Hugging Face's logo

guoyu-zhang
/
model_hh_usp4_400

PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card Files Community
guoyu-zhang commited on
Commit
fb04e6c
•
1 Parent(s): 6c5f9e7

model_hh_usp4_400

Browse files
Files changed (6) hide show
  1. README.md +19 -19
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. final_checkpoint/adapter_config.json +3 -3
  5. final_checkpoint/adapter_model.safetensors +1 -1
  6. training_args.bin +1 -1
README.md CHANGED
@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 4.8447
22
- - Rewards/chosen: -12.8728
23
- - Rewards/rejected: -15.9738
24
- - Rewards/accuracies: 0.6200
25
- - Rewards/margins: 3.1010
26
- - Logps/rejected: -130.8977
27
- - Logps/chosen: -125.8617
28
- - Logits/rejected: -0.9554
29
- - Logits/chosen: -0.9016
30
 
31
  ## Model description
32
 
@@ -60,16 +60,16 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
- | 0.0115 | 4.0 | 100 | 2.1095 | -12.3873 | -13.8364 | 0.6200 | 1.4491 | -128.5228 | -125.3223 | -0.2640 | -0.2414 |
64
- | 0.0271 | 8.0 | 200 | 3.0011 | -0.7751 | -1.2662 | 0.5200 | 0.4911 | -114.5559 | -112.4198 | -0.1794 | -0.1752 |
65
- | 0.0029 | 12.0 | 300 | 5.8848 | -30.6815 | -32.8502 | 0.5300 | 2.1687 | -149.6492 | -145.6491 | -0.9305 | -0.8856 |
66
- | 0.0 | 16.0 | 400 | 4.8706 | -12.8599 | -15.9629 | 0.6200 | 3.1030 | -130.8855 | -125.8473 | -0.9564 | -0.9029 |
67
- | 0.0 | 20.0 | 500 | 4.8654 | -12.8852 | -15.9625 | 0.6200 | 3.0773 | -130.8851 | -125.8754 | -0.9556 | -0.9016 |
68
- | 0.0 | 24.0 | 600 | 4.8663 | -12.8617 | -15.9688 | 0.6200 | 3.1071 | -130.8921 | -125.8493 | -0.9551 | -0.9013 |
69
- | 0.0 | 28.0 | 700 | 4.8599 | -12.8977 | -15.9664 | 0.6200 | 3.0686 | -130.8894 | -125.8893 | -0.9553 | -0.9015 |
70
- | 0.0 | 32.0 | 800 | 4.8410 | -12.8636 | -15.9914 | 0.6200 | 3.1277 | -130.9172 | -125.8515 | -0.9553 | -0.9014 |
71
- | 0.0 | 36.0 | 900 | 4.8425 | -12.8856 | -15.9582 | 0.6200 | 3.0726 | -130.8803 | -125.8759 | -0.9551 | -0.9014 |
72
- | 0.0 | 40.0 | 1000 | 4.8447 | -12.8728 | -15.9738 | 0.6200 | 3.1010 | -130.8977 | -125.8617 | -0.9554 | -0.9016 |
73
 
74
 
75
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 4.4266
22
+ - Rewards/chosen: -7.2918
23
+ - Rewards/rejected: -9.3870
24
+ - Rewards/accuracies: 0.5500
25
+ - Rewards/margins: 2.0952
26
+ - Logps/rejected: -122.5611
27
+ - Logps/chosen: -121.2051
28
+ - Logits/rejected: -0.2787
29
+ - Logits/chosen: -0.2572
30
 
31
  ## Model description
32
 
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 0.098 | 4.0 | 100 | 2.3307 | -3.2289 | -4.9359 | 0.5700 | 1.7070 | -117.6155 | -116.6908 | -0.5136 | -0.5011 |
64
+ | 0.2615 | 8.0 | 200 | 3.5637 | -3.5399 | -4.5546 | 0.5700 | 1.0147 | -117.1918 | -117.0363 | -0.4837 | -0.4844 |
65
+ | 0.0137 | 12.0 | 300 | 4.2146 | -3.4955 | -5.8321 | 0.5600 | 2.3366 | -118.6113 | -116.9870 | -0.3503 | -0.3327 |
66
+ | 0.0 | 16.0 | 400 | 4.4247 | -7.2840 | -9.3968 | 0.5500 | 2.1128 | -122.5721 | -121.1964 | -0.2788 | -0.2574 |
67
+ | 0.0 | 20.0 | 500 | 4.4045 | -7.2800 | -9.4193 | 0.5600 | 2.1393 | -122.5971 | -121.1920 | -0.2793 | -0.2578 |
68
+ | 0.0 | 24.0 | 600 | 4.4242 | -7.2774 | -9.3711 | 0.5600 | 2.0936 | -122.5435 | -121.1891 | -0.2789 | -0.2573 |
69
+ | 0.0 | 28.0 | 700 | 4.4048 | -7.2951 | -9.4062 | 0.5600 | 2.1110 | -122.5825 | -121.2088 | -0.2785 | -0.2570 |
70
+ | 0.0 | 32.0 | 800 | 4.4098 | -7.2804 | -9.3847 | 0.5500 | 2.1043 | -122.5586 | -121.1924 | -0.2783 | -0.2569 |
71
+ | 0.0 | 36.0 | 900 | 4.4251 | -7.2849 | -9.3768 | 0.5500 | 2.0918 | -122.5498 | -121.1974 | -0.2792 | -0.2575 |
72
+ | 0.0 | 40.0 | 1000 | 4.4266 | -7.2918 | -9.3870 | 0.5500 | 2.0952 | -122.5611 | -121.2051 | -0.2787 | -0.2572 |
73
 
74
 
75
  ### Framework versions
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "fc_out",
24
- "k_proj",
25
- "wte",
26
  "v_proj",
27
- "fc_in",
28
  "q_proj",
 
29
  "out_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "fc_in",
24
  "fc_out",
 
 
25
  "v_proj",
26
+ "wte",
27
  "q_proj",
28
+ "k_proj",
29
  "out_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ae941c4d05b8de3d6f0cf83630ef65a1fb53d1382a900d5b317ea3a6936bdae
3
  size 12608472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c541264c6df00ab1c1c7f2b98855c93d0ad81ac4752045da7df9d9d4253e9b1
3
  size 12608472
final_checkpoint/adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "fc_out",
24
- "k_proj",
25
- "wte",
26
  "v_proj",
27
- "fc_in",
28
  "q_proj",
 
29
  "out_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "fc_in",
24
  "fc_out",
 
 
25
  "v_proj",
26
+ "wte",
27
  "q_proj",
28
+ "k_proj",
29
  "out_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
final_checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ae941c4d05b8de3d6f0cf83630ef65a1fb53d1382a900d5b317ea3a6936bdae
3
  size 12608472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c541264c6df00ab1c1c7f2b98855c93d0ad81ac4752045da7df9d9d4253e9b1
3
  size 12608472
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c4bf29ebe38e562cba8c2a8bd6b3f6016dc211695290125d3803e8c63282560
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6bb695e37bfcc88c4754bdc34684ec1747667d55be1250a5b962a9f6ce62fdc
3
  size 4984