Hugging Face's logo

taicheng
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
taicheng commited on
Commit
0993a3c
·
verified ·
1 Parent(s): 5d80b61

Model save

Browse files
Files changed (4) hide show
  1. README.md +20 -20
  2. all_results.json +4 -4
  3. train_results.json +4 -4
  4. trainer_state.json +0 -0
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 [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4952
22
- - Rewards/chosen: -2.8107
23
- - Rewards/rejected: -3.8708
24
- - Rewards/accuracies: 0.7718
25
- - Rewards/margins: 1.0601
26
- - Logps/rejected: -631.7385
27
- - Logps/chosen: -545.9743
28
- - Logits/rejected: -1.0385
29
- - Logits/chosen: -1.1509
30
 
31
  ## Model description
32
 
@@ -61,17 +61,17 @@ The following hyperparameters were used during training:
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
- | 0.6163 | 0.1047 | 100 | -2.1006 | -2.0162 | -303.8351 | -310.3097 | 0.6178 | 0.6806 | -0.3893 | 0.2672 | -0.6565 |
67
- | 0.5679 | 0.2094 | 200 | -1.8227 | -1.7394 | -352.2879 | -389.6575 | 0.5567 | 0.7401 | -0.8739 | 0.5761 | -1.4500 |
68
- | 0.5412 | 0.3141 | 300 | -1.3111 | -1.2181 | -421.3257 | -483.0423 | 0.5305 | 0.7460 | -1.5642 | 0.8196 | -2.3838 |
69
- | 0.5364 | 0.4187 | 400 | -1.2334 | -1.1332 | -416.6979 | -476.3458 | 0.5143 | 0.7579 | -1.5180 | 0.7989 | -2.3169 |
70
- | 0.5046 | 0.5234 | 500 | -1.1373 | -1.0302 | -529.9542 | -605.2977 | 0.5062 | 0.7579 | -2.6505 | 0.9559 | -3.6064 |
71
- | 0.4736 | 0.6281 | 600 | 0.5059 | -2.7244 | -3.7650 | 0.7639 | 1.0406 | -621.1549 | -537.3406 | -1.0135 | -1.1253 |
72
- | 0.4619 | 0.7328 | 700 | 0.4994 | -2.9240 | -3.9991 | 0.7619 | 1.0750 | -644.5651 | -557.3041 | -1.0064 | -1.1194 |
73
- | 0.4926 | 0.8375 | 800 | 0.4962 | -2.7247 | -3.7455 | 0.7659 | 1.0207 | -619.2051 | -537.3770 | -1.0516 | -1.1641 |
74
- | 0.4856 | 0.9422 | 900 | 0.4952 | -2.8107 | -3.8708 | 0.7718 | 1.0601 | -631.7385 | -545.9743 | -1.0385 | -1.1509 |
75
 
76
 
77
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4945
22
+ - Rewards/chosen: -2.5678
23
+ - Rewards/rejected: -3.6349
24
+ - Rewards/accuracies: 0.7778
25
+ - Rewards/margins: 1.0671
26
+ - Logps/rejected: -608.1346
27
+ - Logps/chosen: -521.7063
28
+ - Logits/rejected: -0.9901
29
+ - Logits/chosen: -1.1024
30
 
31
  ## Model description
32
 
 
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
+ | 0.6212 | 0.1047 | 100 | 0.6321 | -0.3313 | -0.5450 | 0.6944 | 0.2137 | -299.1472 | -298.0506 | -2.0086 | -2.0933 |
67
+ | 0.5618 | 0.2094 | 200 | 0.5601 | -0.8198 | -1.3660 | 0.7222 | 0.5461 | -381.2446 | -346.9064 | -1.6694 | -1.7551 |
68
+ | 0.54 | 0.3141 | 300 | 0.5265 | -1.5221 | -2.3343 | 0.7460 | 0.8122 | -478.0748 | -417.1275 | -1.0704 | -1.1715 |
69
+ | 0.5261 | 0.4187 | 400 | 0.5082 | -1.6553 | -2.5263 | 0.7540 | 0.8710 | -497.2759 | -430.4526 | -1.1014 | -1.2013 |
70
+ | 0.5107 | 0.5234 | 500 | 0.5059 | -2.4506 | -3.4250 | 0.75 | 0.9744 | -587.1476 | -509.9848 | -0.9852 | -1.0956 |
71
+ | 0.4851 | 0.6281 | 600 | 0.5023 | -2.2726 | -3.2316 | 0.7679 | 0.9590 | -567.8049 | -492.1783 | -0.9970 | -1.1078 |
72
+ | 0.4681 | 0.7328 | 700 | 0.4993 | -2.3170 | -3.3688 | 0.7679 | 1.0517 | -581.5197 | -496.6232 | -1.0068 | -1.1190 |
73
+ | 0.4852 | 0.8375 | 800 | 0.4950 | -2.3970 | -3.4117 | 0.7738 | 1.0147 | -585.8156 | -504.6183 | -1.0237 | -1.1353 |
74
+ | 0.4907 | 0.9422 | 900 | 0.4945 | -2.5678 | -3.6349 | 0.7778 | 1.0671 | -608.1346 | -521.7063 | -0.9901 | -1.1024 |
75
 
76
 
77
  ### Framework versions
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9997382884061764,
3
  "total_flos": 0.0,
4
- "train_loss": 0.2358125359600127,
5
- "train_runtime": 19082.7985,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 3.204,
8
- "train_steps_per_second": 0.05
9
  }
 
1
  {
2
  "epoch": 0.9997382884061764,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.5319095570379527,
5
+ "train_runtime": 23762.0752,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 2.573,
8
+ "train_steps_per_second": 0.04
9
  }
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9997382884061764,
3
  "total_flos": 0.0,
4
- "train_loss": 0.2358125359600127,
5
- "train_runtime": 19082.7985,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 3.204,
8
- "train_steps_per_second": 0.05
9
  }
 
1
  {
2
  "epoch": 0.9997382884061764,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.5319095570379527,
5
+ "train_runtime": 23762.0752,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 2.573,
8
+ "train_steps_per_second": 0.04
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff