Hugging Face's logo

alphaboi
/
test-mod

PEFT
Safetensors
Model card Files Community
alphaboi commited on
Commit
74f9d8f
·
verified ·
1 Parent(s): b489fe6

Upload folder using huggingface_hub

Browse files
Files changed (42) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. checkpoint-10/adapter_config.json +2 -2
  4. checkpoint-10/adapter_model.safetensors +1 -1
  5. checkpoint-10/optimizer.pt +1 -1
  6. checkpoint-10/trainer_state.json +2 -2
  7. checkpoint-10/training_args.bin +1 -1
  8. checkpoint-20/adapter_config.json +2 -2
  9. checkpoint-20/adapter_model.safetensors +1 -1
  10. checkpoint-20/optimizer.pt +1 -1
  11. checkpoint-20/trainer_state.json +4 -4
  12. checkpoint-20/training_args.bin +1 -1
  13. checkpoint-30/adapter_config.json +2 -2
  14. checkpoint-30/adapter_model.safetensors +1 -1
  15. checkpoint-30/optimizer.pt +1 -1
  16. checkpoint-30/trainer_state.json +6 -6
  17. checkpoint-30/training_args.bin +1 -1
  18. checkpoint-40/adapter_config.json +2 -2
  19. checkpoint-40/adapter_model.safetensors +1 -1
  20. checkpoint-40/optimizer.pt +1 -1
  21. checkpoint-40/trainer_state.json +8 -8
  22. checkpoint-40/training_args.bin +1 -1
  23. checkpoint-50/adapter_config.json +2 -2
  24. checkpoint-50/adapter_model.safetensors +1 -1
  25. checkpoint-50/optimizer.pt +1 -1
  26. checkpoint-50/trainer_state.json +10 -10
  27. checkpoint-50/training_args.bin +1 -1
  28. checkpoint-60/adapter_config.json +2 -2
  29. checkpoint-60/adapter_model.safetensors +1 -1
  30. checkpoint-60/optimizer.pt +1 -1
  31. checkpoint-60/trainer_state.json +12 -12
  32. checkpoint-60/training_args.bin +1 -1
  33. checkpoint-70/adapter_config.json +2 -2
  34. checkpoint-70/adapter_model.safetensors +1 -1
  35. checkpoint-70/optimizer.pt +1 -1
  36. checkpoint-70/trainer_state.json +14 -14
  37. checkpoint-70/training_args.bin +1 -1
  38. checkpoint-72/adapter_config.json +2 -2
  39. checkpoint-72/adapter_model.safetensors +1 -1
  40. checkpoint-72/optimizer.pt +1 -1
  41. checkpoint-72/trainer_state.json +14 -14
  42. checkpoint-72/training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29c71234b7bfc9a2f7092be11046b78d052c3d0622c35b299772cc4d2ad38aa8
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089e9b02962974c75c6049905f2ab2ce48248b37664b9f385cca31095074a258
3
  size 6832600
checkpoint-10/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-10/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ca828839c64970467cf55b58ffbd1f53b73e3ad1a2e5933cdc27e123c90255b
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6239c4d573eb2621ff10ad222da14f996c8d2f3390a0d3f7cf6fc3cc303933
3
  size 6832600
checkpoint-10/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cffbc214a20d64a1b532325b180c30108db78f41aaa1670881f5333cb01f239c
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d973c62bd97ddb6cba001ce0ce6e8ab3627ab738820551fed79860e1fbe433
3
  size 27338682
checkpoint-10/trainer_state.json CHANGED
@@ -10,9 +10,9 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  }
18
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  }
18
  ],
checkpoint-10/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304
checkpoint-20/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-20/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68af77a19da9675388e80eb7bdea74e5e7ef351ac92d88994ea37e31fa6c4745
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df8ec53bf646e3db4650fe8d85776edeeaa740c75069ff07c904891c4a1edf60
3
  size 6832600
checkpoint-20/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:097940af545fa57601d7dec8fc7bd519dba08b13a8006fd528f95d548c2cdfde
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0cd3d5e3b70abcc506047a384469b16e5ad770b0aafc11942ce45b90071e873
3
  size 27338682
checkpoint-20/trainer_state.json CHANGED
@@ -10,16 +10,16 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
- "grad_norm": 1.591796875,
21
  "learning_rate": 0.0002,
22
- "loss": 1.1127,
23
  "step": 20
24
  }
25
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
+ "grad_norm": 1.5771484375,
21
  "learning_rate": 0.0002,
22
+ "loss": 1.1222,
23
  "step": 20
24
  }
25
  ],
