Hugging Face's logo

hugodk-sch
/
aftonposten-6b-align-scan

PEFT
Safetensors
gptj
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
hugodk-sch commited on
Commit
28afa8e
•
1 Parent(s): 4d1cc05

Model save

Browse files
Files changed (8) hide show
  1. README.md +26 -28
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. all_results.json +15 -15
  5. eval_results.json +13 -13
  6. train_results.json +3 -3
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -1,13 +1,11 @@
1
  ---
2
  library_name: peft
3
  tags:
4
- - alignment-handbook
5
  - trl
6
  - dpo
 
7
  - generated_from_trainer
8
  base_model: NbAiLab/nb-gpt-j-6B-v2
9
- datasets:
10
- - hugodk-sch/aftonposten_title_prefs
11
  model-index:
12
  - name: aftonposten-6b-align-scan
13
  results: []
@@ -18,17 +16,17 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # aftonposten-6b-align-scan
20
 
21
- This model is a fine-tuned version of [data/ap-gpt-j-6b-sft-qlora-04-08](https://huggingface.co/data/ap-gpt-j-6b-sft-qlora-04-08) on the hugodk-sch/aftonposten_title_prefs dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4994
24
- - Rewards/chosen: 0.0025
25
- - Rewards/rejected: -0.0003
26
- - Rewards/accuracies: 0.6038
27
- - Rewards/margins: 0.0028
28
- - Logps/rejected: -37.5434
29
- - Logps/chosen: -33.7834
30
- - Logits/rejected: -2.0909
31
- - Logits/chosen: -2.0955
32
 
33
  ## Model description
34
 
@@ -63,21 +61,21 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
65
  |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
66
- | 0.4997 | 0.26 | 100 | -2.2320 | -2.2272 | -33.8530 | -37.3521 | 0.5000 | 0.5183 | 0.0018 | 0.0002 | 0.0016 |
67
- | 0.4992 | 0.52 | 200 | -2.2288 | -2.2240 | -33.7422 | -37.2812 | 0.4999 | 0.5748 | 0.0029 | 0.0006 | 0.0024 |
68
- | 0.4982 | 0.78 | 300 | -2.2289 | -2.2241 | -33.7545 | -37.2741 | 0.4999 | 0.5042 | 0.0028 | 0.0004 | 0.0024 |
69
- | 0.4967 | 1.04 | 400 | 0.4999 | 0.0036 | 0.0030 | 0.5623 | 0.0006 | -37.2152 | -33.6722 | -2.2047 | -2.2095 |
70
- | 0.4954 | 1.3 | 500 | 0.4998 | 0.0042 | 0.0033 | 0.5772 | 0.0009 | -37.1891 | -33.6191 | -2.1759 | -2.1807 |
71
- | 0.4964 | 1.56 | 600 | 0.4996 | 0.0044 | 0.0026 | 0.5685 | 0.0018 | -37.2574 | -33.5925 | -2.1522 | -2.1569 |
72
- | 0.4942 | 1.82 | 700 | 0.4996 | 0.0034 | 0.0018 | 0.5797 | 0.0016 | -37.3406 | -33.6981 | -2.1370 | -2.1417 |
73
- | 0.4926 | 2.08 | 800 | 0.4995 | 0.0037 | 0.0013 | 0.5947 | 0.0024 | -37.3864 | -33.6678 | -2.1276 | -2.1323 |
74
- | 0.491 | 2.34 | 900 | 0.4995 | 0.0031 | 0.0006 | 0.5739 | 0.0025 | -37.4562 | -33.7214 | -2.1107 | -2.1154 |
75
- | 0.4941 | 2.6 | 1000 | 0.4995 | 0.0028 | 0.0001 | 0.6059 | 0.0027 | -37.5025 | -33.7503 | -2.0960 | -2.1006 |
76
- | 0.4943 | 2.86 | 1100 | 0.4995 | 0.0025 | -0.0002 | 0.5826 | 0.0028 | -37.5382 | -33.7800 | -2.0918 | -2.0965 |
77
- | 0.4911 | 3.12 | 1200 | 0.4995 | 0.0026 | -0.0001 | 0.6009 | 0.0027 | -37.5257 | -33.7754 | -2.0913 | -2.0959 |
78
- | 0.4906 | 3.38 | 1300 | 0.4995 | 0.0025 | -0.0002 | 0.6034 | 0.0027 | -37.5366 | -33.7817 | -2.0909 | -2.0955 |
79
- | 0.4928 | 3.64 | 1400 | 0.4995 | 0.0025 | -0.0003 | 0.5922 | 0.0028 | -37.5423 | -33.7843 | -2.0903 | -2.0950 |
80
- | 0.4912 | 3.9 | 1500 | 0.4995 | 0.0025 | -0.0003 | 0.6034 | 0.0028 | -37.5427 | -33.7835 | -2.0908 | -2.0954 |
81
 
