Hugging Face's logo

mkhalifa
/
instrucode

Model card Files Community
Muhammad Khalifa commited on
Commit
70d9848
·
1 Parent(s): eca3a85

update 100-shot models

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. low-shot-task-specific-100-ex/coin_flip/best_model/adapter_model.bin +1 -1
  2. low-shot-task-specific-100-ex/coin_flip/best_model/optimizer.pt +1 -1
  3. low-shot-task-specific-100-ex/coin_flip/best_model/rng_state.pth +1 -1
  4. low-shot-task-specific-100-ex/coin_flip/best_model/scheduler.pt +1 -1
  5. low-shot-task-specific-100-ex/coin_flip/best_model/trainer_state.json +27 -67
  6. low-shot-task-specific-100-ex/coin_flip/best_model/training_args.bin +1 -1
  7. low-shot-task-specific-100-ex/cola/best_model/adapter_model.bin +1 -1
  8. low-shot-task-specific-100-ex/cola/best_model/optimizer.pt +1 -1
  9. low-shot-task-specific-100-ex/cola/best_model/rng_state.pth +1 -1
  10. low-shot-task-specific-100-ex/cola/best_model/scheduler.pt +1 -1
  11. low-shot-task-specific-100-ex/cola/best_model/trainer_state.json +27 -67
  12. low-shot-task-specific-100-ex/cola/best_model/training_args.bin +1 -1
  13. low-shot-task-specific-100-ex/commonsense_qa/best_model/adapter_model.bin +1 -1
  14. low-shot-task-specific-100-ex/commonsense_qa/best_model/optimizer.pt +1 -1
  15. low-shot-task-specific-100-ex/commonsense_qa/best_model/rng_state.pth +1 -1
  16. low-shot-task-specific-100-ex/commonsense_qa/best_model/scheduler.pt +1 -1
  17. low-shot-task-specific-100-ex/commonsense_qa/best_model/trainer_state.json +27 -67
  18. low-shot-task-specific-100-ex/commonsense_qa/best_model/training_args.bin +1 -1
  19. low-shot-task-specific-100-ex/emotion/best_model/adapter_model.bin +1 -1
  20. low-shot-task-specific-100-ex/emotion/best_model/optimizer.pt +1 -1
  21. low-shot-task-specific-100-ex/emotion/best_model/rng_state.pth +1 -1
  22. low-shot-task-specific-100-ex/emotion/best_model/scheduler.pt +1 -1
  23. low-shot-task-specific-100-ex/emotion/best_model/trainer_state.json +27 -67
  24. low-shot-task-specific-100-ex/emotion/best_model/training_args.bin +1 -1
  25. low-shot-task-specific-100-ex/social_i_qa/best_model/adapter_model.bin +1 -1
  26. low-shot-task-specific-100-ex/social_i_qa/best_model/optimizer.pt +1 -1
  27. low-shot-task-specific-100-ex/social_i_qa/best_model/rng_state.pth +1 -1
  28. low-shot-task-specific-100-ex/social_i_qa/best_model/scheduler.pt +1 -1
  29. low-shot-task-specific-100-ex/social_i_qa/best_model/trainer_state.json +27 -67
  30. low-shot-task-specific-100-ex/social_i_qa/best_model/training_args.bin +1 -1
  31. low-shot-task-specific-100-ex/sst/best_model/adapter_model.bin +1 -1
  32. low-shot-task-specific-100-ex/sst/best_model/optimizer.pt +1 -1
  33. low-shot-task-specific-100-ex/sst/best_model/rng_state.pth +1 -1
  34. low-shot-task-specific-100-ex/sst/best_model/scheduler.pt +1 -1
  35. low-shot-task-specific-100-ex/sst/best_model/trainer_state.json +27 -67
  36. low-shot-task-specific-100-ex/sst/best_model/training_args.bin +1 -1
  37. low-shot-task-specific-100-ex/sum/best_model/adapter_model.bin +1 -1
  38. low-shot-task-specific-100-ex/sum/best_model/optimizer.pt +1 -1
  39. low-shot-task-specific-100-ex/sum/best_model/rng_state.pth +1 -1
  40. low-shot-task-specific-100-ex/sum/best_model/scheduler.pt +1 -1
  41. low-shot-task-specific-100-ex/sum/best_model/trainer_state.json +27 -67
  42. low-shot-task-specific-100-ex/sum/best_model/training_args.bin +1 -1
  43. low-shot-task-specific-100-ex/svamp/best_model/adapter_model.bin +1 -1
  44. low-shot-task-specific-100-ex/svamp/best_model/optimizer.pt +1 -1
  45. low-shot-task-specific-100-ex/svamp/best_model/rng_state.pth +1 -1
  46. low-shot-task-specific-100-ex/svamp/best_model/scheduler.pt +1 -1
  47. low-shot-task-specific-100-ex/svamp/best_model/trainer_state.json +27 -67
  48. low-shot-task-specific-100-ex/svamp/best_model/training_args.bin +1 -1
  49. low-shot-task-specific-100-ex/word-sorting/best_model/adapter_model.bin +1 -1
  50. low-shot-task-specific-100-ex/word-sorting/best_model/optimizer.pt +1 -1
low-shot-task-specific-100-ex/coin_flip/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd47cb9e4d59e5592dc86a4825506634b4b81810e2c8cce8d4ee00b654660681
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900b929352d7b9864cf5124eb4c572a8b6dae37682d249b2ab7580664a91b940
3
  size 104973389
low-shot-task-specific-100-ex/coin_flip/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89cb77b938fcbec8ef8fc937366b88a4eb9b3dda7246bcdf5841e8d1ff389eb7
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9906cf6b230090f82e564d944ed89f86f7b93fbea51a96f60d93b92105d169fe
