Model save
Browse files- README.md +19 -25
- all_results.json +4 -17
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- runs/Apr26_05-14-17_dsw-3393-565b8f59b6-l5p7k/events.out.tfevents.1714108924.dsw-3393-565b8f59b6-l5p7k.40537.0 +2 -2
- train_results.json +4 -4
- trainer_state.json +0 -0
README.md
CHANGED
@@ -2,15 +2,9 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
9 |
-
- trl
|
10 |
-
- dpo
|
11 |
-
- generated_from_trainer
|
12 |
-
datasets:
|
13 |
-
- HuggingFaceH4/ultrafeedback_binarized
|
14 |
model-index:
|
15 |
- name: zephyr-7b-dpo-full
|
16 |
results: []
|
@@ -21,17 +15,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
|
22 |
# zephyr-7b-dpo-full
|
23 |
|
24 |
-
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on
|
25 |
It achieves the following results on the evaluation set:
|
26 |
-
- Loss:
|
27 |
-
- Rewards/chosen: -
|
28 |
-
- Rewards/rejected: -
|
29 |
-
- Rewards/accuracies: 0.
|
30 |
-
- Rewards/margins:
|
31 |
-
- Logps/rejected: -
|
32 |
-
- Logps/chosen: -
|
33 |
-
- Logits/rejected: 0.
|
34 |
-
- Logits/chosen: -
|
35 |
|
36 |
## Model description
|
37 |
|
@@ -68,15 +62,15 @@ 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 |
|
70 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: zephyr-7b-dpo-full
|
10 |
results: []
|
|
|
15 |
|
16 |
# zephyr-7b-dpo-full
|
17 |
|
18 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.3374
|
21 |
+
- Rewards/chosen: -14.5395
|
22 |
+
- Rewards/rejected: -18.1313
|
23 |
+
- Rewards/accuracies: 0.6409
|
24 |
+
- Rewards/margins: 3.5918
|
25 |
+
- Logps/rejected: -2073.3389
|
26 |
+
- Logps/chosen: -1735.9152
|
27 |
+
- Logits/rejected: -0.6740
|
28 |
+
- Logits/chosen: -1.0018
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
+
| 4.5854 | 0.1047 | 100 | 4.3811 | -0.2719 | -0.4992 | 0.6488 | 0.2273 | -310.1242 | -309.1552 | -2.1923 | -2.2813 |
|
66 |
+
| 2.6464 | 0.2093 | 200 | 2.6063 | -9.6247 | -11.6315 | 0.625 | 2.0068 | -1423.3580 | -1244.4360 | 0.6982 | -0.3562 |
|
67 |
+
| 1.9069 | 0.3140 | 300 | 2.2624 | -9.8468 | -11.9256 | 0.6329 | 2.0788 | -1452.7675 | -1266.6490 | 1.5569 | 0.4590 |
|
68 |
+
| 1.6642 | 0.4186 | 400 | 1.6421 | -14.4918 | -17.8494 | 0.625 | 3.3576 | -2045.1493 | -1731.1526 | -0.0875 | -0.7751 |
|
69 |
+
| 1.6328 | 0.5233 | 500 | 1.5120 | -13.0737 | -16.3036 | 0.6389 | 3.2299 | -1890.5623 | -1589.3370 | -0.0918 | -0.6590 |
|
70 |
+
| 1.6032 | 0.6279 | 600 | 1.4752 | -17.3374 | -21.4238 | 0.6230 | 4.0864 | -2402.5845 | -2015.7072 | 0.6402 | 0.0190 |
|
71 |
+
| 1.5039 | 0.7326 | 700 | 1.3853 | -14.1299 | -17.5624 | 0.6528 | 3.4325 | -2016.4491 | -1694.9624 | -0.4968 | -0.8898 |
|
72 |
+
| 1.3527 | 0.8373 | 800 | 1.3663 | -13.9016 | -17.2583 | 0.6448 | 3.3567 | -1986.0359 | -1672.1306 | -0.6750 | -1.0375 |
|
73 |
+
| 1.5137 | 0.9419 | 900 | 1.3374 | -14.5395 | -18.1313 | 0.6409 | 3.5918 | -2073.3389 | -1735.9152 | -0.6740 | -1.0018 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,22 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 0.9994767137624281,
|
3 |
-
"eval_logits/chosen": -0.35997089743614197,
|
4 |
-
"eval_logits/rejected": 0.7096247673034668,
|
5 |
-
"eval_logps/chosen": -440.0589599609375,
|
6 |
-
"eval_logps/rejected": -523.0543212890625,
|
7 |
-
"eval_loss": 0.4903615117073059,
|
8 |
-
"eval_rewards/accuracies": 0.7698412537574768,
|
9 |
-
"eval_rewards/chosen": -1.5809098482131958,
|
10 |
-
"eval_rewards/margins": 1.0475648641586304,
|
11 |
-
"eval_rewards/rejected": -2.6284749507904053,
|
12 |
-
"eval_runtime": 176.963,
|
13 |
-
"eval_samples": 2000,
|
14 |
-
"eval_samples_per_second": 11.302,
|
15 |
-
"eval_steps_per_second": 0.356,
|
16 |
"total_flos": 0.0,
|
17 |
-
"train_loss":
|
18 |
-
"train_runtime":
|
19 |
"train_samples": 61134,
|
20 |
-
"train_samples_per_second": 3.
|
21 |
-
"train_steps_per_second": 0.
|
22 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.9994767137624281,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 2.1165736393154604,
|
5 |
+
"train_runtime": 18133.1885,
|
6 |
"train_samples": 61134,
|
7 |
+
"train_samples_per_second": 3.371,
|
8 |
+
"train_steps_per_second": 0.053
|
9 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d01b4522d4331954513b741ee229db1ee50faf8180950d2d7b946855cdc3515
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9d70ede8f353fbc790dfdd38530b55b9faebfe3d7ab5a06afc531f4dc531553
|
3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2ec0eb8794a7b89aac7eb2e3ef3fa32dde10b0bae20f9ab2fd46b776d16e913
|
3 |
size 4540516344
|
runs/Apr26_05-14-17_dsw-3393-565b8f59b6-l5p7k/events.out.tfevents.1714108924.dsw-3393-565b8f59b6-l5p7k.40537.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ca7d85abffa48f034963c09db20b166c6eaf7f43f9224e061784a0d538dacef
|
3 |
+
size 74119
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 0.9994767137624281,
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss":
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 61134,
|
7 |
-
"train_samples_per_second": 3.
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.9994767137624281,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 2.1165736393154604,
|
5 |
+
"train_runtime": 18133.1885,
|
6 |
"train_samples": 61134,
|
7 |
+
"train_samples_per_second": 3.371,
|
8 |
+
"train_steps_per_second": 0.053
|
9 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|