head.bin
294
+ 06/01/2024 12:05:51 - INFO - __main__ - Adapter Name = cola
295
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.weight
296
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.bias
297
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.weight
298
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.bias
299
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.weight
300
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.bias
301
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.weight
302
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.bias
303
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.weight
304
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.bias
305
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.weight
306
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.bias
307
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.weight
308
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.bias
309
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.weight
310
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.bias
311
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.weight
312
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.bias
313
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.weight
314
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.bias
315
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.weight
316
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.bias
317
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.weight
318
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.bias
319
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.weight
320
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.bias
321
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.weight
322
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.bias
323
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.weight
324
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.bias
325
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.weight
326
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.bias
327
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.weight
328
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.bias
329
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.weight
330
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.bias
331
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.weight
332
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.bias
333
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.weight
334
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.bias
335
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.weight
336
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.bias
337
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.weight
338
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.bias
339
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.weight
340
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.bias
341
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.weight
342
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.bias
343
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.weight
344
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.bias
345
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.weight
346
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.bias
347
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.weight
348
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.bias
349
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.weight
350
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.bias
351
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.weight
352
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.bias
353
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.weight
354
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.bias
355
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.weight
356
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.bias
357
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.weight
358
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.bias
359
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.weight
360
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.bias
361
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.weight
362
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.bias
363
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.weight
364
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.bias
365
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.weight
366
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.bias
367
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.weight
368
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.bias
369
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.weight
370
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.bias
371
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.weight
372
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.bias
373
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.weight
374
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.bias
375
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.weight
376
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.bias
377
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.weight
378
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.bias
379
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.weight
380
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.bias
381
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.weight
382
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.bias
383
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.weight
384
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.bias
385
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.weight
386
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.bias
387
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.weight
388
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.bias
389
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.weight
390
+ 06/01/2024 12:05:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.bias
391
+ 06/01/2024 12:05:51 - INFO - __main__ - heads.cola.1.weight
392
+ 06/01/2024 12:05:51 - INFO - __main__ - heads.cola.1.bias
393
+ 06/01/2024 12:05:51 - INFO - __main__ - heads.cola.4.weight
394
+ 06/01/2024 12:05:51 - INFO - __main__ - heads.cola.4.bias
395
+ 06/01/2024 12:05:54 - INFO - __main__ - Sample 3397 of the training set: {'input_ids': [101, 9901, 13303, 2044, 1996, 12383, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
396
+ 06/01/2024 12:05:54 - INFO - __main__ - Sample 2366 of the training set: {'input_ids': [101, 1996, 3586, 3631, 10647, 1005, 1055, 12277, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
397
+ 06/01/2024 12:05:54 - INFO - __main__ - Sample 2356 of the training set: {'input_ids': [101, 2057, 19379, 26860, 2094, 4981, 2083, 1996, 4624, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
398
+ 06/01/2024 12:10:44 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
399
+ 06/01/2024 12:10:44 - INFO - __main__ - f_var shape : torch.Size([1043, 2, 2])
400
+ 06/01/2024 12:10:44 - INFO - __main__ - tensor([[-2.2763, 2.3324],
401
+ [-1.8188, 1.8609],
402
+ [-1.6634, 1.6638],
403
+ ...,
404
+ [-3.0412, 3.1232],
405
+ [-0.9870, 0.8577],
406
+ [-0.5357, 0.3929]], device='cuda:0')
407
+ 06/01/2024 12:10:44 - INFO - __main__ - tensor([[[ 4.2765, 2.1601],
408
+ [ 2.1601, 4.4863]],
409
+
410
+ [[ 3.1863, 1.3376],
411
+ [ 1.3376, 3.4189]],
412
+
413
+ [[ 3.6683, 0.5845],
414
+ [ 0.5845, 4.1141]],
415
+
416
+ ...,
417
+
418
+ [[ 4.6443, 3.8401],
419
+ [ 3.8401, 4.7094]],
420
+
421
+ [[ 5.9511, -2.9900],
422
+ [-2.9900, 6.5578]],
423
+
424
+ [[ 5.5230, -3.1333],
425
+ [-3.1333, 6.1906]]], device='cuda:0')
426
+ 06/01/2024 12:10:44 - INFO - __main__ - ***** Completed training *****
427
+ 06/01/2024 12:10:49 - INFO - __main__ - Number of labels detected = 2
428
+ 06/01/2024 12:10:49 - INFO - __main__ - ***** Starting script *****
429
+ 06/01/2024 12:10:50 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
430
+ 06/01/2024 12:10:51 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/adapter_config.json
431
+ 06/01/2024 12:10:51 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
432
+ 06/01/2024 12:10:51 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/pytorch_adapter.bin
433
+ 06/01/2024 12:10:51 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/head_config.json
434
+ 06/01/2024 12:10:51 - INFO - adapters.heads.model_mixin - Adding head 'cola' with config {'head_type': 'classification', 'num_labels': 2, 'layers': 2, 'activation_function': 'tanh', 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'use_pooler': False, 'bias': True, 'dropout_prob': None}.