3
  size 209984517
low-shot-task-specific-100-ex/coin_flip/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b683f78ced98226c01d86c04f25e6a3295aa86e50560601c917694a914d68aad
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e482f68aee4b354cad62400db9fdeb5b976710c5407b5ccbc9fb83983e947b7
3
  size 14575
low-shot-task-specific-100-ex/coin_flip/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb69dbf6f829f506b60594816da07bc6940e3d9adce52ab976bf73b294ac5127
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aea4ff6d6c72e86d24e872bf7765995d2e2e0abda70fdf4dff06ed25a492666
3
  size 627
low-shot-task-specific-100-ex/coin_flip/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 0.7364377379417419,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/coin_flip/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 4.770002365112305,
14
- "eval_runtime": 0.7512,
15
- "eval_samples_per_second": 26.626,
16
- "eval_steps_per_second": 3.994,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 4.635828971862793,
22
- "eval_runtime": 0.7546,
23
- "eval_samples_per_second": 26.505,
24
- "eval_steps_per_second": 3.976,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 4.354025363922119,
30
- "eval_runtime": 0.7548,
31
- "eval_samples_per_second": 26.499,
32
- "eval_steps_per_second": 3.975,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 5.9999999999999995e-05,
38
- "loss": 4.5475,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 3.8307082653045654,
44
- "eval_runtime": 0.7548,
45
- "eval_samples_per_second": 26.498,
46
- "eval_steps_per_second": 3.975,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 3.6256070137023926,
52
- "eval_runtime": 0.7542,
53
- "eval_samples_per_second": 26.519,
54
- "eval_steps_per_second": 3.978,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 2.8008601665496826,
60
- "eval_runtime": 0.7532,
61
- "eval_samples_per_second": 26.552,
62
- "eval_steps_per_second": 3.983,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 1.8803138732910156,
68
- "eval_runtime": 0.7625,
69
- "eval_samples_per_second": 26.229,
70
- "eval_steps_per_second": 3.934,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.00011399999999999999,
76
- "loss": 2.7123,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 0.7364377379417419,
82
- "eval_runtime": 0.7535,
83
- "eval_samples_per_second": 26.542,
84
- "eval_steps_per_second": 3.981,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 2393497935544320.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 6.666666666666667e-05,
14
+ "loss": 3.5884,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.333333333333333e-05,
20
+ "loss": 0.8993,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4e-05,
26
+ "loss": 0.2492,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 2.6666666666666667e-05,
32
+ "loss": 0.1766,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 0.1544,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 0.0,
44
+ "loss": 0.1371,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 3582829037813760.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/coin_flip/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd2f888c4bb95dd2b9338dcfeb755b0ed743f36bb3535194839914be97ca407
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dac19ece9926ce0df65478a28bc7c2376d0aab79aeef27eb692db5c74efbeb6
3
  size 4091
low-shot-task-specific-100-ex/cola/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1223c9b19186bca2d1f9a40d1afb7b9d667bb02a7b7fdf5a29875a3ba0ad2c8f
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf6eaeebbd72ab6814da833d9eda14981f05692b2765a3de982dfd71c1fc537
3
  size 104973389
low-shot-task-specific-100-ex/cola/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52d58812c7b440cb5008d9896abfb5be121a3021dd1ec3e407cf5ece524078cb
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d16a56b4d5cf1511d315501d9eaabcd5aa34e6693772060a35cbe3e2cdd9c1
3
  size 209984517
low-shot-task-specific-100-ex/cola/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cfb4b1b5009a9b015311afd9778b0ef0a4a8bc389c04629a1d2e68a84aeea44
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577ca82244635df762528677a0c1f397652f06dfb861feea220b11b2a5c0b33a
3
  size 14575
low-shot-task-specific-100-ex/cola/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b63e6b896793d947452e2a5278b1333dd1dcc71d94b37f92a47c6766156ba1e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495734eb861c1697fb12451c91ebf183750105f664f8401e6e4afa76e8c58d35
3
  size 627
