Model save
Browse files- README.md +47 -47
- adapter_model.safetensors +1 -1
- all_results.json +4 -4
- runs/Apr05_17-15-39_gpu-1/events.out.tfevents.1712305026.gpu-1.1152924.0 +2 -2
- train_results.json +4 -4
- trainer_state.json +0 -0
README.md
CHANGED
@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen: -2.
|
23 |
-
- Rewards/rejected: -3.
|
24 |
-
- Rewards/accuracies: 0.
|
25 |
-
- Rewards/margins: 1.
|
26 |
-
- Logps/rejected: -635.
|
27 |
-
- Logps/chosen: -
|
28 |
-
- Logits/rejected: -1.
|
29 |
-
- Logits/chosen: -1.
|
30 |
|
31 |
## Model description
|
32 |
|
@@ -61,44 +61,44 @@ The following hyperparameters were used during training:
|
|
61 |
|
62 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
63 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
|
103 |
|
104 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4864
|
22 |
+
- Rewards/chosen: -2.8126
|
23 |
+
- Rewards/rejected: -3.9101
|
24 |
+
- Rewards/accuracies: 0.7395
|
25 |
+
- Rewards/margins: 1.0975
|
26 |
+
- Logps/rejected: -635.6184
|
27 |
+
- Logps/chosen: -545.9131
|
28 |
+
- Logits/rejected: -1.1317
|
29 |
+
- Logits/chosen: -1.2524
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
61 |
|
62 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
63 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
64 |
+
| 0.6821 | 0.03 | 100 | 0.6821 | 0.0498 | 0.0267 | 0.6565 | 0.0231 | -241.9392 | -259.6706 | -1.9557 | -2.0951 |
|
65 |
+
| 0.6496 | 0.05 | 200 | 0.6487 | -0.0543 | -0.1608 | 0.6810 | 0.1065 | -260.6906 | -270.0797 | -1.9313 | -2.0680 |
|
66 |
+
| 0.6042 | 0.08 | 300 | 0.6216 | -0.3050 | -0.5140 | 0.6730 | 0.2090 | -296.0115 | -295.1514 | -1.8895 | -2.0229 |
|
67 |
+
| 0.6218 | 0.1 | 400 | 0.5940 | -0.6189 | -0.9584 | 0.6810 | 0.3395 | -340.4455 | -326.5407 | -1.8155 | -1.9431 |
|
68 |
+
| 0.5674 | 0.13 | 500 | 0.5780 | -1.5729 | -2.0527 | 0.7040 | 0.4797 | -449.8770 | -421.9457 | -1.6637 | -1.7893 |
|
69 |
+
| 0.5632 | 0.16 | 600 | 0.5649 | -0.7810 | -1.2808 | 0.7040 | 0.4999 | -372.6913 | -342.7494 | -1.6489 | -1.7786 |
|
70 |
+
| 0.5331 | 0.18 | 700 | 0.5607 | -1.9088 | -2.6807 | 0.7060 | 0.7719 | -512.6751 | -455.5275 | -1.4691 | -1.5919 |
|
71 |
+
| 0.4996 | 0.21 | 800 | 0.5433 | -1.4500 | -2.1596 | 0.7070 | 0.7096 | -460.5685 | -409.6544 | -1.5461 | -1.6710 |
|
72 |
+
| 0.514 | 0.24 | 900 | 0.5440 | -1.2657 | -1.9170 | 0.7190 | 0.6512 | -436.3041 | -391.2230 | -1.5014 | -1.6214 |
|
73 |
+
| 0.5468 | 0.26 | 1000 | 0.5418 | -1.3702 | -2.0703 | 0.7175 | 0.7001 | -451.6408 | -401.6767 | -1.4449 | -1.5656 |
|
74 |
+
| 0.569 | 0.29 | 1100 | 0.5299 | -1.1397 | -1.8623 | 0.7210 | 0.7227 | -430.8414 | -378.6177 | -1.4278 | -1.5524 |
|
75 |
+
| 0.5732 | 0.31 | 1200 | 0.5185 | -1.1057 | -1.8287 | 0.7250 | 0.7231 | -427.4810 | -375.2183 | -1.3596 | -1.4804 |
|
76 |
+
| 0.5332 | 0.34 | 1300 | 0.5315 | -2.1367 | -3.0509 | 0.7240 | 0.9142 | -549.7025 | -478.3255 | -1.1977 | -1.3072 |
|
77 |
+
| 0.5431 | 0.37 | 1400 | 0.5211 | -1.2563 | -2.0974 | 0.7260 | 0.8411 | -454.3522 | -390.2846 | -1.3130 | -1.4314 |
|
78 |
+
| 0.4862 | 0.39 | 1500 | 0.5162 | -1.3677 | -2.2741 | 0.7355 | 0.9063 | -472.0146 | -401.4262 | -1.2795 | -1.4015 |
|
79 |
+
| 0.5858 | 0.42 | 1600 | 0.5073 | -1.8100 | -2.6996 | 0.7365 | 0.8896 | -514.5671 | -445.6515 | -1.1534 | -1.2718 |
|
80 |
+
| 0.5147 | 0.44 | 1700 | 0.5000 | -2.2681 | -3.2167 | 0.7340 | 0.9486 | -566.2829 | -491.4621 | -1.1468 | -1.2691 |
|
81 |
+
| 0.4809 | 0.47 | 1800 | 0.5022 | -2.9278 | -3.9903 | 0.7405 | 1.0625 | -643.6409 | -557.4312 | -1.0617 | -1.1786 |
|
82 |
+