435
+ 06/01/2024 12:10:51 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/pytorch_model_head.bin
436
+ 06/01/2024 12:10:51 - INFO - __main__ - Adapter Name = cola
437
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.weight
438
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.bias
439
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.weight
440
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.bias
441
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.weight
442
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.bias
443
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.weight
444
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.bias
445
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.weight
446
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.bias
447
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.weight
448
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.bias
449
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.weight
450
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.bias
451
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.weight
452
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.bias
453
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.weight
454
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.bias
455
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.weight
456
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.bias
457
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.weight
458
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.bias
459
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.weight
460
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.bias
461
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.weight
462
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.bias
463
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.weight
464
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.bias
465
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.weight
466
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.bias
467
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.weight
468
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.bias
469
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.weight
470
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.bias
471
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.weight
472
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.bias
473
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.weight
474
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.bias
475
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.weight
476
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.bias
477
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.weight
478
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.bias
479
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.weight
480
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.bias
481
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.weight
482
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.bias
483
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.weight
484
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.bias
485
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.weight
486
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.bias
487
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.weight
488
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.bias
489
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.weight
490
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.bias
491
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.weight
492
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.bias
493
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.weight
494
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.bias
495
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.weight
496
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.bias
497
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.weight
498
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.bias
499
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.weight
500
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.bias
501
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.weight
502
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.bias
503
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.weight
504
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.bias
505
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.weight
506
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.bias
507
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.weight
508
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.bias
509
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.weight
510
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.bias
511
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.weight
512
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.bias
513
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.weight
514
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.bias
515
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.weight
516
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.bias
517
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.weight
518
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.bias
519
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.weight
520
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.bias
521
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.weight
522
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.bias
523
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.weight
524
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.bias
525
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.weight
526
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.bias
527
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.weight
528