low-shot-task-specific-100-ex/cola/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 3.2643978595733643,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/cola/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 7.496130466461182,
14
- "eval_runtime": 0.651,
15
- "eval_samples_per_second": 30.721,
16
- "eval_steps_per_second": 4.608,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 7.389729976654053,
22
- "eval_runtime": 0.6506,
23
- "eval_samples_per_second": 30.74,
24
- "eval_steps_per_second": 4.611,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 7.235182285308838,
30
- "eval_runtime": 0.6495,
31
- "eval_samples_per_second": 30.792,
32
- "eval_steps_per_second": 4.619,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 5.9999999999999995e-05,
38
- "loss": 7.3487,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 6.905265808105469,
44
- "eval_runtime": 0.6482,
45
- "eval_samples_per_second": 30.855,
46
- "eval_steps_per_second": 4.628,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 6.568731784820557,
52
- "eval_runtime": 0.6499,
53
- "eval_samples_per_second": 30.774,
54
- "eval_steps_per_second": 4.616,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 5.829730987548828,
60
- "eval_runtime": 0.6495,
61
- "eval_samples_per_second": 30.791,
62
- "eval_steps_per_second": 4.619,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 5.088259220123291,
68
- "eval_runtime": 0.6485,
69
- "eval_samples_per_second": 30.84,
70
- "eval_steps_per_second": 4.626,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.00011999999999999999,
76
- "loss": 5.6641,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 3.2643978595733643,
82
- "eval_runtime": 0.6478,
83
- "eval_samples_per_second": 30.872,
84
- "eval_steps_per_second": 4.631,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 862945020149760.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 6.8e-05,
14
+ "loss": 6.9013,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.466666666666667e-05,
20
+ "loss": 4.5097,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4.133333333333334e-05,
26
+ "loss": 1.3419,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 2.8e-05,
32
+ "loss": 0.312,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.4666666666666666e-05,
38
+ "loss": 0.1887,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 1.3333333333333334e-06,
44
+ "loss": 0.1659,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 1397031336345600.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/cola/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7584dccd05bece2a9ec3f622ce5aa37500e33036a484978bd2e232bdb92a42bd
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:030d874224160392a528da785805f84b87012297066180d07cb7f334c83a3b1c
3
  size 4091
low-shot-task-specific-100-ex/commonsense_qa/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f63d75b63e7b225c36c047b776e506742a0eb06a2cb34d6ac32cbc8faea89420
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949e2fce99ab8e025bccb82e82cde96dfefff4db63f88191a2dc513f466f95fe
3
  size 104973389
low-shot-task-specific-100-ex/commonsense_qa/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fdd8a85dbed2d83977bbce5185352392812b7736e12294c276e5e9046d46672
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ae1e782342c243ae71ef5ed3bce12577030d9ac5b0ee3f3216294b93571507
3
  size 209984517
low-shot-task-specific-100-ex/commonsense_qa/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7d44b7a4cdc1eb16e6709c586b407ac6e8b61b77e11a4182c69dce6b3efbf4
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b4046a77d21f3c9945d5e736c8c40a3c0242857a18a73f733de62410972bcf
3
  size 14575
low-shot-task-specific-100-ex/commonsense_qa/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b63e6b896793d947452e2a5278b1333dd1dcc71d94b37f92a47c6766156ba1e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aea4ff6d6c72e86d24e872bf7765995d2e2e0abda70fdf4dff06ed25a492666
3
  size 627
low-shot-task-specific-100-ex/commonsense_qa/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 1.0019607543945312,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/commonsense_qa/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 5.86135196685791,
14
- "eval_runtime": 0.8193,
15
- "eval_samples_per_second": 24.41,
16
- "eval_steps_per_second": 3.662,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 5.789961814880371,
22
- "eval_runtime": 0.8276,
23
- "eval_samples_per_second": 24.167,
24
- "eval_steps_per_second": 3.625,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 5.628936767578125,
30
- "eval_runtime": 0.8224,
31
- "eval_samples_per_second": 24.32,
32
