AmberYifan
commited on
Commit
•
35bbf69
1
Parent(s):
d045310
Model save
Browse files- README.md +24 -16
- all_results.json +4 -4
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- train_results.json +4 -4
- 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 is a fine-tuned version of [AmberYifan/mistral-safe-sft-full](https://huggingface.co/AmberYifan/mistral-safe-sft-full) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
-
- Rewards/real: 10.
|
20 |
-
- Rewards/generated: -5.
|
21 |
-
- Rewards/accuracies: 0
|
22 |
-
- Rewards/margins: 15.
|
23 |
-
- Logps/generated: -
|
24 |
-
- Logps/real: -111.
|
25 |
-
- Logits/generated: -2.
|
26 |
-
- Logits/real: -2.
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -59,13 +59,21 @@ The following hyperparameters were used during training:
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
|
61 |
|:-------------:|:------:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
|
70 |
|
71 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [AmberYifan/mistral-safe-sft-full](https://huggingface.co/AmberYifan/mistral-safe-sft-full) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2284
|
19 |
+
- Rewards/real: 10.1344
|
20 |
+
- Rewards/generated: -5.3158
|
21 |
+
- Rewards/accuracies: 1.0
|
22 |
+
- Rewards/margins: 15.4503
|
23 |
+
- Logps/generated: -131.8755
|
24 |
+
- Logps/real: -111.3366
|
25 |
+
- Logits/generated: -2.7694
|
26 |
+
- Logits/real: -2.7499
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
|
61 |
|:-------------:|:------:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
|
62 |
+
| 0.278 | 0.0640 | 100 | 0.2703 | 8.6366 | -3.4251 | 0.9922 | 12.0617 | -112.9675 | -126.3148 | -2.9055 | -2.8963 |
|
63 |
+
| 0.2283 | 0.1280 | 200 | 0.2438 | 9.5699 | -4.6271 | 0.9922 | 14.1970 | -124.9880 | -116.9817 | -2.8308 | -2.8192 |
|
64 |
+
| 0.2284 | 0.1919 | 300 | 0.2384 | 9.7849 | -5.0781 | 0.9922 | 14.8630 | -129.4981 | -114.8321 | -2.8396 | -2.8204 |
|
65 |
+
| 0.2154 | 0.2559 | 400 | 0.2361 | 9.8971 | -4.8914 | 0.9922 | 14.7885 | -127.6311 | -113.7101 | -2.8303 | -2.8085 |
|
66 |
+
| 0.2368 | 0.3199 | 500 | 0.2351 | 9.9762 | -5.0488 | 0.9922 | 15.0249 | -129.2045 | -112.9195 | -2.8228 | -2.8083 |
|
67 |
+
| 0.2065 | 0.3839 | 600 | 0.2346 | 10.0426 | -4.9610 | 0.9922 | 15.0035 | -128.3267 | -112.2554 | -2.8204 | -2.8086 |
|
68 |
+
| 0.2244 | 0.4479 | 700 | 0.2317 | 10.0417 | -5.1299 | 1.0 | 15.1716 | -130.0162 | -112.2640 | -2.8203 | -2.8076 |
|
69 |
+
| 0.2161 | 0.5118 | 800 | 0.2297 | 10.0737 | -5.0565 | 1.0 | 15.1303 | -129.2824 | -111.9440 | -2.8437 | -2.8337 |
|
70 |
+
| 0.2127 | 0.5758 | 900 | 0.2302 | 10.0913 | -5.0905 | 1.0 | 15.1818 | -129.6217 | -111.7683 | -2.8251 | -2.8150 |
|
71 |
+
| 0.2017 | 0.6398 | 1000 | 0.2298 | 10.1245 | -5.2627 | 1.0 | 15.3872 | -131.3441 | -111.4362 | -2.7955 | -2.7831 |
|
72 |
+
| 0.2152 | 0.7038 | 1100 | 0.2297 | 10.0889 | -5.3503 | 1.0 | 15.4392 | -132.2204 | -111.7925 | -2.7790 | -2.7609 |
|
73 |
+
| 0.2074 | 0.7678 | 1200 | 0.2298 | 10.1143 | -5.3204 | 1.0 | 15.4346 | -131.9209 | -111.5385 | -2.7919 | -2.7734 |
|
74 |
+
| 0.2107 | 0.8317 | 1300 | 0.2287 | 10.1349 | -5.3137 | 1.0 | 15.4486 | -131.8539 | -111.3324 | -2.7734 | -2.7524 |
|
75 |
+
| 0.1947 | 0.8957 | 1400 | 0.2288 | 10.1265 | -5.3252 | 1.0 | 15.4517 | -131.9686 | -111.4160 | -2.7803 | -2.7613 |
|
76 |
+
| 0.2056 | 0.9597 | 1500 | 0.2284 | 10.1344 | -5.3158 | 1.0 | 15.4503 | -131.8755 | -111.3366 | -2.7694 | -2.7499 |
|
77 |
|
78 |
|
79 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 50000,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.2371997828675781,
|
5 |
+
"train_runtime": 22626.3768,
|
6 |
"train_samples": 50000,
|
7 |
+
"train_samples_per_second": 2.21,
|
8 |
+
"train_steps_per_second": 0.069
|
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:f8a1942bd55858075b25eb0470befcb6e04ff14f6348397bd2f4fd3752d7c466
|
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 sha256:91ed86f263a377ae2dabfe1bbae67be544df8a898ded8d30fd221a6b97796387
|
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 sha256:34bed1a0fb09ea859275db026a93e7fb10f9c943cbd229730a1c7bbb68edc72b
|
3 |
size 4540516344
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 50000,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.2371997828675781,
|
5 |
+
"train_runtime": 22626.3768,
|
6 |
"train_samples": 50000,
|
7 |
+
"train_samples_per_second": 2.21,
|
8 |
+
"train_steps_per_second": 0.069
|
9 |
}
|
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 6392
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef5dc1a07b1f0e5b9bb9903ddc99a2a4669946e91f2f63904650bc346746a90b
|
3 |
size 6392
|