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.bias
529
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.weight
530
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.bias
531
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.weight
532
+ 06/01/2024 12:10:51 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.bias
533
+ 06/01/2024 12:10:51 - INFO - __main__ - heads.cola.1.weight
534
+ 06/01/2024 12:10:51 - INFO - __main__ - heads.cola.1.bias
535
+ 06/01/2024 12:10:51 - INFO - __main__ - heads.cola.4.weight
536
+ 06/01/2024 12:10:51 - INFO - __main__ - heads.cola.4.bias
537
+ 06/01/2024 12:10:54 - INFO - __main__ - Sample 3397 of the training set: {'input_ids': [101, 9901, 13303, 2044, 1996, 12383, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
538
+ 06/01/2024 12:10:54 - INFO - __main__ - Sample 2366 of the training set: {'input_ids': [101, 1996, 3586, 3631, 10647, 1005, 1055, 12277, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
539
+ 06/01/2024 12:10:54 - INFO - __main__ - Sample 2356 of the training set: {'input_ids': [101, 2057, 19379, 26860, 2094, 4981, 2083, 1996, 4624, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
540
+ 06/01/2024 12:15:51 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
541
+ 06/01/2024 12:15:51 - INFO - __main__ - f_var shape : torch.Size([1043, 2, 2])
542
+ 06/01/2024 12:15:51 - INFO - __main__ - tensor([[-2.4427, 2.6179],
543
+ [-1.8617, 1.9990],
544
+ [-1.7362, 1.8366],
545
+ ...,
546
+ [-3.4044, 3.5965],
547
+ [-2.7229, 2.8187],
548
+ [-2.1238, 2.1852]], device='cuda:0')
549
+ 06/01/2024 12:15:51 - INFO - __main__ - tensor([[[ 4.2594, 2.3833],
550
+ [ 2.3833, 4.3946]],
551
+
552
+ [[ 3.1920, 1.2501],
553
+ [ 1.2501, 3.4573]],
554
+
555
+ [[ 3.6047, 0.5266],
556
+ [ 0.5266, 4.1780]],
557
+
558
+ ...,
559
+
560
+ [[ 4.9522, 4.3707],
561
+ [ 4.3707, 4.9895]],
562
+
563
+ [[ 5.7035, 0.4758],
564
+ [ 0.4758, 6.6389]],
565
+
566
+ [[ 7.4642, -3.3615],
567
+ [-3.3615, 8.7533]]], device='cuda:0')
568
+ 06/01/2024 12:15:51 - INFO - __main__ - ***** Completed training *****
569
+ 06/01/2024 12:15:55 - INFO - __main__ - Number of labels detected = 2
570
+ 06/01/2024 12:15:55 - INFO - __main__ - ***** Starting script *****
571
+ 06/01/2024 12:15:56 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
572
+ 06/01/2024 12:15:57 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/adapter_config.json
573
+ 06/01/2024 12:15:57 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
574
+ 06/01/2024 12:15:57 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/pytorch_adapter.bin
575
+ 06/01/2024 12:15:57 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/head_config.json
576
+ 06/01/2024 12:15:57 - INFO - adapters.heads.model_mixin - Adding head 'cola' with config {'head_type': 'classification', 'num_labels': 2, 'layers': 2, 'activation_function': 'tanh', 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'use_pooler': False, 'bias': True, 'dropout_prob': None}.
577
+ 06/01/2024 12:15:57 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/pytorch_model_head.bin
578
+ 06/01/2024 12:15:57 - INFO - __main__ - Adapter Name = cola
579
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.weight
580
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.bias
581
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.weight
582
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.bias
583
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.weight
584
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.bias
585
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.weight
586
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.bias
587
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.weight
588
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.bias
589
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.weight
590
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.bias
591
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.weight
592
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.bias
593
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.weight
594
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.bias
595
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.weight
596
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.bias
597
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.weight
598
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.bias
599
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.weight
600
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.bias
601
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.weight
602
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.bias
603
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.weight
604
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.bias
605
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.weight
606
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.bias
607
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.weight
608
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.bias
609
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.weight
610
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.bias
611
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.weight
612
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.bias
613
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.weight
614
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.bias
615
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.weight
616
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.bias
617
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.weight
618
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.bias
619
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.weight
620
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.bias
621
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.weight
622
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.bias
623
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.weight