- "eval_steps_per_second": 3.648,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 5.9999999999999995e-05,
38
- "loss": 5.5941,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 4.905825614929199,
44
- "eval_runtime": 0.8285,
45
- "eval_samples_per_second": 24.14,
46
- "eval_steps_per_second": 3.621,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 4.051631927490234,
52
- "eval_runtime": 0.8299,
53
- "eval_samples_per_second": 24.099,
54
- "eval_steps_per_second": 3.615,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 3.0537314414978027,
60
- "eval_runtime": 0.8237,
61
- "eval_samples_per_second": 24.28,
62
- "eval_steps_per_second": 3.642,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 2.2741684913635254,
68
- "eval_runtime": 0.8216,
69
- "eval_samples_per_second": 24.344,
70
- "eval_steps_per_second": 3.652,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.00011999999999999999,
76
- "loss": 3.1561,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 1.0019607543945312,
82
- "eval_runtime": 0.8235,
83
- "eval_samples_per_second": 24.287,
84
- "eval_steps_per_second": 3.643,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 3078414183628800.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 6.666666666666667e-05,
14
+ "loss": 4.5215,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.333333333333333e-05,
20
+ "loss": 1.6265,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4e-05,
26
+ "loss": 0.5894,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 2.6666666666666667e-05,
32
+ "loss": 0.4951,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 0.359,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 0.0,
44
+ "loss": 0.3024,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 4569405149675520.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/commonsense_qa/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcaa3c829539bb3746b5f7e0dafb15dbfccde57e3d5650c68eb42e3fbbacfa3e
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893639fde84c03a31eac95c7cc32efd5ac331dcc6aad3a9d8c1cc4820826b76c
3
  size 4091
low-shot-task-specific-100-ex/emotion/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23178e724f805ef456b15b82726bde7476bb7f85943ce21b94a72364d19f8459
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a36fbadf1693a95d51fb67815f543304b8f28ac83311b4deb4e9e2e6fd4fd2
3
  size 104973389
low-shot-task-specific-100-ex/emotion/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73979bacc3db61859edeb2672ed3234900273717c07987eb84d60c9ebb4e30cc
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8e89ae6be170509d3aede5b9db1253d03aa028322d13df82e8eb65a2fc4e08
3
  size 209984517
low-shot-task-specific-100-ex/emotion/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a608d60cb0a08df4efb2f7fa2cd8590824d7f4a718f101d397116dc4b5272878
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ceb0596676a94d8e2213650ba935fa425b8b167f3a10682ab367ee5d59bf39e
3
  size 14575
low-shot-task-specific-100-ex/emotion/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b63e6b896793d947452e2a5278b1333dd1dcc71d94b37f92a47c6766156ba1e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aea4ff6d6c72e86d24e872bf7765995d2e2e0abda70fdf4dff06ed25a492666
3
  size 627
low-shot-task-specific-100-ex/emotion/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 3.7403335571289062,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/emotion/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 6.759609222412109,
14
- "eval_runtime": 0.7242,
15
- "eval_samples_per_second": 27.617,
16
- "eval_steps_per_second": 4.143,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 6.701653957366943,
22
- "eval_runtime": 0.7245,
23
- "eval_samples_per_second": 27.606,
24
- "eval_steps_per_second": 4.141,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 6.61182165145874,
30
- "eval_runtime": 0.7269,
31
- "eval_samples_per_second": 27.515,
32
- "eval_steps_per_second": 4.127,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 5.9999999999999995e-05,
38
- "loss": 6.5973,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 6.34386682510376,
44
- "eval_runtime": 0.7251,
45
- "eval_samples_per_second": 27.583,
46
- "eval_steps_per_second": 4.137,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 5.928864479064941,
52
- "eval_runtime": 0.7256,
53
- "eval_samples_per_second": 27.565,
54
- "eval_steps_per_second": 4.135,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 5.030377388000488,
60
- "eval_runtime": 0.7248,
61
- "eval_samples_per_second": 27.593,
62
- "eval_steps_per_second": 4.139,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 4.649694442749023,
