Model save
Browse files- README.md +2 -23
- all_results.json +5 -5
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- train_results.json +5 -5
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -14,16 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# zephyr-7b-dpo-full
|
15 |
|
16 |
This model was trained from scratch on the None dataset.
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.5286
|
19 |
-
- Rewards/chosen: -1.7068
|
20 |
-
- Rewards/rejected: -3.1572
|
21 |
-
- Rewards/accuracies: 0.7695
|
22 |
-
- Rewards/margins: 1.4504
|
23 |
-
- Logps/rejected: -627.3446
|
24 |
-
- Logps/chosen: -474.2680
|
25 |
-
- Logits/rejected: -0.7503
|
26 |
-
- Logits/chosen: -0.5802
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -43,12 +33,12 @@ More information needed
|
|
43 |
|
44 |
The following hyperparameters were used during training:
|
45 |
- learning_rate: 1e-06
|
46 |
-
- train_batch_size:
|
47 |
- eval_batch_size: 8
|
48 |
- seed: 5
|
49 |
- distributed_type: multi-GPU
|
50 |
- num_devices: 8
|
51 |
-
- gradient_accumulation_steps:
|
52 |
- total_train_batch_size: 128
|
53 |
- total_eval_batch_size: 64
|
54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
@@ -58,17 +48,6 @@ The following hyperparameters were used during training:
|
|
58 |
|
59 |
### Training results
|
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 |
-
| 0.6254 | 0.21 | 100 | 0.6260 | -0.1988 | -0.5392 | 0.6992 | 0.3404 | -365.5406 | -323.4606 | 0.3870 | 0.3426 |
|
64 |
-
| 0.5841 | 0.42 | 200 | 0.5597 | -0.4205 | -1.0478 | 0.7305 | 0.6273 | -416.4040 | -345.6356 | 0.1437 | 0.0907 |
|
65 |
-
| 0.5389 | 0.63 | 300 | 0.5285 | -0.6859 | -1.5998 | 0.7773 | 0.9140 | -471.6094 | -372.1726 | 0.2331 | 0.2134 |
|
66 |
-
| 0.5188 | 0.84 | 400 | 0.5197 | -0.7311 | -1.7606 | 0.7852 | 1.0295 | -487.6861 | -376.6970 | -0.1165 | -0.1000 |
|
67 |
-
| 0.3402 | 1.05 | 500 | 0.5344 | -1.5025 | -2.9522 | 0.7773 | 1.4497 | -606.8411 | -453.8337 | -0.4375 | -0.3802 |
|
68 |
-
| 0.3141 | 1.26 | 600 | 0.5426 | -1.7806 | -3.3337 | 0.7539 | 1.5531 | -644.9940 | -481.6454 | -0.6733 | -0.5363 |
|
69 |
-
| 0.3324 | 1.47 | 700 | 0.5322 | -1.7213 | -3.2147 | 0.7773 | 1.4934 | -633.0936 | -475.7130 | -0.9457 | -0.7473 |
|
70 |
-
| 0.3372 | 1.67 | 800 | 0.5313 | -1.7652 | -3.2295 | 0.7656 | 1.4643 | -634.5750 | -480.1067 | -0.7581 | -0.5822 |
|
71 |
-
| 0.3058 | 1.88 | 900 | 0.5286 | -1.7068 | -3.1572 | 0.7695 | 1.4504 | -627.3446 | -474.2680 | -0.7503 | -0.5802 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
14 |
# zephyr-7b-dpo-full
|
15 |
|
16 |
This model was trained from scratch on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 1e-06
|
36 |
+
- train_batch_size: 2
|
37 |
- eval_batch_size: 8
|
38 |
- seed: 5
|
39 |
- distributed_type: multi-GPU
|
40 |
- num_devices: 8
|
41 |
+
- gradient_accumulation_steps: 8
|
42 |
- total_train_batch_size: 128
|
43 |
- total_eval_batch_size: 64
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
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": 2.0,
|
3 |
+
"train_loss": 0.11559809408500558,
|
4 |
+
"train_runtime": 23407.6305,
|
5 |
+
"train_samples": 106682,
|
6 |
+
"train_samples_per_second": 9.115,
|
7 |
+
"train_steps_per_second": 0.071
|
8 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0e47c941b4dacd35c121d5e4bc0286cf8b5e81054c59e2d56144e860df9597c
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dca0065a230087c3b55705c6a6f7054e64f0b81d4cd9031df0f8aad008ede197
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d1d4980829c9d3d06ef7a81e02fffa0e40201c4532305ec6a04aba5f5e1b689
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdae88e9a153704c05b7398a5c9237f862194fe810bc9fe187286c41d9552058
|
3 |
size 1168138808
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
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": 2.0,
|
3 |
+
"train_loss": 0.11559809408500558,
|
4 |
+
"train_runtime": 23407.6305,
|
5 |
+
"train_samples": 106682,
|
6 |
+
"train_samples_per_second": 9.115,
|
7 |
+
"train_steps_per_second": 0.071
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53e04de78c43c6d34212d0523f5accae0cd42011de8bac7befb2084cd87faa70
|
3 |
size 6648
|