624
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.bias
625
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.weight
626
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.bias
627
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.weight
628
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.bias
629
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.weight
630
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.bias
631
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.weight
632
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.bias
633
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.weight
634
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.bias
635
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.weight
636
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.bias
637
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.weight
638
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.bias
639
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.weight
640
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.bias
641
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.weight
642
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.bias
643
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.weight
644
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.bias
645
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.weight
646
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.bias
647
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.weight
648
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.bias
649
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.weight
650
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.bias
651
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.weight
652
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.bias
653
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.weight
654
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.bias
655
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.weight
656
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.bias
657
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.weight
658
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.bias
659
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.weight
660
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.bias
661
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.weight
662
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.bias
663
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.weight
664
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.bias
665
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.weight
666
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.bias
667
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.weight
668
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.bias
669
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.weight
670
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.bias
671
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.weight
672
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.bias
673
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.weight
674
+ 06/01/2024 12:15:57 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.bias
675
+ 06/01/2024 12:15:57 - INFO - __main__ - heads.cola.1.weight
676
+ 06/01/2024 12:15:57 - INFO - __main__ - heads.cola.1.bias
677
+ 06/01/2024 12:15:57 - INFO - __main__ - heads.cola.4.weight
678
+ 06/01/2024 12:15:57 - INFO - __main__ - heads.cola.4.bias
679
+ 06/01/2024 12:16:02 - INFO - __main__ - Sample 3397 of the training set: {'input_ids': [101, 9901, 13303, 2044, 1996, 12383, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
680
+ 06/01/2024 12:16:02 - INFO - __main__ - Sample 2366 of the training set: {'input_ids': [101, 1996, 3586, 3631, 10647, 1005, 1055, 12277, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
681
+ 06/01/2024 12:16:02 - INFO - __main__ - Sample 2356 of the training set: {'input_ids': [101, 2057, 19379, 26860, 2094, 4981, 2083, 1996, 4624, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
682
+ 06/01/2024 12:21:09 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
683
+ 06/01/2024 12:21:09 - INFO - __main__ - f_var shape : torch.Size([1043, 2, 2])
684
+ 06/01/2024 12:21:09 - INFO - __main__ - tensor([[-2.7018, 2.9278],
685
+ [-2.1563, 2.3556],
686
+ [-1.7670, 1.8868],
687
+ ...,
688
+ [-3.7648, 3.9964],
689
+ [-2.8124, 2.9454],
690
+ [-1.9931, 2.0436]], device='cuda:0')
691
+ 06/01/2024 12:21:09 - INFO - __main__ - tensor([[[ 4.7950, 1.9634],
692
+ [ 1.9634, 4.9622]],
693
+
694
+ [[ 3.6191, 1.1228],
695
+ [ 1.1228, 3.9051]],
696
+
697
+ [[ 4.1466, -0.2768],
698
+ [-0.2768, 4.9214]],
699
+
700
+ ...,
701
+
702
+ [[ 5.2033, 4.4562],
703
+ [ 4.4562, 5.2588]],
704
+
705
+ [[ 6.5369, -0.6365],
706
+ [-0.6365, 7.5989]],
707
+
708
+ [[ 9.1744, -5.8993],
709
+ [-5.8993, 10.9482]]], device='cuda:0')
710
+ 06/01/2024 12:21:09 - INFO - __main__ - ***** Completed training *****
711
+ 06/01/2024 12:21:14 - INFO - __main__ - Number of labels detected = 2
712
+ 06/01/2024 12:21:14 - INFO - __main__ - ***** Starting script *****
713
+ 06/01/2024 12:21:16 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
714
+ 06/01/2024 12:21:16 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/adapter_config.json
715
+ 06/01/2024 12:21:16 - INFO - adapters.configuration.model_adapters_config - Adding adapter 'cola'.
716
+ 06/01/2024 12:21:16 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/pytorch_adapter.bin
717
+ 06/01/2024 12:21:16 - INFO - adapters.loading - Loading module configuration from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/head_config.json
718
+ 06/01/2024 12:21:16 - INFO - adapters.heads.model_mixin - Adding head 'cola' with config {'head_type': 'classification', 'num_labels': 2, 'layers': 2, 'activation_function': 'tanh', 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'use_pooler': False, 'bias': True, 'dropout_prob': None}.