68
- "eval_runtime": 0.7259,
69
- "eval_samples_per_second": 27.554,
70
- "eval_steps_per_second": 4.133,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.00011999999999999999,
76
- "loss": 5.1116,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 3.7403335571289062,
82
- "eval_runtime": 0.7246,
83
- "eval_samples_per_second": 27.602,
84
- "eval_steps_per_second": 4.14,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 2252558490992640.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 6.666666666666667e-05,
14
+ "loss": 6.0546,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.333333333333333e-05,
20
+ "loss": 4.0909,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4e-05,
26
+ "loss": 2.2994,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 2.6666666666666667e-05,
32
+ "loss": 0.9901,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 0.5193,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 0.0,
44
+ "loss": 0.4048,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 3335566854389760.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/emotion/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cec69ccd4746da9921e4026850479fcbb626150ed87fa80dc42db47d3486b211
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9176c654caac25b5d0276963fccddd09a64e358e438dedb0a65065e09d8fd8c
3
  size 4091
low-shot-task-specific-100-ex/social_i_qa/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef60f33031060f9266bfe61d170eb7c269e012245e37652a45d7c3131c8d3add
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3baf0333809d650d988f3171ce163a104f77f0e24849b73d92595f523c450a1
3
  size 104973389
low-shot-task-specific-100-ex/social_i_qa/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abbeb1912756da0877b31d08f01c2fd522bbb55dc819144a235dd9eae39560ec
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54d9b70c62c40e51621ac1d0f737b9f4fe7817f8322bafec0256d8c4acc22f68
3
  size 209984517
low-shot-task-specific-100-ex/social_i_qa/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ab0262a43d8b8116e7c1b8d394e85687822d3581f13149fbc20dd3f065e85a6
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bcf9f292ce90305d3f64ff1cc106681764cf8693b49bb19dd2577e6cf765e6e
3
  size 14575
low-shot-task-specific-100-ex/social_i_qa/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b63e6b896793d947452e2a5278b1333dd1dcc71d94b37f92a47c6766156ba1e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aea4ff6d6c72e86d24e872bf7765995d2e2e0abda70fdf4dff06ed25a492666
3
  size 627
low-shot-task-specific-100-ex/social_i_qa/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 0.821982741355896,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/social_i_qa/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 6.487459659576416,
14
- "eval_runtime": 0.8925,
15
- "eval_samples_per_second": 22.408,
16
- "eval_steps_per_second": 3.361,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 6.3755621910095215,
22
- "eval_runtime": 0.897,
23
- "eval_samples_per_second": 22.297,
24
- "eval_steps_per_second": 3.345,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 6.16649866104126,
30
- "eval_runtime": 0.8963,
31
- "eval_samples_per_second": 22.314,
32
- "eval_steps_per_second": 3.347,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 5.9999999999999995e-05,
38
- "loss": 6.1511,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 5.644223690032959,
44
- "eval_runtime": 0.8985,
45
- "eval_samples_per_second": 22.259,
46
- "eval_steps_per_second": 3.339,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 4.884535312652588,
52
- "eval_runtime": 0.9023,
53
- "eval_samples_per_second": 22.166,
54
- "eval_steps_per_second": 3.325,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 3.0946044921875,
60
- "eval_runtime": 0.8991,
61
- "eval_samples_per_second": 22.245,
62
- "eval_steps_per_second": 3.337,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 2.1555423736572266,
68
- "eval_runtime": 0.9036,
69
- "eval_samples_per_second": 22.133,
70
- "eval_steps_per_second": 3.32,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.00011999999999999999,
76
- "loss": 3.3011,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 0.821982741355896,
82
- "eval_runtime": 0.8939,
83
- "eval_samples_per_second": 22.373,
84
- "eval_steps_per_second": 3.356,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 3338039476224000.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 6.666666666666667e-05,
14
+ "loss": 4.9972,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.333333333333333e-05,
20
