Hugging Face's logo

Batnini
/
knowledge-agent-write-back

Safetensors
Model card Files
xet
 Community
Batnini commited on
Commit
04ed133
·
verified ·
1 Parent(s): 0dbba6b

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. adapter/adapter_config.json +6 -6
  2. adapter/adapter_model.safetensors +2 -2
  3. adapter/checkpoint-1/adapter_config.json +6 -6
  4. adapter/checkpoint-1/adapter_model.safetensors +2 -2
  5. adapter/checkpoint-1/optimizer.pt +2 -2
  6. adapter/checkpoint-1/trainer_state.json +1 -1
  7. adapter/checkpoint-10/adapter_config.json +6 -6
  8. adapter/checkpoint-10/adapter_model.safetensors +2 -2
  9. adapter/checkpoint-10/optimizer.pt +2 -2
  10. adapter/checkpoint-10/trainer_state.json +5 -5
  11. adapter/checkpoint-11/adapter_config.json +6 -6
  12. adapter/checkpoint-11/adapter_model.safetensors +2 -2
  13. adapter/checkpoint-11/optimizer.pt +2 -2
  14. adapter/checkpoint-11/trainer_state.json +5 -5
  15. adapter/checkpoint-12/adapter_config.json +6 -6
  16. adapter/checkpoint-12/adapter_model.safetensors +2 -2
  17. adapter/checkpoint-12/optimizer.pt +2 -2
  18. adapter/checkpoint-12/trainer_state.json +5 -5
  19. adapter/checkpoint-13/adapter_config.json +6 -6
  20. adapter/checkpoint-13/adapter_model.safetensors +2 -2
  21. adapter/checkpoint-13/optimizer.pt +2 -2
  22. adapter/checkpoint-13/trainer_state.json +5 -5
  23. adapter/checkpoint-14/adapter_config.json +6 -6
  24. adapter/checkpoint-14/adapter_model.safetensors +2 -2
  25. adapter/checkpoint-14/optimizer.pt +2 -2
  26. adapter/checkpoint-14/trainer_state.json +5 -5
  27. adapter/checkpoint-15/adapter_config.json +6 -6
  28. adapter/checkpoint-15/adapter_model.safetensors +2 -2
  29. adapter/checkpoint-15/optimizer.pt +2 -2
  30. adapter/checkpoint-15/trainer_state.json +5 -5
  31. adapter/checkpoint-2/adapter_config.json +6 -6
  32. adapter/checkpoint-2/adapter_model.safetensors +2 -2
  33. adapter/checkpoint-2/optimizer.pt +2 -2
  34. adapter/checkpoint-2/trainer_state.json +1 -1
  35. adapter/checkpoint-3/adapter_config.json +6 -6
  36. adapter/checkpoint-3/adapter_model.safetensors +2 -2
  37. adapter/checkpoint-3/optimizer.pt +2 -2
  38. adapter/checkpoint-3/trainer_state.json +1 -1
  39. adapter/checkpoint-4/adapter_config.json +6 -6
  40. adapter/checkpoint-4/adapter_model.safetensors +2 -2
  41. adapter/checkpoint-4/optimizer.pt +2 -2
  42. adapter/checkpoint-4/trainer_state.json +1 -1
  43. adapter/checkpoint-5/adapter_config.json +6 -6
  44. adapter/checkpoint-5/adapter_model.safetensors +2 -2
  45. adapter/checkpoint-5/optimizer.pt +2 -2
  46. adapter/checkpoint-5/trainer_state.json +1 -1
  47. adapter/checkpoint-6/adapter_config.json +6 -6
  48. adapter/checkpoint-6/adapter_model.safetensors +2 -2
  49. adapter/checkpoint-6/optimizer.pt +2 -2
  50. adapter/checkpoint-6/trainer_state.json +1 -1
adapter/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98c1a96e3957d6f2d8ac76a92aaead06fd6271985eba9a3c6751e465f80dd2af
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3be2c8518433696a6aa5b088a43823facc099b20c7beab385e9352ec3023f2e
3
+ size 239536776
adapter/checkpoint-1/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-1/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ce0fa1f789d5239dc91e9e1f9389a8890548841e35e2991a117a4268853a82
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70c3c9e261473ae17f27314b2bba1b03909921856bf5c133d5e2078fe6f26477
3
+ size 239536776
adapter/checkpoint-1/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:176f12959d3e8db149fbdc04eb8859cadc5107cc37a4d7e4268df2bf83774c5c
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e085fd55cad63de4fbae77072082b27df5ccf6b6498e66ab3b053bc24aa5a34
3
+ size 243818437
adapter/checkpoint-1/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 12301446340608.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 12695312228352.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
adapter/checkpoint-10/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-10/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a29e0d2a70dfb944c3f4843d60865ff9804ad190500e952e50f8d17b8b71d14b
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d17ae14cc83cb1bacf66ddbf8a731aa95e7ee88c27331d712b7f05316ab93b
3
+ size 239536776
adapter/checkpoint-10/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b70b2be656da4eaa67e78914f91447b6c2cb786487d5cc3550ca0b4a81830fa1
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f101ceedd36da51a74e912ba21ac9744d4bcf49d3acf3677c9a6a4f2f45e9b5
3
+ size 243818437
adapter/checkpoint-10/trainer_state.json CHANGED
@@ -10,12 +10,12 @@
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "entropy": 1.4535226494073867,
14
  "epoch": 10.0,
15
- "grad_norm": 3.046875,
16
  "learning_rate": 8e-05,
17
- "loss": 2.295806121826172,
18
- "mean_token_accuracy": 0.6982592329382896,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
@@ -37,7 +37,7 @@
37
  "attributes": {}
38
  }
39
  },
40
- "total_flos": 124394379411456.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
 