719
+ 06/01/2024 12:21:16 - INFO - adapters.loading - Loading module weights from ./outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/pytorch_model_head.bin
720
+ 06/01/2024 12:21:16 - INFO - __main__ - Adapter Name = cola
721
+ 06/01/2024 12:21:16 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.weight
722
+ 06/01/2024 12:21:16 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_down.0.bias
723
+ 06/01/2024 12:21:16 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.weight
724
+ 06/01/2024 12:21:16 - INFO - __main__ - bert.encoder.layer.0.attention.output.adapters.cola.adapter_up.bias
725
+ 06/01/2024 12:21:16 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.weight
726
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_down.0.bias
727
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.weight
728
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.0.output.adapters.cola.adapter_up.bias
729
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.weight
730
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_down.0.bias
731
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.weight
732
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.attention.output.adapters.cola.adapter_up.bias
733
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.weight
734
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_down.0.bias
735
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.weight
736
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.1.output.adapters.cola.adapter_up.bias
737
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.weight
738
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_down.0.bias
739
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.weight
740
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.attention.output.adapters.cola.adapter_up.bias
741
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.weight
742
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_down.0.bias
743
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.weight
744
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.2.output.adapters.cola.adapter_up.bias
745
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.weight
746
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_down.0.bias
747
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.weight
748
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.attention.output.adapters.cola.adapter_up.bias
749
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.weight
750
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_down.0.bias
751
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.weight
752
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.3.output.adapters.cola.adapter_up.bias
753
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.weight
754
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_down.0.bias
755
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.weight
756
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.attention.output.adapters.cola.adapter_up.bias
757
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.weight
758
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_down.0.bias
759
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.weight
760
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.4.output.adapters.cola.adapter_up.bias
761
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.weight
762
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_down.0.bias
763
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.weight
764
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.attention.output.adapters.cola.adapter_up.bias
765
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.weight
766
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_down.0.bias
767
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.weight
768
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.5.output.adapters.cola.adapter_up.bias
769
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.weight
770
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_down.0.bias
771
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.weight
772
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.attention.output.adapters.cola.adapter_up.bias
773
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.weight
774
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_down.0.bias
775
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.weight
776
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.6.output.adapters.cola.adapter_up.bias
777
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.weight
778
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_down.0.bias
779
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.weight
780
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.attention.output.adapters.cola.adapter_up.bias
781
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.weight
782
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_down.0.bias
783
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.weight
784
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.7.output.adapters.cola.adapter_up.bias
785
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.weight
786
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_down.0.bias
787
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.weight
788
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.attention.output.adapters.cola.adapter_up.bias
789
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.weight
790
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_down.0.bias
791
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.weight
792
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.8.output.adapters.cola.adapter_up.bias
793
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.weight
794
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_down.0.bias
795
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.weight
796
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.attention.output.adapters.cola.adapter_up.bias
797
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.weight
798
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_down.0.bias
799
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.weight
800
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.9.output.adapters.cola.adapter_up.bias
801
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.weight
802
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_down.0.bias
803
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.weight
804
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.attention.output.adapters.cola.adapter_up.bias
805
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.weight
806
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_down.0.bias
807
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.weight
808
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.10.output.adapters.cola.adapter_up.bias
809
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.weight
810
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_down.0.bias
811
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.weight
812
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.attention.output.adapters.cola.adapter_up.bias
813
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.weight
814
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_down.0.bias
815
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.weight
816
+ 06/01/2024 12:21:17 - INFO - __main__ - bert.encoder.layer.11.output.adapters.cola.adapter_up.bias
817
+ 06/01/2024 12:21:17 - INFO - __main__ - heads.cola.1.weight
818
+ 06/01/2024 12:21:17 - INFO - __main__ - heads.cola.1.bias
819
+ 06/01/2024 12:21:17 - INFO - __main__ - heads.cola.4.weight
820
+ 06/01/2024 12:21:17 - INFO - __main__ - heads.cola.4.bias
821
+ 06/01/2024 12:21:20 - INFO - __main__ - Sample 3397 of the training set: {'input_ids': [101, 9901, 13303, 2044, 1996, 12383, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
822
+ 06/01/2024 12:21:20 - INFO - __main__ - Sample 2366 of the training set: {'input_ids': [101, 1996, 3586, 3631, 10647, 1005, 1055, 12277, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 1}.