| 0.46 | 0.5 | 1900 | 0.5003 | -2.4333 | -3.5014 | 0.7355 | 1.0681 | -594.7523 | -507.9823 | -1.1041 | -1.2253 |
|
83 |
+
| 0.477 | 0.52 | 2000 | 0.4989 | -2.3912 | -3.3897 | 0.7345 | 0.9985 | -583.5771 | -503.7692 | -1.1185 | -1.2392 |
|
84 |
+
| 0.5068 | 0.55 | 2100 | 0.4939 | -2.4778 | -3.4672 | 0.7430 | 0.9894 | -591.3240 | -512.4297 | -1.1255 | -1.2462 |
|
85 |
+
| 0.4832 | 0.58 | 2200 | 0.4925 | -2.1250 | -3.0518 | 0.7425 | 0.9268 | -549.7868 | -477.1522 | -1.1670 | -1.2899 |
|
86 |
+
| 0.4731 | 0.6 | 2300 | 0.4923 | -2.8792 | -4.0084 | 0.7435 | 1.1291 | -645.4448 | -552.5742 | -1.0953 | -1.2155 |
|
87 |
+
| 0.4782 | 0.63 | 2400 | 0.4923 | -2.8503 | -3.9248 | 0.7420 | 1.0745 | -637.0914 | -549.6804 | -1.0794 | -1.1978 |
|
88 |
+
| 0.4983 | 0.65 | 2500 | 0.4906 | -2.5713 | -3.6558 | 0.7410 | 1.0845 | -610.1890 | -521.7778 | -1.1292 | -1.2522 |
|
89 |
+
| 0.4746 | 0.68 | 2600 | 0.4947 | -2.5857 | -3.7233 | 0.7365 | 1.1375 | -616.9340 | -523.2234 | -1.1267 | -1.2491 |
|
90 |
+
| 0.514 | 0.71 | 2700 | 0.4924 | -2.6975 | -3.8049 | 0.7355 | 1.1074 | -625.0958 | -534.3994 | -1.1248 | -1.2463 |
|
91 |
+
| 0.4662 | 0.73 | 2800 | 0.4899 | -2.8300 | -3.9668 | 0.7380 | 1.1368 | -641.2913 | -547.6557 | -1.1134 | -1.2345 |
|
92 |
+
| 0.5111 | 0.76 | 2900 | 0.4873 | -2.9392 | -4.0635 | 0.7405 | 1.1244 | -650.9627 | -558.5706 | -1.1188 | -1.2396 |
|
93 |
+
| 0.4758 | 0.79 | 3000 | 0.4866 | -2.8621 | -3.9416 | 0.7410 | 1.0795 | -638.7724 | -550.8655 | -1.1318 | -1.2526 |
|
94 |
+
| 0.4908 | 0.81 | 3100 | 0.4869 | -2.8503 | -3.9411 | 0.7420 | 1.0908 | -638.7193 | -549.6837 | -1.1347 | -1.2555 |
|
95 |
+
| 0.4641 | 0.84 | 3200 | 0.4866 | -2.8111 | -3.8990 | 0.7405 | 1.0878 | -634.5079 | -545.7666 | -1.1347 | -1.2554 |
|
96 |
+
| 0.5096 | 0.86 | 3300 | 0.4864 | -2.7992 | -3.8880 | 0.7395 | 1.0887 | -633.4041 | -544.5740 | -1.1379 | -1.2586 |
|
97 |
+
| 0.455 | 0.89 | 3400 | 0.4866 | -2.8126 | -3.9082 | 0.7395 | 1.0956 | -635.4322 | -545.9153 | -1.1336 | -1.2544 |
|
98 |
+
| 0.5262 | 0.92 | 3500 | 0.4864 | -2.8110 | -3.9081 | 0.7410 | 1.0971 | -635.4207 | -545.7535 | -1.1342 | -1.2550 |
|
99 |
+
| 0.466 | 0.94 | 3600 | 0.4866 | -2.8133 | -3.9106 | 0.7400 | 1.0973 | -635.6727 | -545.9836 | -1.1347 | -1.2555 |
|
100 |
+
| 0.4945 | 0.97 | 3700 | 0.4864 | -2.8101 | -3.9080 | 0.7400 | 1.0979 | -635.4124 | -545.6666 | -1.1321 | -1.2528 |
|
101 |
+
| 0.5013 | 0.99 | 3800 | 0.4864 | -2.8126 | -3.9101 | 0.7395 | 1.0975 | -635.6184 | -545.9131 | -1.1317 | -1.2524 |
|
102 |
|
103 |
|
104 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671150064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c3b8d704741cd454e7912199cf0a41e3db684cabc59d2f2d23adac95c72384
|
3 |
size 671150064
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 61134,
|
6 |
-
"train_samples_per_second": 1.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.5238101308459981,
|
4 |
+
"train_runtime": 42749.2467,
|
5 |
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 1.43,
|
7 |
+
"train_steps_per_second": 0.089
|
8 |
}
|
runs/Apr05_17-15-39_gpu-1/events.out.tfevents.1712305026.gpu-1.1152924.0
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:ecdd11513212c08010d27497d35182e2270f5b82dd52e55199821a40bb39e402
|
3 |
+
size 296998
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 61134,
|
6 |
-
"train_samples_per_second": 1.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.5238101308459981,
|
4 |
+
"train_runtime": 42749.2467,
|
5 |
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 1.43,
|
7 |
+
"train_steps_per_second": 0.089
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|