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "entropy": 0.8513693287968636,
14
  "epoch": 10.0,
15
+ "grad_norm": 1.34375,
16
  "learning_rate": 8e-05,
17
+ "loss": 1.310697078704834,
18
+ "mean_token_accuracy": 0.8319162212312221,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
 
37
  "attributes": {}
38
  }
39
  },
40
+ "total_flos": 128377220235264.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
adapter/checkpoint-11/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-11/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aee871bd99a9f7b687207d436cb48bb2e99ce3fe4a49d0aa9f2b5adf321bdc72
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9681efd88617c5414ad8a2f16a9fe33ff44ea2cff0324cee219e52ebabff7c
3
+ size 239536776
adapter/checkpoint-11/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68845f446c5dde79cd8ec515256965cae52629ec6ae88c266df936570d3a26fd
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa7a3a67810ffd51f4413bb310c5e0b07749a8aef580fb8d5694adec4318e1a
3
+ size 243818437
adapter/checkpoint-11/trainer_state.json CHANGED
@@ -10,12 +10,12 @@
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "entropy": 1.4535226494073867,
14
  "epoch": 10.0,
15
- "grad_norm": 3.046875,
16
  "learning_rate": 8e-05,
17
- "loss": 2.295806121826172,
18
- "mean_token_accuracy": 0.6982592329382896,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
@@ -37,7 +37,7 @@
37
  "attributes": {}
38
  }
39
  },
40
- "total_flos": 137082875363328.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
 
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "entropy": 0.8513693287968636,
14
  "epoch": 10.0,
15
+ "grad_norm": 1.34375,
16
  "learning_rate": 8e-05,
17
+ "loss": 1.310697078704834,
18
+ "mean_token_accuracy": 0.8319162212312221,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
 
37
  "attributes": {}
38
  }
39
  },
40
+ "total_flos": 141471974572032.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
adapter/checkpoint-12/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-12/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe54aa525c7578a6b9fccf706a68ba1efeb01af91468da9dfc33e63809648845
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2df4368fe55f5a79123103fc8d9321193f5a1c9b4771867f8c8a0e1d214108
3
+ size 239536776
adapter/checkpoint-12/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87cff6786c1a5d91bbc130aef6c8654bed7dfc381eb68d75ea035bccbaf93034
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:effe09760ff16f3e0e212c42ab9a3bf3df4644871b0cd48be8e746b423d3045a
3
+ size 243818437
adapter/checkpoint-12/trainer_state.json CHANGED
@@ -10,12 +10,12 @@
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "entropy": 1.4535226494073867,
14
  "epoch": 10.0,
15
- "grad_norm": 3.046875,
16
  "learning_rate": 8e-05,
17
- "loss": 2.295806121826172,
18
- "mean_token_accuracy": 0.6982592329382896,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
@@ -37,7 +37,7 @@
37
  "attributes": {}
38
  }
39
  },
40
- "total_flos": 149653573607424.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
 
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "entropy": 0.8513693287968636,
14
  "epoch": 10.0,
15
+ "grad_norm": 1.34375,
16
  "learning_rate": 8e-05,
17
+ "loss": 1.310697078704834,
18
+ "mean_token_accuracy": 0.8319162212312221,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
 