823
+ 06/01/2024 12:21:20 - INFO - __main__ - Sample 2356 of the training set: {'input_ids': [101, 2057, 19379, 26860, 2094, 4981, 2083, 1996, 4624, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': 0}.
824
+ 06/01/2024 12:26:23 - INFO - __main__ - f_mu shape : torch.Size([1043, 2])
825
+ 06/01/2024 12:26:23 - INFO - __main__ - f_var shape : torch.Size([1043, 2, 2])
826
+ 06/01/2024 12:26:23 - INFO - __main__ - tensor([[-2.9716, 3.2141],
827
+ [-2.3593, 2.5730],
828
+ [-1.9422, 2.0817],
829
+ ...,
830
+ [-3.9324, 4.1705],
831
+ [-3.0374, 3.1900],
832
+ [-1.5928, 1.5935]], device='cuda:0')
833
+ 06/01/2024 12:26:23 - INFO - __main__ - tensor([[[ 4.9167, 2.1319],
834
+ [ 2.1319, 5.0604]],
835
+
836
+ [[ 3.8028, 1.1293],
837
+ [ 1.1293, 4.0759]],
838
+
839
+ [[ 4.5062, -0.5867],
840
+ [-0.5867, 5.3611]],
841
+
842
+ ...,
843
+
844
+ [[ 5.2096, 4.3945],
845
+ [ 4.3945, 5.2706]],
846
+
847
+ [[ 6.9878, -0.8966],
848
+ [-0.8966, 8.0646]],
849
+
850
+ [[ 9.9758, -7.6343],
851
+ [-7.6343, 11.9324]]], device='cuda:0')
852
+ 06/01/2024 12:26:23 - INFO - __main__ - ***** Completed training *****
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa753ec8c196b6ba25d397655827b50ba5e4e8ab3a0611696974cb2b176b709
3
+ size 51
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54df68e9df6ab9cdfff8670128c4ae7855dd74634433c34c8bba67be1e7133fe
3
+ size 175602
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e66d4b04c437fd3ccaffc68e04f9fd2e618372223261826928f3b73f44e7c0
3
+ size 6119
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e4aa22e380a680fd4a19f99c0eb816c1aae5d95049578a40b736bc9e748b8a
3
+ size 49
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311348bd7650a8f3a355048163b4f943fb66e1e2f0dd3bb51fdeaf84ef29eef8
3
+ size 176263
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c033519eef70ba83c5d56b44f0bbce32998e594d87922adfc87a047d5afdd226
3
+ size 6136
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12595e64dabbe54a88115349f4e3a6060d2960b905e840e2f4f7adc226c3dacf
3
+ size 49
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c6f66a36c141b6cf55345c06acc811085e79f70323c696b9b4ef8c8a66fc26
3
+ size 176796
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf247548110d6eb743395d6cc995cf4dc124733f6fd2c09e0c22d7d4e360904
3
+ size 6144
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f65b5125b231f4c170f931737ff92430d26d6c425fac07c8e6bd7e8f6b82e45
3
+ size 49
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2207108a665da35372314f7bf8dcb6793f4632cfa96a3ffb5f38571c3194d27
3
+ size 176990
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7a3635831442acc4ebfce084fc82ac522911c3c939c9bcc15e2d2872d3c19d
3
+ size 6155
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f583a0ab2f642aa1ff56b5493e1e6845d5bd4d6440091a8dbd30c69223fcd290
3
+ size 49
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e004f76425a6dcabe795fa4f58e43f8473366b1d64aeba5826173b3c97e16bc8
3
+ size 177233
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949998cdd85f8fe1da2e099e65f3d64761bdf65f9ccb3bac58ebcb7985b18898
3
+ size 6162
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4349923e2abe2a9a9e0aec6228bc19283b7531532d5e3089dfb7d93b460c85dd
3
+ size 49
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e72b1e1981b619c147da31387e7eddaeeceb3eacb4d3e42ecaf3e0c5325352
3
+ size 177446
outputs/cola/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d0360d311ca735a14bfd39cf6b4fdfdfd9198c0da9f6fe6b494b049d612c4bf
3
+ size 6169
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_42_8_10000/logfile_la_{args.laplace_sub}.log ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ 06/01/2024 11:25:34 - INFO - __main__ - Number of labels detected = 2
2
+ 06/01/2024 11:25:34 - INFO - __main__ - ***** Starting script *****
3
+ 06/01/2024 11:25:35 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
4
+ 06/01/2024 11:25:36 - INFO - adapters.utils - Attempting to load adapter from source 'hf'...