82
 
83
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
  tags:
 
4
  - trl
5
  - dpo
6
+ - alignment-handbook
7
  - generated_from_trainer
8
  base_model: NbAiLab/nb-gpt-j-6B-v2
 
 
9
  model-index:
10
  - name: aftonposten-6b-align-scan
11
  results: []
 
16
 
17
  # aftonposten-6b-align-scan
18
 
19
+ This model is a fine-tuned version of [NbAiLab/nb-gpt-j-6B-v2](https://huggingface.co/NbAiLab/nb-gpt-j-6B-v2) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2463.1057
22
+ - Rewards/chosen: -0.0198
23
+ - Rewards/rejected: -0.0244
24
+ - Rewards/accuracies: 0.5656
25
+ - Rewards/margins: 0.0046
26
+ - Logps/rejected: -39.9582
27
+ - Logps/chosen: -36.0192
28
+ - Logits/rejected: -1.8605
29
+ - Logits/chosen: -1.8648
30
 
31
  ## Model description
32
 
 
61
 
62
  | Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
63
  |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
64
+ | 2484.2775 | 0.26 | 100 | -2.2323 | -2.2275 | -34.0187 | -37.5204 | 2498.1597 | 0.5565 | 0.0002 | 0.0002 | -0.0000 |
65
+ | 2464.7859 | 0.52 | 200 | -2.2291 | -2.2242 | -34.0338 | -37.5574 | 2496.0791 | 0.5544 | 0.0000 | 0.0004 | -0.0004 |
66
+ | 2430.5529 | 0.78 | 300 | -2.2262 | -2.2213 | -34.0629 | -37.5906 | 2495.6680 | 0.5390 | -0.0003 | 0.0005 | -0.0007 |
67
+ | 2370.302 | 1.04 | 400 | 2492.4653 | -0.0006 | -0.0014 | 0.5623 | 0.0008 | -37.6613 | -34.0994 | -2.1946 | -2.1994 |
68
+ | 2298.9412 | 1.3 | 500 | 2488.4062 | -0.0025 | -0.0037 | 0.5772 | 0.0013 | -37.8883 | -34.2804 | -2.1295 | -2.1343 |
69
+ | 2298.7582 | 1.56 | 600 | 2477.6589 | -0.0053 | -0.0077 | 0.6121 | 0.0024 | -38.2854 | -34.5600 | -2.0589 | -2.0636 |
70
+ | 2254.2998 | 1.82 | 700 | 2477.6624 | -0.0096 | -0.0122 | 0.5540 | 0.0026 | -38.7330 | -34.9921 | -2.0040 | -2.0086 |
71
+ | 2173.4393 | 2.08 | 800 | 2470.5903 | -0.0118 | -0.0152 | 0.5569 | 0.0034 | -39.0386 | -35.2171 | -1.9665 | -1.9710 |
72
+ | 2065.36 | 2.34 | 900 | 2467.7329 | -0.0156 | -0.0195 | 0.5598 | 0.0039 | -39.4668 | -35.5978 | -1.9122 | -1.9166 |
73
+ | 2196.3246 | 2.6 | 1000 | 2464.3682 | -0.0186 | -0.0229 | 0.5511 | 0.0044 | -39.8091 | -35.8901 | -1.8782 | -1.8826 |
74
+ | 2237.6512 | 2.86 | 1100 | 2464.2991 | -0.0196 | -0.0241 | 0.5453 | 0.0044 | -39.9232 | -35.9976 | -1.8646 | -1.8690 |
75
+ | 2032.5133 | 3.12 | 1200 | 2464.4653 | -0.0199 | -0.0243 | 0.5598 | 0.0044 | -39.9447 | -36.0201 | -1.8618 | -1.8662 |
76
+ | 1967.852 | 3.38 | 1300 | 2461.2036 | -0.0197 | -0.0245 | 0.5540 | 0.0048 | -39.9632 | -36.0051 | -1.8608 | -1.8652 |
77
+ | 2084.0914 | 3.64 | 1400 | 2462.6121 | -0.0199 | -0.0245 | 0.5598 | 0.0046 | -39.9675 | -36.0243 | -1.8613 | -1.8656 |
78
+ | 2032.7156 | 3.9 | 1500 | 2463.1057 | -0.0198 | -0.0244 | 0.5656 | 0.0046 | -39.9582 | -36.0192 | -1.8605 | -1.8648 |
79
 
80
 
81
  ### Framework versions
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "o_proj",
23
  "v_proj",
24
  "gate_proj",
25
  "up_proj",
26
- "k_proj",
27
  "down_proj",
28
- "q_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "q_proj",
23
  "o_proj",
24
  "v_proj",
25
  "gate_proj",
26
  "up_proj",
 