+ "loss": 1.4853,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4e-05,
26
+ "loss": 0.4584,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 2.6666666666666667e-05,
32
+ "loss": 0.3353,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 0.2728,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 0.0,
44
+ "loss": 0.2213,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 4962552021319680.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/social_i_qa/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b54b052f5cac8f07391027a3b0c53c8bffff1028fc30595e86e27a07c6b887e
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af11791e6cdf16263699f5c07021c5d83c28dff3223886bef6b07b99808437e
3
  size 4091
low-shot-task-specific-100-ex/sst/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0ab51ab7c25129d35e69c6a5c9f19421507d7aea82814b2fbf3fbb9e27e0120
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4a8082792fc849393266eaa10c1e85cc9c3ae5e398cfcaec5bc226efa12578
3
  size 104973389
low-shot-task-specific-100-ex/sst/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75b2aab283007757d7da6dabd8a4d1a3e6a88f4f3b3c863b51c6af953abd76f6
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f13f5bf513a01427c8ef493fc671d1afae75974286dc054d4310620eed43190
3
  size 209984517
low-shot-task-specific-100-ex/sst/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd5c668f408d63f497259a79124b33e953210b9fb047bdfd418e598fe5018820
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34aa090882640627386ae3817671b84253ebaab4311765be68e81e144e48ef55
3
  size 14575
low-shot-task-specific-100-ex/sst/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:daa948d8422c0ff5c84b04b3a278a49a8c2106994063cdc84b33b076944943d4
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16485f213295154c0d69518bb66258b478c3854316b9ff741b7b323a6b7d753
3
  size 627
low-shot-task-specific-100-ex/sst/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 4.71249532699585,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/sst/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 7.7774858474731445,
14
- "eval_runtime": 0.6674,
15
- "eval_samples_per_second": 29.965,
16
- "eval_steps_per_second": 4.495,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 7.758080959320068,
22
- "eval_runtime": 0.6648,
23
- "eval_samples_per_second": 30.083,
24
- "eval_steps_per_second": 4.512,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 7.7222137451171875,
30
- "eval_runtime": 0.6677,
31
- "eval_samples_per_second": 29.954,
32
- "eval_steps_per_second": 4.493,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 4.2e-05,
38
- "loss": 7.716,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 7.386101722717285,
44
- "eval_runtime": 0.6691,
45
- "eval_samples_per_second": 29.892,
46
- "eval_steps_per_second": 4.484,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 7.176695346832275,
52
- "eval_runtime": 0.6671,
53
- "eval_samples_per_second": 29.982,
54
- "eval_steps_per_second": 4.497,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 6.573421478271484,
60
- "eval_runtime": 0.6678,
61
- "eval_samples_per_second": 29.951,
62
- "eval_steps_per_second": 4.493,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 6.066993236541748,
68
- "eval_runtime": 0.6693,
69
- "eval_samples_per_second": 29.881,
70
- "eval_steps_per_second": 4.482,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.000102,
76
- "loss": 6.5057,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 4.71249532699585,
82
- "eval_runtime": 0.6679,
83
- "eval_samples_per_second": 29.944,
84
- "eval_steps_per_second": 4.492,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 1760506745978880.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 7.066666666666667e-05,
14
+ "loss": 7.3041,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.7333333333333336e-05,
20
+ "loss": 4.82,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4.4000000000000006e-05,
26
+ "loss": 1.2888,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 3.066666666666667e-05,
32
+ "loss": 0.2708,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.7333333333333336e-05,
38
+ "loss": 0.1504,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 4.000000000000001e-06,
44
+ "loss": 0.1077,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 2554218354769920.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/sst/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82db56540ff893c3d36fa725b2ccaa3a282af73561fa81b1cd27f7673a28d02f
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b68d5494fd59a8931fe75179461097ab12bf65feb3b85581dd03a1bc109cd9
3