5
+ 06/01/2024 11:25:36 - INFO - adapters.utils - Repo id must be in the form 'repo_name' or 'namespace/repo_name': './outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_42_8_10000/step_0'. Use `repo_type` argument if needed.
6
+ 06/01/2024 11:25:36 - INFO - adapters.utils - Attempting to load adapter from source 'ah'...
7
+ 06/01/2024 11:25:36 - INFO - adapters.utils - No adapter with name './outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_42_8_10000/step_0' was found in the adapter index.
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/logfile_la_{args.laplace_sub}.log ADDED
The diff for this file is too large to render. See raw diff
 
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c340ee078dd34e63f2ece7311b2000c2656dcb82475fc69852cb61dd8480c9
3
+ size 69
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238e336de54b22ba2e51b422b5c3e6ffb986047ab9fc3564ae64ba8e22a6fb9b
3
+ size 68667
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_0/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecfe87259e2e429200d03c344842629eafc4a94ca868a77feed719e295991414
3
+ size 6117
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63b62c0874c2f4f8e1b95ad25aaeafd910795ec519b6990474c1a96f9480adc
3
+ size 68
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:680d6a81a26decd83b1066d9d1b8b5660e50edc6e5ef8390177dd1b9cd399005
3
+ size 69192
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_1999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44b1d5774d7a0140f9490f19c6522dc7ae4ae52a4936f17a97e56260564f5b4
3
+ size 6126
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee37011a76c331e5d81afafae436bf65f8ef27864968ebad7db073046f7196f5
3
+ size 68
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65b5d6b860784277d3407fcb662151ef7401237646d22ddd00cde3aa4a5b1e3
3
+ size 69224
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_3999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2900938a34c4900220e231392afad9c2c87ea6a93e129ca8747be441d3e321b
3
+ size 6132
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05642000bfd35d8399125bc08678dfb01c74e8ae4e34be30bb48c7bc86639405
3
+ size 68
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc986dd29f091adee1a46af3ecd42016a0b00e9e202511f3c88fe036ab119fda
3
+ size 69368
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_5999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ee178a4f8ca7625d30afaefe2284db9288722727900095f5bc46aa86e8fe72
3
+ size 6141
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b22be691ad6d600e15acf1701ca9d926b42e740f74dab3bb43f6e070056dabd6
3
+ size 68
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a851b20df67042973f2242e4af2e08ef5154fa8ec35279ec24902468bbb4697f
3
+ size 69456
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_7999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68137da4aa4cba3d12a8a7050809107fc8788963f0121e4bfdecba98f8d9ecd1
3
+ size 6168
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f78f933b7b7c9c44ce7d7a5a3e85a7fff35981f2a0bcd28bdbcca11b64f09a6
3
+ size 68
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb219c2690e703c318aef585ea697a44bc420a0bab5de8820cd841d0afd996e8
3
+ size 69275
outputs/mrpc/bert-base-uncased_adapterstrain_val_0.0001_65_8_10000/step_9999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7767e31bf735f013d27120195c2ab3738c953460ff0f6ebad7f3764abfe0b79b
3
+ size 6162
outputs/mrpc/bert-base-uncased_adapterstrain_val_5e-05_42_8_10000/logfile_la_{args.laplace_sub}.log ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ 06/01/2024 11:24:10 - INFO - __main__ - Number of labels detected = 2
2
+ 06/01/2024 11:24:10 - INFO - __main__ - ***** Starting script *****
3
+ 06/01/2024 11:24:16 - INFO - adapters.heads.model_mixin - Adding head 'default' with config {'head_type': 'masked_lm', 'vocab_size': 30522, 'embedding_size': 768, 'layers': 2, 'activation_function': 'gelu', 'layer_norm': True, 'bias': True, 'shift_labels': False, 'label2id': None}.