checkpoint-20/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304
checkpoint-30/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-30/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7a0c7366b1a8cfd391c960c2cabe4ac033ee34c5028ca211733223113a09583
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bbef078d5c140677a5a69f6fa6864a8f631586a67f0f227afc470387f0dc1f5
3
  size 6832600
checkpoint-30/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:736043ffff7be34cddadf6c11278ea7e0f0823ce677614ca36a7d8fd48af0969
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497b526615ff07addd479c1b072efce207d8c3db3ff2d9bf8dc5d62f66fb72b0
3
  size 27338682
checkpoint-30/trainer_state.json CHANGED
@@ -10,23 +10,23 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
- "grad_norm": 1.591796875,
21
  "learning_rate": 0.0002,
22
- "loss": 1.1127,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
- "grad_norm": 0.765625,
28
  "learning_rate": 0.0002,
29
- "loss": 0.554,
30
  "step": 30
31
  }
32
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
+ "grad_norm": 1.5771484375,
21
  "learning_rate": 0.0002,
22
+ "loss": 1.1222,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
+ "grad_norm": 0.66748046875,
28
  "learning_rate": 0.0002,
29
+ "loss": 0.5563,
30
  "step": 30
31
  }
32
  ],
checkpoint-30/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304
checkpoint-40/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-40/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b25c525f303ba7341e580fb16ffbab9841a2f582995bd66dadb80400fec9e779
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee136b35ecab263229c2a5cc09588a2b068195ab08b4f35eb04aee51785dd1d
3
  size 6832600
checkpoint-40/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a553d5ff47f409e140e8d07d471b49a1671f245ce575638b42962605fdee169
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f6ce72b6125275a965c4c78490086feb151bf209fb9bcec0f10991bedb30c1
3
  size 27338682
checkpoint-40/trainer_state.json CHANGED
@@ -10,30 +10,30 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
- "grad_norm": 1.591796875,
21
  "learning_rate": 0.0002,
22
- "loss": 1.1127,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
- "grad_norm": 0.765625,
28
  "learning_rate": 0.0002,
29
- "loss": 0.554,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
- "grad_norm": 0.658203125,
35
  "learning_rate": 0.0002,
36
- "loss": 0.5075,
37
  "step": 40
38
  }
39
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
+ "grad_norm": 1.5771484375,
21
  "learning_rate": 0.0002,
22
+ "loss": 1.1222,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
+ "grad_norm": 0.66748046875,
28
  "learning_rate": 0.0002,
29
+ "loss": 0.5563,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
+ "grad_norm": 0.6455078125,
35
  "learning_rate": 0.0002,
36
+ "loss": 0.5064,
37
  "step": 40
38
  }
39
  ],
checkpoint-40/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304
checkpoint-50/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-50/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53b33ec378161b6ed59eeb4719f16952b93b9eb6d51c1efbcb4db3f476ec4d6d
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb9a4e2b8ffc1bbde07b3cc8314ca0f3451a017154b8438581e6289557d03bc
3
  size 6832600
checkpoint-50/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f151af44081bc4561651ac681a73f9c7a74c6bc440575739a8d33980c179842
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88990edb9dc7bf5ed1ed1ca9f5cfef074535755129f1547e954f359832c42436
3
  size 27338682
checkpoint-50/trainer_state.json CHANGED
@@ -10,37 +10,37 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
- "grad_norm": 1.591796875,
21
  "learning_rate": 0.0002,
22
- "loss": 1.1127,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
- "grad_norm": 0.765625,
28
  "learning_rate": 0.0002,
29
- "loss": 0.554,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
- "grad_norm": 0.658203125,
35
  "learning_rate": 0.0002,
36
- "loss": 0.5075,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
- "grad_norm": 0.60498046875,
42
  "learning_rate": 0.0002,
43
- "loss": 0.4615,
44
  "step": 50
45
  }
46
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
