Model save
Browse files- README.md +20 -20
- all_results.json +5 -5
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- runs/May10_12-21-48_n136-098-158/events.out.tfevents.1715315002.n136-098-158.1854935.0 +2 -2
- train_results.json +5 -5
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model was trained from scratch on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.
|
19 |
-
- Rewards/chosen: -
|
20 |
-
- Rewards/rejected: -
|
21 |
-
- Rewards/accuracies: 0.
|
22 |
-
- Rewards/margins:
|
23 |
-
- Logps/rejected: -
|
24 |
-
- Logps/chosen: -
|
25 |
-
- Logits/rejected: -
|
26 |
-
- Logits/chosen: -
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -58,17 +58,17 @@ The following hyperparameters were used during training:
|
|
58 |
|
59 |
### Training results
|
60 |
|
61 |
-
| Training Loss | Epoch | Step |
|
62 |
-
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
15 |
|
16 |
This model was trained from scratch on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.3947
|
19 |
+
- Rewards/chosen: -2.4314
|
20 |
+
- Rewards/rejected: -2.0023
|
21 |
+
- Rewards/accuracies: 0.3867
|
22 |
+
- Rewards/margins: -0.4292
|
23 |
+
- Logps/rejected: -517.7516
|
24 |
+
- Logps/chosen: -554.9180
|
25 |
+
- Logits/rejected: -1.0823
|
26 |
+
- Logits/chosen: -1.1239
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
58 |
|
59 |
### Training results
|
60 |
|
61 |
+
| Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
|
62 |
+
|:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
|
63 |
+
| 0.3047 | 0.1 | 100 | -2.4405 | -2.3863 | -361.0801 | -337.7748 | 0.8551 | 0.3203 | -0.4930 | -0.2905 | -0.2025 |
|
64 |
+
| 0.1861 | 0.21 | 200 | -1.5418 | -1.5107 | -450.2716 | -421.0934 | 1.0495 | 0.3867 | -1.3850 | -0.3493 | -1.0357 |
|
65 |
+
| 0.1608 | 0.31 | 300 | -1.4367 | -1.4022 | -454.9446 | -422.9684 | 1.0910 | 0.3945 | -1.4317 | -0.3772 | -1.0544 |
|
66 |
+
| 0.1368 | 0.42 | 400 | -1.0538 | -1.0131 | -520.1699 | -479.6456 | 1.3010 | 0.4102 | -2.0839 | -0.4627 | -1.6212 |
|
67 |
+
| 0.1364 | 0.52 | 500 | -1.6466 | -1.6090 | -470.0934 | -430.8614 | 1.1773 | 0.3711 | -1.5832 | -0.4498 | -1.1334 |
|
68 |
+
| 0.1223 | 0.63 | 600 | 1.3206 | -2.2971 | -1.8297 | 0.4141 | -0.4674 | -500.4930 | -541.4883 | -1.1541 | -1.1880 |
|
69 |
+
| 0.0971 | 0.73 | 700 | 1.4638 | -2.6554 | -2.1594 | 0.3906 | -0.4959 | -533.4667 | -577.3128 | -0.9392 | -0.9712 |
|
70 |
+
| 0.1035 | 0.84 | 800 | 1.4475 | -2.5761 | -2.1538 | 0.3945 | -0.4222 | -532.9068 | -569.3817 | -0.8902 | -0.9232 |
|
71 |
+
| 0.088 | 0.94 | 900 | 1.3947 | -2.4314 | -2.0023 | 0.3867 | -0.4292 | -517.7516 | -554.9180 | -1.0823 | -1.1239 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
all_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": 0.05187356284775659,
|
4 |
+
"train_runtime": 7314.4586,
|
5 |
+
"train_samples": 122268,
|
6 |
+
"train_samples_per_second": 16.716,
|
7 |
+
"train_steps_per_second": 0.131
|
8 |
}
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943178720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:938e0d524d2c5b738205f45cbd32d084ef09b48fc55b42d2357ec2767acdf6c6
|
3 |
size 4943178720
|
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 sha256:1ec78470671379c923d72d3be323be44ae390376154e5d9fd23e55a6f9be5d44
|
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 4540532728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e68bdcd164f3a46f36753fb22642732b303167d2c92a5668db1be3f302bf4b44
|
3 |
size 4540532728
|
runs/May10_12-21-48_n136-098-158/events.out.tfevents.1715315002.n136-098-158.1854935.0
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 sha256:12c7b7fa838a8b64c129bfdfbe99a6f5a620e4b04254e73d65b5d5412d77b2d2
|
3 |
+
size 39189
|
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": 0.05187356284775659,
|
4 |
+
"train_runtime": 7314.4586,
|
5 |
+
"train_samples": 122268,
|
6 |
+
"train_samples_per_second": 16.716,
|
7 |
+
"train_steps_per_second": 0.131
|
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 6264
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ee00489c1463fae472326de1af05f14960d5729e1f2cab6ea21d656cab52f1b
|
3 |
size 6264
|