Model save
Browse files- README.md +32 -38
- adapter_model.safetensors +1 -1
- all_results.json +5 -18
- train_results.json +5 -5
- trainer_state.json +0 -0
README.md
CHANGED
@@ -2,16 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
-
- trl
|
7 |
-
- dpo
|
8 |
-
- generated_from_trainer
|
9 |
- trl
|
10 |
- dpo
|
11 |
- generated_from_trainer
|
12 |
base_model: mistralai/Mistral-7B-v0.1
|
13 |
-
datasets:
|
14 |
-
- HuggingFaceH4/ultrafeedback_binarized
|
15 |
model-index:
|
16 |
- name: zephyr-7b-dpo-qlora
|
17 |
results: []
|
@@ -22,17 +16,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
22 |
|
23 |
# zephyr-7b-dpo-qlora
|
24 |
|
25 |
-
This model is a fine-tuned version of [
|
26 |
It achieves the following results on the evaluation set:
|
27 |
-
- Loss: 0.
|
28 |
-
- Rewards/chosen: -2.
|
29 |
-
- Rewards/rejected: -3.
|
30 |
-
- Rewards/accuracies: 0.
|
31 |
-
- Rewards/margins: 1.
|
32 |
-
- Logps/rejected: -
|
33 |
-
- Logps/chosen: -
|
34 |
-
- Logits/rejected:
|
35 |
-
- Logits/chosen:
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -69,31 +63,31 @@ The following hyperparameters were used during training:
|
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
|
92 |
|
93 |
### Framework versions
|
94 |
|
95 |
- PEFT 0.7.1
|
96 |
-
- Transformers 4.
|
97 |
-
- Pytorch 2.
|
98 |
-
- Datasets 2.
|
99 |
- Tokenizers 0.15.2
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
|
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
8 |
base_model: mistralai/Mistral-7B-v0.1
|
|
|
|
|
9 |
model-index:
|
10 |
- name: zephyr-7b-dpo-qlora
|
11 |
results: []
|
|
|
16 |
|
17 |
# zephyr-7b-dpo-qlora
|
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: 0.4974
|
22 |
+
- Rewards/chosen: -2.4531
|
23 |
+
- Rewards/rejected: -3.4740
|
24 |
+
- Rewards/accuracies: 0.75
|
25 |
+
- Rewards/margins: 1.0209
|
26 |
+
- Logps/rejected: -595.1221
|
27 |
+
- Logps/chosen: -517.0148
|
28 |
+
- Logits/rejected: -1.3432
|
29 |
+
- Logits/chosen: -1.4359
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
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 |
+
| 0.6641 | 0.05 | 100 | 0.6636 | 0.0054 | -0.0681 | 0.6900 | 0.0735 | -254.5337 | -271.1659 | -2.0436 | -2.1368 |
|
67 |
+
| 0.6105 | 0.1 | 200 | 0.6075 | -0.3236 | -0.5938 | 0.6890 | 0.2702 | -307.0967 | -304.0613 | -2.0030 | -2.0919 |
|
68 |
+
| 0.5883 | 0.16 | 300 | 0.5817 | -0.7122 | -1.1286 | 0.7020 | 0.4164 | -360.5768 | -342.9188 | -1.9914 | -2.0761 |
|
69 |
+
| 0.5651 | 0.21 | 400 | 0.5665 | -0.7901 | -1.2897 | 0.7250 | 0.4996 | -376.6874 | -350.7093 | -1.9001 | -1.9820 |
|
70 |
+
| 0.5136 | 0.26 | 500 | 0.5520 | -1.0330 | -1.6646 | 0.7190 | 0.6316 | -414.1808 | -374.9992 | -1.8081 | -1.8880 |
|
71 |
+
| 0.5587 | 0.31 | 600 | 0.5327 | -1.3215 | -2.0089 | 0.7320 | 0.6874 | -448.6079 | -403.8534 | -1.4665 | -1.5609 |
|
72 |
+
| 0.5167 | 0.37 | 700 | 0.5299 | -1.2797 | -2.1992 | 0.7230 | 0.9196 | -467.6413 | -399.6684 | -1.3918 | -1.4903 |
|