37
  "attributes": {}
38
  }
39
  },
40
+ "total_flos": 154445159571456.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
adapter/checkpoint-13/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-13/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45b40737c9ddc72ae19e833e08e169e5f1002bbd9aff96ce344550b4db23d7e5
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c8bf5cc5e3a9080536acd4e22d9b395f3b96ac285a926ec195764e9a3ac920
3
+ size 239536776
adapter/checkpoint-13/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdfa6deb4f989862f3cd407e10f2ac9d06d1137109a053701d5ce06c6a68e617
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de3a29fd07f2ee3595d0ac98721df096041694f03ff5aa11649d155f5ecb5ca
3
+ size 243818437
adapter/checkpoint-13/trainer_state.json CHANGED
@@ -10,12 +10,12 @@
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "entropy": 1.4535226494073867,
14
  "epoch": 10.0,
15
- "grad_norm": 3.046875,
16
  "learning_rate": 8e-05,
17
- "loss": 2.295806121826172,
18
- "mean_token_accuracy": 0.6982592329382896,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
@@ -37,7 +37,7 @@
37
  "attributes": {}
38
  }
39
  },
40
- "total_flos": 162072817655808.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
 
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "entropy": 0.8513693287968636,
14
  "epoch": 10.0,
15
+ "grad_norm": 1.34375,
16
  "learning_rate": 8e-05,
17
+ "loss": 1.310697078704834,
18
+ "mean_token_accuracy": 0.8319162212312221,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
 
37
  "attributes": {}
38
  }
39
  },
40
+ "total_flos": 167262041137152.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
adapter/checkpoint-14/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-14/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a476e70c9e67048c4892fd9f5e9f70ded338d85ef5c44a86141c2ce49763a1ee
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50aa8b388ec8733ac44bd472b9465ce8dd25750a07b47bb921b8abe78e93449
3
+ size 239536776
adapter/checkpoint-14/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b11d2a906c1b8dda251b88971127a4508d57b0e527c64be76bc3ce5c13b72406
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b435012f854d460c7c66d1e22a7d951f7b7fc22aa9f957bc2f757111325d4c16
3
+ size 243818437
adapter/checkpoint-14/trainer_state.json CHANGED
@@ -10,12 +10,12 @@
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "entropy": 1.4535226494073867,
14
  "epoch": 10.0,
15
- "grad_norm": 3.046875,
16
  "learning_rate": 8e-05,
17
- "loss": 2.295806121826172,
18
- "mean_token_accuracy": 0.6982592329382896,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
@@ -37,7 +37,7 @@
37
  "attributes": {}
38
  }
39
  },
40
- "total_flos": 174643515899904.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
 
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "entropy": 0.8513693287968636,
14
  "epoch": 10.0,
15
+ "grad_norm": 1.34375,
16
  "learning_rate": 8e-05,
17
+ "loss": 1.310697078704834,
18
+ "mean_token_accuracy": 0.8319162212312221,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
 
37
  "attributes": {}
38
  }
39
  },
40
+ "total_flos": 180235226136576.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
adapter/checkpoint-15/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-15/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98c1a96e3957d6f2d8ac76a92aaead06fd6271985eba9a3c6751e465f80dd2af
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3be2c8518433696a6aa5b088a43823facc099b20c7beab385e9352ec3023f2e
3
+ size 239536776
adapter/checkpoint-15/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c7b95523d0eb0840773e7a8a89b454480020e49a49280c0ee0d138341c3598f
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4935ec169e25391ef800c9705cd37a3a5b35a3c6cde2dd9395cae3ff03c3ee2
3
+ size 243818437
adapter/checkpoint-15/trainer_state.json CHANGED
@@ -10,12 +10,12 @@
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "entropy": 1.4535226494073867,
14
  "epoch": 10.0,
15
- "grad_norm": 3.046875,
16
  "learning_rate": 8e-05,
17
- "loss": 2.295806121826172,
18
- "mean_token_accuracy": 0.6982592329382896,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
@@ -37,7 +37,7 @@
37
  "attributes": {}
38
  }
39
  },
40
- "total_flos": 187332011851776.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
 
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "entropy": 0.8513693287968636,
14
  "epoch": 10.0,
15
+ "grad_norm": 1.34375,
16
  "learning_rate": 8e-05,
17
+ "loss": 1.310697078704834,
18
+ "mean_token_accuracy": 0.8319162212312221,
19
  "num_tokens": 6910.0,
20
  "step": 10
21
  }
 
