Model save
Browse files- README.md +24 -3
- 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
@@ -14,6 +14,16 @@ 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 |
|
18 |
## Model description
|
19 |
|
@@ -33,12 +43,12 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 1e-06
|
36 |
-
- train_batch_size:
|
37 |
- eval_batch_size: 8
|
38 |
-
- seed:
|
39 |
- distributed_type: multi-GPU
|
40 |
- num_devices: 8
|
41 |
-
- gradient_accumulation_steps:
|
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
|
@@ -48,6 +58,17 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
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: 0.5304
|
19 |
+
- Rewards/chosen: -2.0877
|
20 |
+
- Rewards/rejected: -3.5813
|
21 |
+
- Rewards/accuracies: 0.7969
|
22 |
+
- Rewards/margins: 1.4935
|
23 |
+
- Logps/rejected: -669.7546
|
24 |
+
- Logps/chosen: -512.3596
|
25 |
+
- Logits/rejected: -0.0805
|
26 |
+
- Logits/chosen: 0.0044
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
43 |
|
44 |
The following hyperparameters were used during training:
|
45 |
- learning_rate: 1e-06
|
46 |
+
- train_batch_size: 4
|
47 |
- eval_batch_size: 8
|
48 |
+
- seed: 4
|
49 |
- distributed_type: multi-GPU
|
50 |
- num_devices: 8
|
51 |
+
- gradient_accumulation_steps: 4
|
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 |
|
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 |
+
| 0.6209 | 0.21 | 100 | 0.6260 | -0.2545 | -0.6360 | 0.6953 | 0.3815 | -375.2259 | -329.0332 | 0.3909 | 0.3389 |
|
64 |
+
| 0.5447 | 0.42 | 200 | 0.5506 | -0.6231 | -1.4102 | 0.7852 | 0.7871 | -452.6489 | -365.8961 | 0.5763 | 0.5112 |
|
65 |
+
| 0.5257 | 0.63 | 300 | 0.5325 | -0.9411 | -1.9562 | 0.7617 | 1.0151 | -507.2468 | -397.6915 | 0.2916 | 0.2656 |
|
66 |
+
| 0.5016 | 0.84 | 400 | 0.5168 | -1.1370 | -2.2739 | 0.7930 | 1.1368 | -539.0118 | -417.2896 | 0.1301 | 0.1581 |
|
67 |
+
| 0.3557 | 1.05 | 500 | 0.5232 | -1.5956 | -3.0234 | 0.7852 | 1.4277 | -613.9626 | -463.1488 | 0.1606 | 0.1971 |
|
68 |
+
| 0.3459 | 1.26 | 600 | 0.5179 | -1.8408 | -3.1490 | 0.7969 | 1.3082 | -626.5206 | -487.6650 | 0.1677 | 0.2149 |
|
69 |
+
| 0.3321 | 1.47 | 700 | 0.5331 | -2.0696 | -3.5323 | 0.7891 | 1.4626 | -664.8507 | -510.5476 | -0.0690 | 0.0033 |
|
70 |
+
| 0.2983 | 1.67 | 800 | 0.5289 | -2.0385 | -3.4952 | 0.7930 | 1.4566 | -661.1429 | -507.4386 | -0.0746 | 0.0060 |
|
71 |
+
| 0.3235 | 1.88 | 900 | 0.5304 | -2.0877 | -3.5813 | 0.7969 | 1.4935 | -669.7546 | -512.3596 | -0.0805 | 0.0044 |
|
72 |
|
73 |
|
74 |
### 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": 0.44723546317538376,
|
4 |
+
"train_runtime": 8668.6976,
|
5 |
+
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 14.105,
|
7 |
+
"train_steps_per_second": 0.11
|
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 sha256:4400d5cc92103182c0288602258bcb6a357097c64fdd3c11599cc42caa1ffea8
|
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:d49e56f1ffb7e3b39edf0324f5f7b5fa8049cb6b5243bb8606d58cea6fd54f4c
|
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:be757ff962fe896c71369dfc072edc1b45a8a8170b10760f068e2d5c05ec06f0
|
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 sha256:4f1b4fe6c8278ecf71a36df42146155fd60f564232f4a0499a05cab556a07fb1
|
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": 0.44723546317538376,
|
4 |
+
"train_runtime": 8668.6976,
|
5 |
+
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 14.105,
|
7 |
+
"train_steps_per_second": 0.11
|
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:bf44d047df68bef9d42ea33d5bfa7fdecd645ea74f86b115b9c82ad801a096e6
|
3 |
size 6648
|