73 |
+
| 0.5465 | 0.42 | 800 | 0.5189 | -1.6646 | -2.4686 | 0.7200 | 0.8041 | -494.5844 | -438.1617 | -1.3685 | -1.4642 |
|
74 |
+
| 0.5002 | 0.47 | 900 | 0.5142 | -1.7844 | -2.7217 | 0.7290 | 0.9373 | -519.8885 | -450.1383 | -1.4179 | -1.5054 |
|
75 |
+
| 0.5017 | 0.52 | 1000 | 0.5058 | -2.6175 | -3.6120 | 0.7360 | 0.9946 | -608.9218 | -533.4493 | -1.2973 | -1.3948 |
|
76 |
+
| 0.4966 | 0.58 | 1100 | 0.5043 | -2.0581 | -2.9819 | 0.7370 | 0.9239 | -545.9103 | -477.5080 | -1.3783 | -1.4740 |
|
77 |
+
| 0.5087 | 0.63 | 1200 | 0.5040 | -2.3715 | -3.3475 | 0.7450 | 0.9760 | -582.4712 | -508.8495 | -1.3331 | -1.4262 |
|
78 |
+
| 0.4799 | 0.68 | 1300 | 0.5011 | -2.3067 | -3.3444 | 0.7450 | 1.0377 | -582.1562 | -502.3687 | -1.3340 | -1.4277 |
|
79 |
+
| 0.4606 | 0.73 | 1400 | 0.4991 | -2.5016 | -3.5583 | 0.7430 | 1.0567 | -603.5469 | -521.8631 | -1.3291 | -1.4219 |
|
80 |
+
| 0.4763 | 0.79 | 1500 | 0.4985 | -2.4979 | -3.5204 | 0.7470 | 1.0225 | -599.7631 | -521.4944 | -1.3394 | -1.4325 |
|
81 |
+
| 0.5008 | 0.84 | 1600 | 0.4977 | -2.4555 | -3.4719 | 0.7480 | 1.0164 | -594.9102 | -517.2504 | -1.3492 | -1.4415 |
|
82 |
+
| 0.4654 | 0.89 | 1700 | 0.4976 | -2.4498 | -3.4672 | 0.7510 | 1.0174 | -594.4417 | -516.6852 | -1.3478 | -1.4402 |
|
83 |
+
| 0.4854 | 0.94 | 1800 | 0.4975 | -2.4526 | -3.4731 | 0.7480 | 1.0205 | -595.0339 | -516.9640 | -1.3441 | -1.4366 |
|
84 |
+
| 0.4879 | 0.99 | 1900 | 0.4974 | -2.4531 | -3.4740 | 0.75 | 1.0209 | -595.1221 | -517.0148 | -1.3432 | -1.4359 |
|
85 |
|
86 |
|
87 |
### Framework versions
|
88 |
|
89 |
- PEFT 0.7.1
|
90 |
+
- Transformers 4.39.3
|
91 |
+
- Pytorch 2.3.0+cu121
|
92 |
+
- Datasets 2.19.1
|
93 |
- Tokenizers 0.15.2
|
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 sha256:7b408f44a61689a8466c178933f9b3f575cfed42b20ffb147556750c13f45448
|
3 |
size 671150064
|
all_results.json
CHANGED
@@ -1,21 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"eval_rewards/accuracies": 0.7559999823570251,
|
9 |
-
"eval_rewards/chosen": -2.5097556114196777,
|
10 |
-
"eval_rewards/margins": 1.0807288885116577,
|
11 |
-
"eval_rewards/rejected": -3.590484380722046,
|
12 |
-
"eval_runtime": 449.3054,
|
13 |
-
"eval_samples": 2000,
|
14 |
-
"eval_samples_per_second": 4.451,
|
15 |
-
"eval_steps_per_second": 0.278,
|
16 |
-
"train_loss": 0.528951391499704,
|
17 |
-
"train_runtime": 37787.7404,
|
18 |
-
"train_samples": 61135,
|
19 |
-
"train_samples_per_second": 1.618,
|
20 |
-
"train_steps_per_second": 0.051
|
21 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.5312882837824796,
|
4 |
+
"train_runtime": 19005.9968,
|
5 |
+
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 3.217,
|
7 |
+
"train_steps_per_second": 0.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.5312882837824796,
|
4 |
+
"train_runtime": 19005.9968,
|
5 |
+
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 3.217,
|
7 |
+
"train_steps_per_second": 0.1
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|