  size 4091
low-shot-task-specific-100-ex/sum/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7cc16d00544954ce77b8cae15ccb1f3d592abfd2e8a630f9f4afd1fecf5a7be
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2c2c1869e16917f0713fe4958b0fd90a395bc1551cdd4c805a036b409ee11e
3
  size 104973389
low-shot-task-specific-100-ex/sum/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a11eba00d1ce3e5f0d03227932d4e26433f2f6b6a7c8dc1f7f157da65ae61a16
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1bc3f72790a64267d5724bc6229edf90cbb987e421f8a994a903cd30c1b21f
3
  size 209984517
low-shot-task-specific-100-ex/sum/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cfb4b1b5009a9b015311afd9778b0ef0a4a8bc389c04629a1d2e68a84aeea44
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a52c225a78208eb165a8c30467227762e3ced5a053ad4bfc3a92262e3ccc33c
3
  size 14575
low-shot-task-specific-100-ex/sum/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b63e6b896793d947452e2a5278b1333dd1dcc71d94b37f92a47c6766156ba1e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aea4ff6d6c72e86d24e872bf7765995d2e2e0abda70fdf4dff06ed25a492666
3
  size 627
low-shot-task-specific-100-ex/sum/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 1.7415841817855835,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/sum/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 3.6972098350524902,
14
- "eval_runtime": 0.6541,
15
- "eval_samples_per_second": 30.578,
16
- "eval_steps_per_second": 4.587,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 3.5827407836914062,
22
- "eval_runtime": 0.6516,
23
- "eval_samples_per_second": 30.695,
24
- "eval_steps_per_second": 4.604,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 3.435373306274414,
30
- "eval_runtime": 0.6534,
31
- "eval_samples_per_second": 30.611,
32
- "eval_steps_per_second": 4.592,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 5.9999999999999995e-05,
38
- "loss": 3.5457,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 3.144989013671875,
44
- "eval_runtime": 0.6516,
45
- "eval_samples_per_second": 30.692,
46
- "eval_steps_per_second": 4.604,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 2.9391090869903564,
52
- "eval_runtime": 0.6511,
53
- "eval_samples_per_second": 30.718,
54
- "eval_steps_per_second": 4.608,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 2.312290668487549,
60
- "eval_runtime": 0.6505,
61
- "eval_samples_per_second": 30.745,
62
- "eval_steps_per_second": 4.612,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 1.938306450843811,
68
- "eval_runtime": 0.6508,
69
- "eval_samples_per_second": 30.732,
70
- "eval_steps_per_second": 4.61,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.00011999999999999999,
76
- "loss": 2.4305,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 1.7415841817855835,
82
- "eval_runtime": 0.6535,
83
- "eval_samples_per_second": 30.603,
84
- "eval_steps_per_second": 4.59,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 1186858480435200.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 6.666666666666667e-05,
14
+ "loss": 3.0337,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.333333333333333e-05,
20
+ "loss": 1.7695,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4e-05,
26
+ "loss": 0.506,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 2.6666666666666667e-05,
32
+ "loss": 0.2987,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 0.2552,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 0.0,
44
+ "loss": 0.2156,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 1780287720652800.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/sum/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9b167b4b835edf4fa5e13863bdad1f68e733f002739a766fe1eb9a9eb6f48df
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed2a9d96b9d414d97522c11e4a4005166f181c7e4ce8763f264a4da637a347b
3
  size 4091
low-shot-task-specific-100-ex/svamp/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f29211dc7f547a0a871873375eefed004d258e206cecfee346d1c18ddb963d3
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c988598d575c2d615f27babef066bdb1465845d830f01d1b757b90f57a8f98
3
  size 104973389
low-shot-task-specific-100-ex/svamp/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2b859941698531e737b7ef66017873e12852369c66d25abd3373ec677259117
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2008f46e96a2efc77627c37dc472e78315d8d260cbc110fc22b8b7648959ecc
3
  size 209984517
low-shot-task-specific-100-ex/svamp/best_model/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5077750d4ebc29a06666f871f496d7ff06c1cb14dbd8f8954de69896bf4426ab
