RAIJAY/NBERT_2
Browse files- README.md +21 -16
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
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-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen:
|
23 |
-
- Rewards/rejected: -
|
24 |
-
- Rewards/accuracies:
|
25 |
-
- Rewards/margins:
|
26 |
-
- Logps/rejected: -
|
27 |
-
- Logps/chosen: -
|
28 |
-
- Logits/rejected: -
|
29 |
-
- Logits/chosen: -
|
30 |
|
31 |
## Model description
|
32 |
|
@@ -54,16 +54,21 @@ The following hyperparameters were used during training:
|
|
54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
- lr_scheduler_type: linear
|
56 |
- lr_scheduler_warmup_steps: 2
|
57 |
-
- training_steps:
|
58 |
|
59 |
### Training results
|
60 |
|
61 |
-
| Training Loss | Epoch | Step
|
62 |
-
|
63 |
-
|
|
64 |
-
|
|
65 |
-
| 0.
|
66 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
|
69 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0229
|
22 |
+
- Rewards/chosen: -740.3076
|
23 |
+
- Rewards/rejected: -1059.6395
|
24 |
+
- Rewards/accuracies: 0.9988
|
25 |
+
- Rewards/margins: 319.3320
|
26 |
+
- Logps/rejected: -10817.7158
|
27 |
+
- Logps/chosen: -7838.3896
|
28 |
+
- Logits/rejected: -32.6170
|
29 |
+
- Logits/chosen: -26.3151
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
- lr_scheduler_type: linear
|
56 |
- lr_scheduler_warmup_steps: 2
|
57 |
+
- training_steps: 25806
|
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 |
+
| 37.7926 | 0.67 | 2867 | 2.8916 | -149.7567 | -197.0506 | 0.9359 | 47.2939 | -2191.8269 | -1932.8804 | 38.0669 | 4.1036 |
|
64 |
+
| 84.7229 | 1.33 | 5734 | 2.0247 | -327.4202 | -450.9706 | 0.9656 | 123.5504 | -4731.0264 | -3709.5146 | -17.6232 | -16.2614 |
|
65 |
+
| 0.4302 | 2.0 | 8601 | 0.2490 | -391.4300 | -536.8747 | 0.9923 | 145.4447 | -5590.0679 | -4349.6123 | -13.6537 | -12.7337 |
|
66 |
+
| 0.6952 | 2.67 | 11468 | 0.0587 | -606.4489 | -775.4740 | 0.9970 | 169.0251 | -7976.0605 | -6499.8027 | 8.1646 | -0.2018 |
|
67 |
+
| 0.2119 | 3.33 | 14335 | 0.2843 | -641.6364 | -925.0908 | 0.9907 | 283.4543 | -9472.2285 | -6851.6772 | -11.2088 | -13.0496 |
|
68 |
+
| 0.129 | 4.0 | 17202 | 0.1065 | -706.7910 | -1019.4420 | 0.9958 | 312.6511 | -10415.7412 | -7503.2227 | 29.4650 | 10.0032 |
|
69 |
+
| 0.1046 | 4.67 | 20069 | 0.1005 | -758.2514 | -1105.3041 | 0.9977 | 347.0525 | -11274.3594 | -8017.8281 | -37.3526 | -28.3912 |
|
70 |
+
| 0.0656 | 5.33 | 22936 | 0.0241 | -790.2775 | -1078.3324 | 0.9986 | 288.0548 | -11004.6445 | -8338.0889 | -7.1017 | -13.6854 |
|
71 |
+
| 0.0 | 6.0 | 25803 | 0.0229 | -740.3076 | -1059.6395 | 0.9988 | 319.3320 | -10817.7158 | -7838.3896 | -32.6170 | -26.3151 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,14 +19,14 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"k_proj",
|
23 |
-
"v_proj",
|
24 |
-
"o_proj",
|
25 |
"down_proj",
|
26 |
-
"
|
27 |
"lm_head",
|
28 |
"up_proj",
|
29 |
-
"
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM"
|
32 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
|
|
22 |
"down_proj",
|
23 |
+
"gate_proj",
|
24 |
"lm_head",
|
25 |
"up_proj",
|
26 |
+
"q_proj",
|
27 |
+
"v_proj",
|
28 |
+
"o_proj",
|
29 |
+
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM"
|
32 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 609389712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae0f871bb072a5dd8c81e42087e6de9788c7501cd0d3f965e5c58e8158f835cd
|
3 |
size 609389712
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:068c33107d83952fcc7d63d650e0d78843ebe13a25b623183abfa4c8a25c5396
|
3 |
size 4219
|