27
  "down_proj",
28
+ "k_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae05e30e298858cdca7a0c71dc8e5fe02939042f934bc13d1830d5b1bfc60782
3
  size 176183216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5eb4a5adaea6cb5fb54a0d4729a15c3ab2d9782eadbc65d5a950651eb8fdc92
3
  size 176183216
all_results.json CHANGED
@@ -1,21 +1,21 @@
1
  {
2
  "epoch": 4.0,
3
- "eval_logits/chosen": -2.0955071449279785,
4
- "eval_logits/rejected": -2.0908851623535156,
5
- "eval_logps/chosen": -33.783447265625,
6
- "eval_logps/rejected": -37.54340744018555,
7
- "eval_loss": 0.49944302439689636,
8
- "eval_rewards/accuracies": 0.6038206219673157,
9
- "eval_rewards/chosen": 0.0025110626593232155,
10
- "eval_rewards/margins": 0.0027789229061454535,
11
- "eval_rewards/rejected": -0.00026786039234139025,
12
- "eval_runtime": 145.762,
13
  "eval_samples": 343,
14
- "eval_samples_per_second": 2.353,
15
- "eval_steps_per_second": 0.295,
16
- "train_loss": 0.39746343532165923,
17
- "train_runtime": 10799.7737,
18
  "train_samples": 3079,
19
- "train_samples_per_second": 1.14,
20
  "train_steps_per_second": 0.143
21
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "eval_logits/chosen": -2.226093053817749,
4
+ "eval_logits/rejected": -2.221263885498047,
5
+ "eval_logps/chosen": -34.05622100830078,
6
+ "eval_logps/rejected": -37.58139419555664,
7
+ "eval_loss": 2495.922119140625,
8
+ "eval_rewards/accuracies": 0.529900312423706,
9
+ "eval_rewards/chosen": -0.00021668746194336563,
10
+ "eval_rewards/margins": 0.00043102249037474394,
11
+ "eval_rewards/rejected": -0.0006477099377661943,
12
+ "eval_runtime": 145.39,
13
  "eval_samples": 343,
14
+ "eval_samples_per_second": 2.359,
15
+ "eval_steps_per_second": 0.296,
16
+ "train_loss": 1756.4536297686689,
17
+ "train_runtime": 10797.265,
18
  "train_samples": 3079,
19
+ "train_samples_per_second": 1.141,
20
  "train_steps_per_second": 0.143
21
  }
eval_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "epoch": 4.0,
3
- "eval_logits/chosen": -2.0955071449279785,
4
- "eval_logits/rejected": -2.0908851623535156,
5
- "eval_logps/chosen": -33.783447265625,
6
- "eval_logps/rejected": -37.54340744018555,
7
- "eval_loss": 0.49944302439689636,
8
- "eval_rewards/accuracies": 0.6038206219673157,
9
- "eval_rewards/chosen": 0.0025110626593232155,
10
- "eval_rewards/margins": 0.0027789229061454535,
11
- "eval_rewards/rejected": -0.00026786039234139025,
12
- "eval_runtime": 145.762,
13
  "eval_samples": 343,
14
- "eval_samples_per_second": 2.353,
15
- "eval_steps_per_second": 0.295
16
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -2.226093053817749,
4
+ "eval_logits/rejected": -2.221263885498047,
5
+ "eval_logps/chosen": -34.05622100830078,
6
+ "eval_logps/rejected": -37.58139419555664,
7
+ "eval_loss": 2495.922119140625,
8
+ "eval_rewards/accuracies": 0.529900312423706,
9
+ "eval_rewards/chosen": -0.00021668746194336563,
10
+ "eval_rewards/margins": 0.00043102249037474394,
11
+ "eval_rewards/rejected": -0.0006477099377661943,
12
+ "eval_runtime": 145.39,
13
  "eval_samples": 343,
14
+ "eval_samples_per_second": 2.359,
15
+ "eval_steps_per_second": 0.296
16
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
- "train_loss": 0.39746343532165923,
4
- "train_runtime": 10799.7737,
5
  "train_samples": 3079,
6
- "train_samples_per_second": 1.14,
7
  "train_steps_per_second": 0.143
8
  }
 
1
  {
2
  "epoch": 4.0,
3
+ "train_loss": 1756.4536297686689,
4
+ "train_runtime": 10797.265,
5
  "train_samples": 3079,
6
+ "train_samples_per_second": 1.141,
7
  "train_steps_per_second": 0.143
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5787441541dcfce7292e7a26e4973994d4bc0ee529aed272d19db5c5530e8654
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b8abfa58261899a25124dd1b0d5038d5a5ec747d30923843a4c529696b76c8d
3
  size 4984