4
+ 06/01/2024 11:24:17 - INFO - adapters.utils - Attempting to load adapter from source 'hf'...
5
+ 06/01/2024 11:24:17 - INFO - adapters.utils - Repo id must be in the form 'repo_name' or 'namespace/repo_name': './outputs/mrpc/bert-base-uncased_adapterstrain_val_5e-05_42_8_10000/step_0'. Use `repo_type` argument if needed.
6
+ 06/01/2024 11:24:17 - INFO - adapters.utils - Attempting to load adapter from source 'ah'...
7
+ 06/01/2024 11:24:18 - INFO - adapters.utils - https://raw.githubusercontent.com/Adapter-Hub/Hub/master/dist/v2/index/bert-base-uncased.json not found in cache or force_download set to True, downloading to /root/.cache/torch/adapters/tmp7fkjbr_f
8
+ 06/01/2024 11:24:18 - INFO - adapters.utils - storing https://raw.githubusercontent.com/Adapter-Hub/Hub/master/dist/v2/index/bert-base-uncased.json in cache at /root/.cache/torch/adapters/22e416a3791c0b8e1aafcfac89db490ae05250204ed58e5d81a8645b0726dda0.b141886e1b58ad87e04b024247bf438580086cd7bd78529838848a12d9323e20
9
+ 06/01/2024 11:24:18 - INFO - adapters.utils - creating metadata file for /root/.cache/torch/adapters/22e416a3791c0b8e1aafcfac89db490ae05250204ed58e5d81a8645b0726dda0.b141886e1b58ad87e04b024247bf438580086cd7bd78529838848a12d9323e20
10
+ 06/01/2024 11:24:18 - INFO - adapters.utils - No adapter with name './outputs/mrpc/bert-base-uncased_adapterstrain_val_5e-05_42_8_10000/step_0' was found in the adapter index.
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/logfile_la_{args.laplace_sub}.log ADDED
The diff for this file is too large to render. See raw diff
 
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_0/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85862ef53cde04fd095621971c40cd6d4aa56cadff8274c52cfddf86adefe180
3
+ size 68
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_0/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a9346ab14168a80c973e1a5e3b6b0c6f05eb6b62263987fc724c387cf5061d
3
+ size 68606
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_0/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8875908da7a136b6600fcb2d3ffe61c9a5a8a14a8a36d535486ed9ff8f8c3638
3
+ size 6120
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_1999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe9f2bec627fac5d0b50392516d59184df547f09babf0e417e119c429e05f08
3
+ size 68
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_1999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78135c57fba98a9328bb1737b3062ac46ab32fdffb55fad82ef0fa5b729fa354
3
+ size 69312
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_1999/gpu_stats_la.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15e3619ce929c748a3e942288b03a8049ad12664e6dc2539b41f78c11773fd28
3
+ size 6135
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_3999/all_results_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1683d8b9f46dedb78e1f52b1461afd9ca4fce40efc968789f3349f99200edf7b
3
+ size 68
outputs/mrpc/roberta-base_adapterstrain_val_0.0001_65_8_10000/step_3999/eval_res_la_kron_all_homo_mc_corr_1000.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ab816f2f13ecc0b1092f1bd232250458c175b0b2b1be4d215087dc87484083
3
+ size 69609