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69303b7c1b8eda88caba2f66d02f7e4952ea247079f1347de1a9cdad90a623e
3
  size 14575
low-shot-task-specific-100-ex/svamp/best_model/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b63e6b896793d947452e2a5278b1333dd1dcc71d94b37f92a47c6766156ba1e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aea4ff6d6c72e86d24e872bf7765995d2e2e0abda70fdf4dff06ed25a492666
3
  size 627
low-shot-task-specific-100-ex/svamp/best_model/trainer_state.json CHANGED
@@ -1,95 +1,55 @@
1
  {
2
- "best_metric": 1.6565091609954834,
3
- "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-100-ex/svamp/checkpoint-20",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.8,
13
- "eval_loss": 5.190371036529541,
14
- "eval_runtime": 0.8961,
15
- "eval_samples_per_second": 22.319,
16
- "eval_steps_per_second": 3.348,
17
- "step": 2
18
- },
19
- {
20
- "epoch": 2.0,
21
- "eval_loss": 5.100682735443115,
22
- "eval_runtime": 0.9032,
23
- "eval_samples_per_second": 22.144,
24
- "eval_steps_per_second": 3.322,
25
- "step": 5
26
- },
27
- {
28
- "epoch": 2.8,
29
- "eval_loss": 4.914952278137207,
30
- "eval_runtime": 0.9065,
31
- "eval_samples_per_second": 22.062,
32
- "eval_steps_per_second": 3.309,
33
- "step": 7
34
- },
35
- {
36
- "epoch": 4.0,
37
- "learning_rate": 5.9999999999999995e-05,
38
- "loss": 4.937,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 4.0,
43
- "eval_loss": 4.304265022277832,
44
- "eval_runtime": 0.9048,
45
- "eval_samples_per_second": 22.105,
46
- "eval_steps_per_second": 3.316,
47
- "step": 10
48
  },
49
  {
50
  "epoch": 4.8,
51
- "eval_loss": 3.561671733856201,
52
- "eval_runtime": 0.9075,
53
- "eval_samples_per_second": 22.04,
54
- "eval_steps_per_second": 3.306,
55
- "step": 12
56
- },
57
- {
58
- "epoch": 6.0,
59
- "eval_loss": 2.8418495655059814,
60
- "eval_runtime": 0.9069,
61
- "eval_samples_per_second": 22.052,
62
- "eval_steps_per_second": 3.308,
63
- "step": 15
64
  },
65
  {
66
- "epoch": 6.8,
67
- "eval_loss": 2.3915348052978516,
68
- "eval_runtime": 0.9035,
69
- "eval_samples_per_second": 22.136,
70
- "eval_steps_per_second": 3.32,
71
- "step": 17
72
  },
73
  {
74
  "epoch": 8.0,
75
- "learning_rate": 0.00011999999999999999,
76
- "loss": 3.0207,
77
- "step": 20
78
  },
79
  {
80
- "epoch": 8.0,
81
- "eval_loss": 1.6565091609954834,
82
- "eval_runtime": 0.905,
83
- "eval_samples_per_second": 22.099,
84
- "eval_steps_per_second": 3.315,
85
- "step": 20
86
  }
87
  ],
88
  "logging_steps": 10,
89
- "max_steps": 20,
90
  "num_train_epochs": 10,
91
  "save_steps": 500,
92
- "total_flos": 3347929963560960.0,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.6,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.6,
13
+ "learning_rate": 6.666666666666667e-05,
14
+ "loss": 4.0111,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  "step": 10
16
  },
17
  {
18
+ "epoch": 3.2,
19
+ "learning_rate": 5.333333333333333e-05,
20
+ "loss": 2.0745,
21
+ "step": 20
 
 
22
  },
23
  {
24
  "epoch": 4.8,
25
+ "learning_rate": 4e-05,
26
+ "loss": 1.1402,
27
+ "step": 30
 
 
 
 
 
 
 
 
 
 
28
  },
29
  {
30
+ "epoch": 6.4,
31
+ "learning_rate": 2.6666666666666667e-05,
32
+ "loss": 0.845,
33
+ "step": 40
 
 
34
  },
35
  {
36
  "epoch": 8.0,
37
+ "learning_rate": 1.3333333333333333e-05,
38
+ "loss": 0.6969,
39
+ "step": 50
40
  },
41
  {
42
+ "epoch": 9.6,
43
+ "learning_rate": 0.0,
44
+ "loss": 0.6297,
45
+ "step": 60
 
 
46
  }
47
  ],
48
  "logging_steps": 10,
49
+ "max_steps": 60,
50
  "num_train_epochs": 10,
51
  "save_steps": 500,
52
+ "total_flos": 5063929516523520.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
low-shot-task-specific-100-ex/svamp/best_model/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b132a2d5ba1c5592adec662b49a14662d09b6d2d689b790811b0c67535815c7d
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89187712b0b3f8571d4b05a1d9a0c621cb121c6f3768816a8223cffde0f5134d
3
  size 4091
low-shot-task-specific-100-ex/word-sorting/best_model/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3c5a2be24d9f05a68e2795dcb390c54ada897a16d601b0dd2b44cab21718f0
3
  size 104973389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f174bcbd27519b73a922329f1e5ef20f0a3dbc18de78fb9fbd15133e827c9f40
3
  size 104973389
low-shot-task-specific-100-ex/word-sorting/best_model/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d4146bb863afab1cb22cde74559a41111b3d731420d88faada97d9deff22af9
3
  size 209984517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5e3e7e5726726d88384ef53fe84a880ea76e1d731099ce9851fe02e8f326e2
3
  size 209984517