+ "grad_norm": 1.5771484375,
21
  "learning_rate": 0.0002,
22
+ "loss": 1.1222,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
+ "grad_norm": 0.66748046875,
28
  "learning_rate": 0.0002,
29
+ "loss": 0.5563,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
+ "grad_norm": 0.6455078125,
35
  "learning_rate": 0.0002,
36
+ "loss": 0.5064,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
+ "grad_norm": 0.62451171875,
42
  "learning_rate": 0.0002,
43
+ "loss": 0.4592,
44
  "step": 50
45
  }
46
  ],
checkpoint-50/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304
checkpoint-60/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-60/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef09db24eebbe74fe542dc974ad81f995415b8ebd52b551cf1e0105d8e776292
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3da5b893f53b71e42667360590d0303a5cabec2b19c4680677d3ba2fe6fa2b
3
  size 6832600
checkpoint-60/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d40e5222af061c0fdb250ee82ef4f0d04956ff5b78a16cf03f3d855a82c9329d
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9325ece40d56ecf5c322ed8294ea76437847de82c3847b4fdebe3aeb5c401c
3
  size 27338682
checkpoint-60/trainer_state.json CHANGED
@@ -10,44 +10,44 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
- "grad_norm": 1.591796875,
21
  "learning_rate": 0.0002,
22
- "loss": 1.1127,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
- "grad_norm": 0.765625,
28
  "learning_rate": 0.0002,
29
- "loss": 0.554,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
- "grad_norm": 0.658203125,
35
  "learning_rate": 0.0002,
36
- "loss": 0.5075,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
- "grad_norm": 0.60498046875,
42
  "learning_rate": 0.0002,
43
- "loss": 0.4615,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.8247422680412371,
48
- "grad_norm": 0.6318359375,
49
  "learning_rate": 0.0002,
50
- "loss": 0.4202,
51
  "step": 60
52
  }
53
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
+ "grad_norm": 1.5771484375,
21
  "learning_rate": 0.0002,
22
+ "loss": 1.1222,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
+ "grad_norm": 0.66748046875,
28
  "learning_rate": 0.0002,
29
+ "loss": 0.5563,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
+ "grad_norm": 0.6455078125,
35
  "learning_rate": 0.0002,
36
+ "loss": 0.5064,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
+ "grad_norm": 0.62451171875,
42
  "learning_rate": 0.0002,
43
+ "loss": 0.4592,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.8247422680412371,
48
+ "grad_norm": 0.62939453125,
49
  "learning_rate": 0.0002,
50
+ "loss": 0.4184,
51
  "step": 60
52
  }
53
  ],
checkpoint-60/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304
checkpoint-70/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-70/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff83ef2708098b20cabfc0520a52fa80492d082561f56caff28f66ee413f0be8
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04ffcdee92618373bf9bb9a11fcb0cdb11e80c344985c230fd759bc5ed2a2d1
3
  size 6832600
checkpoint-70/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:638a67d484cb8e71046ccfafc14f83e406f4902406202c0149ef28a2c3266516
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6485ad76d93d84ff54754fe6959052cbc580e340870978fff592572009a405b
3
  size 27338682
checkpoint-70/trainer_state.json CHANGED
@@ -10,51 +10,51 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
- "grad_norm": 1.591796875,
21
  "learning_rate": 0.0002,
22
- "loss": 1.1127,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
- "grad_norm": 0.765625,
28
  "learning_rate": 0.0002,
29
- "loss": 0.554,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
- "grad_norm": 0.658203125,
35
  "learning_rate": 0.0002,
36
- "loss": 0.5075,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
- "grad_norm": 0.60498046875,
42
  "learning_rate": 0.0002,
43
- "loss": 0.4615,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.8247422680412371,
48
- "grad_norm": 0.6318359375,
49
  "learning_rate": 0.0002,
50
- "loss": 0.4202,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 0.9621993127147767,
55
