Model save
Browse files- README.md +21 -25
- adapter_model.safetensors +1 -1
- all_results.json +3 -18
- train_results.json +3 -3
- trainer_state.json +0 -0
README.md
CHANGED
@@ -1,14 +1,10 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
9 |
base_model: mistralai/Mistral-7B-v0.1
|
10 |
-
datasets:
|
11 |
-
- HuggingFaceH4/ultrafeedback_binarized
|
12 |
model-index:
|
13 |
- name: zephyr-7b
|
14 |
results: []
|
@@ -19,19 +15,19 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
# zephyr-7b
|
21 |
|
22 |
-
This model is a fine-tuned version of [
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 0.
|
25 |
-
- Rewards/chosen: -0.
|
26 |
-
- Rewards/rejected: -0.
|
27 |
-
- Rewards/accuracies: 0.
|
28 |
-
- Rewards/margins: 0.
|
29 |
-
- Logps/rejected: -
|
30 |
-
- Logps/chosen: -
|
31 |
-
- Logits/rejected:
|
32 |
-
- Logits/chosen:
|
33 |
-
- Use Label:
|
34 |
-
- Pred Label:
|
35 |
|
36 |
## Model description
|
37 |
|
@@ -68,15 +64,15 @@ The following hyperparameters were used during training:
|
|
68 |
|
69 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Use Label | Pred Label |
|
70 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:----------:|:----------:|
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
library_name: peft
|
3 |
tags:
|
|
|
4 |
- trl
|
5 |
- dpo
|
6 |
- generated_from_trainer
|
7 |
base_model: mistralai/Mistral-7B-v0.1
|
|
|
|
|
8 |
model-index:
|
9 |
- name: zephyr-7b
|
10 |
results: []
|
|
|
15 |
|
16 |
# zephyr-7b
|
17 |
|
18 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6907
|
21 |
+
- Rewards/chosen: -0.3413
|
22 |
+
- Rewards/rejected: -0.5651
|
23 |
+
- Rewards/accuracies: 0.3631
|
24 |
+
- Rewards/margins: 0.2238
|
25 |
+
- Logps/rejected: -131.9111
|
26 |
+
- Logps/chosen: -103.0301
|
27 |
+
- Logits/rejected: -0.1367
|
28 |
+
- Logits/chosen: -0.2437
|
29 |
+
- Use Label: 14866.4766
|
30 |
+
- Pred Label: 3821.5239
|
31 |
|
32 |
## Model description
|
33 |
|
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Use Label | Pred Label |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:----------:|:----------:|
|
67 |
+
| 0.6818 | 0.1 | 100 | 0.6814 | -0.0056 | -0.0496 | 0.3393 | 0.0440 | -80.3582 | -69.4632 | -2.0664 | -2.0975 | 1833.4603 | 22.5397 |
|
68 |
+
| 0.6818 | 0.21 | 200 | 0.6861 | -0.1358 | -0.2381 | 0.3373 | 0.1023 | -99.2068 | -82.4782 | -1.9938 | -2.0215 | 3701.2063 | 258.7936 |
|
69 |
+
| 0.6848 | 0.31 | 300 | 0.6877 | -0.2068 | -0.3388 | 0.3413 | 0.1320 | -109.2766 | -89.5763 | -1.8828 | -1.9157 | 5437.8730 | 626.1270 |
|
70 |
+
| 0.6857 | 0.42 | 400 | 0.6885 | -0.1802 | -0.3299 | 0.3532 | 0.1497 | -108.3913 | -86.9237 | -1.4031 | -1.4529 | 7112.4443 | 1055.5555 |
|
71 |
+
| 0.6894 | 0.52 | 500 | 0.6892 | -0.2862 | -0.4559 | 0.3552 | 0.1697 | -120.9922 | -97.5203 | -0.5997 | -0.6889 | 8741.4287 | 1530.5714 |
|
72 |
+
| 0.6881 | 0.63 | 600 | 0.6918 | -0.3826 | -0.6059 | 0.3532 | 0.2233 | -135.9845 | -107.1618 | -0.2548 | -0.3579 | 10293.6826 | 2082.3174 |
|
73 |
+
| 0.6913 | 0.73 | 700 | 0.6899 | -0.3542 | -0.5787 | 0.3671 | 0.2244 | -133.2637 | -104.3247 | -0.2462 | -0.3470 | 11806.4766 | 2673.5239 |
|
74 |
+
| 0.6893 | 0.84 | 800 | 0.6904 | -0.3443 | -0.5684 | 0.3631 | 0.2241 | -132.2416 | -103.3355 | -0.1293 | -0.2367 | 13331.9043 | 3252.0952 |
|
75 |
+
| 0.689 | 0.94 | 900 | 0.6907 | -0.3413 | -0.5651 | 0.3631 | 0.2238 | -131.9111 | -103.0301 | -0.1367 | -0.2437 | 14866.4766 | 3821.5239 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671150064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a372ac4c2a71cd6d3d51983272071541becc25a55e74ef4b7ce122dbc6f2b513
|
3 |
size 671150064
|
all_results.json
CHANGED
@@ -1,23 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"eval_logps/chosen": -123.7209243774414,
|
6 |
-
"eval_logps/rejected": -161.63131713867188,
|
7 |
-
"eval_loss": 0.6788680553436279,
|
8 |
-
"eval_pred_label": 2490.952392578125,
|
9 |
-
"eval_rewards/accuracies": 0.3591269850730896,
|
10 |
-
"eval_rewards/chosen": -0.548203706741333,
|
11 |
-
"eval_rewards/margins": 0.3141288757324219,
|
12 |
-
"eval_rewards/rejected": -0.8623325824737549,
|
13 |
-
"eval_runtime": 247.4536,
|
14 |
-
"eval_samples": 2000,
|
15 |
-
"eval_samples_per_second": 8.082,
|
16 |
-
"eval_steps_per_second": 0.255,
|
17 |
-
"eval_use_label": 17581.046875,
|
18 |
-
"train_loss": 0.6760230718482851,
|
19 |
-
"train_runtime": 20063.9235,
|
20 |
"train_samples": 61135,
|
21 |
-
"train_samples_per_second": 3.
|
22 |
"train_steps_per_second": 0.048
|
23 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6880922077838039,
|
4 |
+
"train_runtime": 20023.3666,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"train_samples": 61135,
|
6 |
+
"train_samples_per_second": 3.053,
|
7 |
"train_steps_per_second": 0.048
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 61135,
|
6 |
-
"train_samples_per_second": 3.
|
7 |
"train_steps_per_second": 0.048
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6880922077838039,
|
4 |
+
"train_runtime": 20023.3666,
|
5 |
"train_samples": 61135,
|
6 |
+
"train_samples_per_second": 3.053,
|
7 |
"train_steps_per_second": 0.048
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|