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
1996bee
•
1 Parent(s): 2257bb8

Training in progress, step 700

Browse files
Files changed (8) hide show
  1. README.md +15 -27
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. all_results.json +16 -16
  5. eval_results.json +12 -12
  6. train_results.json +5 -5
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -20,15 +20,15 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.9913
24
- - Rewards/chosen: -0.0569
25
- - Rewards/rejected: -0.0657
26
- - Rewards/accuracies: 0.5511
27
- - Rewards/margins: 0.0088
28
- - Logps/rejected: -44.0859
29
- - Logps/chosen: -39.7278
30
- - Logits/rejected: -1.5833
31
- - Logits/chosen: -1.5872
32
 
33
  ## Model description
34
 
@@ -57,27 +57,15 @@ The following hyperparameters were used during training:
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: cosine
59
  - lr_scheduler_warmup_ratio: 0.1
60
- - num_epochs: 4
61
 
62
  ### Training results
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
- | 0.9987 | 0.26 | 100 | -2.2313 | -2.2264 | -34.0499 | -37.5528 | 0.9998 | 0.5336 | -0.0002 | 0.0002 | -0.0004 |
67
- | 0.9965 | 0.52 | 200 | -2.2252 | -2.2204 | -34.0618 | -37.5790 | 0.9996 | 0.5071 | -0.0003 | 0.0004 | -0.0006 |
68
- | 0.9925 | 0.78 | 300 | -2.2214 | -2.2166 | -34.0836 | -37.6063 | 0.9996 | 0.5594 | -0.0005 | 0.0004 | -0.0009 |
69
- | 0.986 | 1.04 | 400 | 0.9994 | -0.0014 | -0.0019 | 0.5212 | 0.0006 | -37.7105 | -34.1717 | -2.1877 | -2.1926 |
70
- | 0.9781 | 1.3 | 500 | 0.9987 | -0.0031 | -0.0044 | 0.5855 | 0.0013 | -37.9551 | -34.3418 | -2.1137 | -2.1185 |
71
- | 0.9774 | 1.56 | 600 | 0.9973 | -0.0073 | -0.0101 | 0.5743 | 0.0027 | -38.5228 | -34.7671 | -2.0162 | -2.0208 |
72
- | 0.9688 | 1.82 | 700 | 0.9969 | -0.0143 | -0.0174 | 0.5482 | 0.0031 | -39.2598 | -35.4681 | -1.9235 | -1.9280 |
73
- | 0.957 | 2.08 | 800 | 0.9954 | -0.0214 | -0.0260 | 0.5540 | 0.0046 | -40.1194 | -36.1733 | -1.8363 | -1.8407 |
74
- | 0.9358 | 2.34 | 900 | 0.9939 | -0.0362 | -0.0423 | 0.5365 | 0.0061 | -41.7483 | -37.6532 | -1.6988 | -1.7029 |
75
- | 0.9535 | 2.6 | 1000 | 0.9921 | -0.0511 | -0.0591 | 0.5453 | 0.0079 | -43.4237 | -39.1479 | -1.6143 | -1.6183 |
76
- | 0.9616 | 2.86 | 1100 | 0.9916 | -0.0562 | -0.0646 | 0.5453 | 0.0084 | -43.9754 | -39.6505 | -1.5880 | -1.5920 |
77
- | 0.9167 | 3.12 | 1200 | 0.9912 | -0.0563 | -0.0651 | 0.5482 | 0.0088 | -44.0289 | -39.6666 | -1.5851 | -1.5890 |
78
- | 0.9033 | 3.38 | 1300 | 0.9913 | -0.0570 | -0.0657 | 0.5453 | 0.0087 | -44.0868 | -39.7316 | -1.5817 | -1.5856 |
79
- | 0.9285 | 3.64 | 1400 | 0.9912 | -0.0569 | -0.0657 | 0.5395 | 0.0088 | -44.0852 | -39.7216 | -1.5825 | -1.5864 |
80
- | 0.9196 | 3.9 | 1500 | 0.9913 | -0.0567 | -0.0655 | 0.5424 | 0.0088 | -44.0648 | -39.7075 | -1.5832 | -1.5871 |
81
 
82
 
83
  ### Framework versions
 
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: 0.6917
24
+ - Rewards/chosen: -0.0042
25
+ - Rewards/rejected: -0.0078
26
+ - Rewards/accuracies: 0.5303
27
+ - Rewards/margins: 0.0036
28
+ - Logps/rejected: -37.5946
29
+ - Logps/chosen: -34.0769
30
+ - Logits/rejected: -2.2218
31
+ - Logits/chosen: -2.2267
32
 
33
  ## Model description
34
 
 
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: cosine
59
  - lr_scheduler_warmup_ratio: 0.1
60
+ - num_epochs: 1
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
66
+ | 0.6868 | 0.26 | 100 | 0.6924 | -0.0018 | -0.0036 | 0.5282 | 0.0018 | -37.5527 | -34.0527 | -2.2284 | -2.2332 |
67
+ | 0.6774 | 0.52 | 200 | 0.6914 | -0.0013 | -0.0052 | 0.5511 | 0.0039 | -37.5690 | -34.0476 | -2.2247 | -2.2295 |
68
+ | 0.6615 | 0.78 | 300 | 0.6913 | -0.0042 | -0.0084 | 0.5478 | 0.0042 | -37.6008 | -34.0770 | -2.2215 | -2.2263 |
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "k_proj",
23
- "o_proj",
24
- "v_proj",
25
- "down_proj",
26
  "up_proj",
27
- "gate_proj",
28
- "q_proj"
 
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "gate_proj",
23
  "k_proj",
 
 
 
24
  "up_proj",
25
+ "down_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "v_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:f9968a4bb556b78754d04833393473ea61e6cc9ca517cac1ac531d1dbcbe29e5
3
  size 176183216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3503d9ddd98d9d9f7de16d9978bbd26fa9fc2615f5d65c6a399fad9a2db5dcfa
3
  size 176183216
all_results.json CHANGED
@@ -1,21 +1,21 @@
1
  {
2
- "epoch": 4.0,
3
- "eval_logits/chosen": -1.5872344970703125,
4
- "eval_logits/rejected": -1.58331298828125,
5
- "eval_logps/chosen": -39.727821350097656,
6
- "eval_logps/rejected": -44.08587646484375,
7
- "eval_loss": 0.9912604689598083,
8
- "eval_rewards/accuracies": 0.5510797500610352,
9
- "eval_rewards/chosen": -0.056932687759399414,
10
- "eval_rewards/margins": 0.008759919553995132,
11
- "eval_rewards/rejected": -0.06569261103868484,
12
- "eval_runtime": 145.7755,
13
  "eval_samples": 343,
14
- "eval_samples_per_second": 2.353,
15
  "eval_steps_per_second": 0.295,
16
- "train_loss": 0.7654441864459546,
17
- "train_runtime": 10797.8934,
18
  "train_samples": 3079,
19
- "train_samples_per_second": 1.141,
20
- "train_steps_per_second": 0.143
21
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -2.2266557216644287,
4
+ "eval_logits/rejected": -2.2218236923217773,
5
+ "eval_logps/chosen": -34.07685852050781,
6
+ "eval_logps/rejected": -37.5946159362793,
7
+ "eval_loss": 0.6916552186012268,
8
+ "eval_rewards/accuracies": 0.530315637588501,
9
+ "eval_rewards/chosen": -0.0042304228991270065,
10
+ "eval_rewards/margins": 0.0035695433616638184,
11
+ "eval_rewards/rejected": -0.007799965795129538,
12
+ "eval_runtime": 145.8282,
13
  "eval_samples": 343,
14
+ "eval_samples_per_second": 2.352,
15
  "eval_steps_per_second": 0.295,
16
+ "train_loss": 0.6806787961489195,
17
+ "train_runtime": 3251.1509,
18
  "train_samples": 3079,
19
+ "train_samples_per_second": 0.947,
20
+ "train_steps_per_second": 0.118
21
  }
eval_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "epoch": 4.0,
3
- "eval_logits/chosen": -1.5872344970703125,
4
- "eval_logits/rejected": -1.58331298828125,
5
- "eval_logps/chosen": -39.727821350097656,
6
- "eval_logps/rejected": -44.08587646484375,
7
- "eval_loss": 0.9912604689598083,
8
- "eval_rewards/accuracies": 0.5510797500610352,
9
- "eval_rewards/chosen": -0.056932687759399414,
10
- "eval_rewards/margins": 0.008759919553995132,
11
- "eval_rewards/rejected": -0.06569261103868484,
12
- "eval_runtime": 145.7755,
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": -2.2266557216644287,
4
+ "eval_logits/rejected": -2.2218236923217773,
5
+ "eval_logps/chosen": -34.07685852050781,
6
+ "eval_logps/rejected": -37.5946159362793,
7
+ "eval_loss": 0.6916552186012268,
8
+ "eval_rewards/accuracies": 0.530315637588501,
9
+ "eval_rewards/chosen": -0.0042304228991270065,
10
+ "eval_rewards/margins": 0.0035695433616638184,
11
+ "eval_rewards/rejected": -0.007799965795129538,
12
+ "eval_runtime": 145.8282,
13
  "eval_samples": 343,
14
+ "eval_samples_per_second": 2.352,
15
  "eval_steps_per_second": 0.295
16
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.0,
3
- "train_loss": 0.7654441864459546,
4
- "train_runtime": 10797.8934,
5
  "train_samples": 3079,
6
- "train_samples_per_second": 1.141,
7
- "train_steps_per_second": 0.143
8
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6806787961489195,
4
+ "train_runtime": 3251.1509,
5
  "train_samples": 3079,
6
+ "train_samples_per_second": 0.947,
7
+ "train_steps_per_second": 0.118
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 sha256:237d42c7ba4f1b445e179b3dad6558bffee1c3e58cd08115fd9ec93a609a8a24
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc8fb2b683b883f5d1032d53b51d9d1dc3ba04b14a841b9b67e32339facc1ba
3
  size 4984