- "grad_norm": 0.6279296875,
56
  "learning_rate": 0.0002,
57
- "loss": 0.4026,
58
  "step": 70
59
  }
60
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
+ "grad_norm": 1.5771484375,
21
  "learning_rate": 0.0002,
22
+ "loss": 1.1222,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
+ "grad_norm": 0.66748046875,
28
  "learning_rate": 0.0002,
29
+ "loss": 0.5563,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
+ "grad_norm": 0.6455078125,
35
  "learning_rate": 0.0002,
36
+ "loss": 0.5064,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
+ "grad_norm": 0.62451171875,
42
  "learning_rate": 0.0002,
43
+ "loss": 0.4592,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.8247422680412371,
48
+ "grad_norm": 0.62939453125,
49
  "learning_rate": 0.0002,
50
+ "loss": 0.4184,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 0.9621993127147767,
55
+ "grad_norm": 0.576171875,
56
  "learning_rate": 0.0002,
57
+ "loss": 0.4028,
58
  "step": 70
59
  }
60
  ],
checkpoint-70/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304
checkpoint-72/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "q_proj",
24
+ "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
checkpoint-72/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29c71234b7bfc9a2f7092be11046b78d052c3d0622c35b299772cc4d2ad38aa8
3
  size 6832600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089e9b02962974c75c6049905f2ab2ce48248b37664b9f385cca31095074a258
3
  size 6832600
checkpoint-72/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:017578256a9a34d463965d0aef1bb7b65e69ddd78821b4e51dd3d2eb0373831e
3
  size 27338682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd63f16da461c601f3eb92aca1b749245db35b4cb28b7cdd759e8ca918c0566d
3
  size 27338682
checkpoint-72/trainer_state.json CHANGED
@@ -10,51 +10,51 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
- "grad_norm": 2.767578125,
14
  "learning_rate": 0.0002,
15
- "loss": 2.5394,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
- "grad_norm": 1.591796875,
21
  "learning_rate": 0.0002,
22
- "loss": 1.1127,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
- "grad_norm": 0.765625,
28
  "learning_rate": 0.0002,
29
- "loss": 0.554,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
- "grad_norm": 0.658203125,
35
  "learning_rate": 0.0002,
36
- "loss": 0.5075,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
- "grad_norm": 0.60498046875,
42
  "learning_rate": 0.0002,
43
- "loss": 0.4615,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.8247422680412371,
48
- "grad_norm": 0.6318359375,
49
  "learning_rate": 0.0002,
50
- "loss": 0.4202,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 0.9621993127147767,
55
- "grad_norm": 0.6279296875,
56
  "learning_rate": 0.0002,
57
- "loss": 0.4026,
58
  "step": 70
59
  }
60
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.13745704467353953,
13
+ "grad_norm": 2.5390625,
14
  "learning_rate": 0.0002,
15
+ "loss": 2.5496,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.27491408934707906,
20
+ "grad_norm": 1.5771484375,
21
  "learning_rate": 0.0002,
22
+ "loss": 1.1222,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 0.41237113402061853,
27
+ "grad_norm": 0.66748046875,
28
  "learning_rate": 0.0002,
29
+ "loss": 0.5563,
30
  "step": 30
31
  },
32
  {
33
  "epoch": 0.5498281786941581,
34
+ "grad_norm": 0.6455078125,
35
  "learning_rate": 0.0002,
36
+ "loss": 0.5064,
37
  "step": 40
38
  },
39
  {
40
  "epoch": 0.6872852233676976,
41
+ "grad_norm": 0.62451171875,
42
  "learning_rate": 0.0002,
43
+ "loss": 0.4592,
44
  "step": 50
45
  },
46
  {
47
  "epoch": 0.8247422680412371,
48
+ "grad_norm": 0.62939453125,
49
  "learning_rate": 0.0002,
50
+ "loss": 0.4184,
51
  "step": 60
52
  },
53
  {
54
  "epoch": 0.9621993127147767,
55
+ "grad_norm": 0.576171875,
56
  "learning_rate": 0.0002,
57
+ "loss": 0.4028,
58
  "step": 70
59
  }
60
  ],
checkpoint-72/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef753aecdb587ccfca7a507325a7344ea18c4f6ec237f4590d0c57a55b7911
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540f901f89791921e9b3cf9ab4587377c091add791e4fe4b6656820764ebd035
3
  size 5304