37
  "attributes": {}
38
  }
39
  },
40
+ "total_flos": 193329980473344.0,
41
  "train_batch_size": 4,
42
  "trial_name": null,
43
  "trial_params": null
adapter/checkpoint-2/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-2/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e59d9845c2883cb094ca32fd920c1c51e66ddd69e86c6b02fd46e3f3051cddc
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e7a048bea5c9b88eae829f5a6ea192d63a9a9ee3be127d8931054344774a0b
3
+ size 239536776
adapter/checkpoint-2/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d0bc9dc9587e31a2378b3bc737cb6de7d1e512c821ec342a7b5c4d24db76862
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b530d3378e9cbb1e3f4ffbcd10e7d058234260cffaeab63775acb44a4da560
3
+ size 243818437
adapter/checkpoint-2/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 24922629316608.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 25720598372352.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
adapter/checkpoint-3/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-3/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1271a02ac30b811df23bf6d4ded5597b51c806f27458fc63f2790f6be6ef98f0
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a2df1a70456844c689f40525f9c3ac54f76c0275316566a7b60d88668ba86d
3
+ size 239536776
adapter/checkpoint-3/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8909fc0348e069e67578ae1ecd1dfc2ce7ab9dc95ae0178d58c4a4aa7c853417
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea813c605e804352ba8ff66dd96e9f8683da294ca935813cb507520dff866fd7
3
+ size 243818437
adapter/checkpoint-3/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 37106277949440.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 38294341263360.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
adapter/checkpoint-4/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-4/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495fd96b71521f51b0859ca6c66f732ce4795d2860d8ecb74eb7d91cbfe53675
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b759651321e274d2fac4ede5eae09ec051c644ddc3da7cd711b4fee072ff7ab
3
+ size 239536776
adapter/checkpoint-4/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd5f2611f0f07200fcffd7e94468ef7c059fcbac076a3b4d287c130d8fb82f7a
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d70fbb46583d0982619b54aa0647e44b07513ed9d5bbe96c792d690c4cd82385
3
+ size 243818437
adapter/checkpoint-4/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 49542350241792.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 51128589877248.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
adapter/checkpoint-5/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-5/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a33586140579f464c809086aced36403d8849cd2c524bed00d56a3271d3c3dab
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e56d014bad376378d3b34998bcb3b3b9fb51b51b3f5db99fc3198c9852018d
3
+ size 239536776
adapter/checkpoint-5/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:684e94bfb97cd50c3d8cbe491de291ceafd499b7fa01a3f05faaa92a625b13ea
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01e814587fc44eb23dc47e7d9794565fa2c4a0982fc0e8ba8e92e6933f5bf3e
3
+ size 243818437
adapter/checkpoint-5/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 61978422534144.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 63962838491136.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
adapter/checkpoint-6/adapter_config.json CHANGED
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -27,16 +27,16 @@
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
- "r": 16,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
34
- "gate_proj",
35
- "up_proj",
36
  "o_proj",
37
- "v_proj",
38
- "down_proj",
39
  "k_proj",
 
 
 
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 256,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
27
  "peft_type": "LORA",
28
  "peft_version": "0.20.0",
29
  "qalora_group_size": 16,
30
+ "r": 64,
31
  "rank_pattern": {},
32
  "revision": null,
33
  "target_modules": [
 
 
34
  "o_proj",
35
+ "up_proj",
 
36
  "k_proj",
37
+ "gate_proj",
38
+ "down_proj",
39
+ "v_proj",
40
  "q_proj"
41
  ],
42
  "target_parameters": null,
adapter/checkpoint-6/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f392c3367758e68ae2a6335f7273eebcc85a9a468fab484f4c404fa526a62f1b
3
- size 59934640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d520e27667af63bf65784a8245076234ec27b98f7e084552481b2c0ac118a13
3
+ size 239536776
adapter/checkpoint-6/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e5f490cfc86381235bdeb3c91a427d42571452be978214b1f1ec171bd223ff8
3
- size 61403589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa67e6c425f93c8b24ac0d40e17dd9d2e7902edc418a3ff7636da87ffc1da8f
3
+ size 243818437
adapter/checkpoint-6/trainer_state.json CHANGED
@@ -26,7 +26,7 @@
26
  "attributes": {}
27
  }
28
  },
29
- "total_flos": 74532292534272.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null
 
26
  "attributes": {}
27
  }
28
  },
29
+ "total_flos": 76918656442368.0,
30
  "train_batch_size": 4,
31
  "trial_name": null,
32
  "trial_params": null