Model save
Browse files
README.md
CHANGED
@@ -5,7 +5,7 @@ tags:
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
8 |
-
base_model:
|
9 |
model-index:
|
10 |
- name: zephyr-7b-dpo-qlora
|
11 |
results: []
|
@@ -16,17 +16,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# zephyr-7b-dpo-qlora
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen: -
|
23 |
-
- Rewards/rejected: -
|
24 |
-
- Rewards/accuracies: 0.
|
25 |
-
- Rewards/margins:
|
26 |
-
- Logps/rejected: -
|
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
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
8 |
+
base_model: alignment-handbook/zephyr-7b-sft-full
|
9 |
model-index:
|
10 |
- name: zephyr-7b-dpo-qlora
|
11 |
results: []
|
|
|
16 |
|
17 |
# zephyr-7b-dpo-qlora
|
18 |
|
19 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5056
|
22 |
+
- Rewards/chosen: -1.4058
|
23 |
+
- Rewards/rejected: -2.2921
|
24 |
+
- Rewards/accuracies: 0.7345
|
25 |
+
- Rewards/margins: 0.8863
|
26 |
+
- Logps/rejected: -492.4564
|
27 |
+
- Logps/chosen: -425.7130
|
28 |
+
- Logits/rejected: -1.8131
|
29 |
+
- Logits/chosen: -1.9265
|
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 |
+
| 0.6896 | 0.03 | 100 | 0.6884 | 0.0072 | -0.0023 | 0.6745 | 0.0096 | -263.4773 | -284.4093 | -2.5586 | -2.6909 |
|
65 |
+
| 0.6699 | 0.05 | 200 | 0.6726 | 0.0082 | -0.0359 | 0.6895 | 0.0441 | -266.8299 | -284.3103 | -2.5495 | -2.6813 |
|
66 |
+
| 0.636 | 0.08 | 300 | 0.6466 | -0.0002 | -0.1125 | 0.6780 | 0.1123 | -274.4987 | -285.1534 | -2.5520 | -2.6823 |
|
67 |
+
| 0.6312 | 0.1 | 400 | 0.6191 | -0.2138 | -0.4222 | 0.6805 | 0.2084 | -305.4655 | -306.5131 | -2.5251 | -2.6530 |
|
68 |
+
| 0.5918 | 0.13 | 500 | 0.6031 | -0.2627 | -0.5412 | 0.6880 | 0.2785 | -317.3649 | -311.4058 | -2.5298 | -2.6575 |
|
69 |
+
| 0.6012 | 0.16 | 600 | 0.5928 | -0.5129 | -0.8554 | 0.6935 | 0.3424 | -348.7829 | -336.4283 | -2.5443 | -2.6737 |
|
70 |
+
| 0.5823 | 0.18 | 700 | 0.5811 | -0.5775 | -1.0207 | 0.7000 | 0.4432 | -365.3115 | -342.8825 | -2.3446 | -2.4662 |
|
71 |
+
| 0.5502 | 0.21 | 800 | 0.5688 | -0.5710 | -1.0329 | 0.7040 | 0.4619 | -366.5324 | -342.2334 | -2.3173 | -2.4395 |
|
72 |
+
| 0.551 | 0.24 | 900 | 0.5723 | -0.5585 | -1.0146 | 0.7100 | 0.4561 | -364.7085 | -340.9870 | -2.2573 | -2.3767 |
|
73 |
+
| 0.5684 | 0.26 | 1000 | 0.5602 | -0.7542 | -1.3111 | 0.7070 | 0.5569 | -394.3551 | -360.5555 | -2.2283 | -2.3464 |
|
74 |
+
| 0.5722 | 0.29 | 1100 | 0.5429 | -0.7936 | -1.4574 | 0.7240 | 0.6638 | -408.9803 | -364.4904 | -2.0677 | -2.1820 |
|
75 |
+
| 0.5866 | 0.31 | 1200 | 0.5338 | -1.0463 | -1.7337 | 0.7205 | 0.6874 | -436.6128 | -389.7662 | -2.0249 | -2.1388 |
|
76 |
+
| 0.5659 | 0.34 | 1300 | 0.5310 | -0.8607 | -1.5398 | 0.7310 | 0.6792 | -417.2296 | -371.2006 | -1.9893 | -2.1049 |
|
77 |
+
| 0.5625 | 0.37 | 1400 | 0.5295 | -0.7999 | -1.5056 | 0.7215 | 0.7058 | -413.8092 | -365.1206 | -1.9254 | -2.0391 |
|
78 |
+
| 0.4575 | 0.39 | 1500 | 0.5266 | -1.1455 | -1.9646 | 0.7260 | 0.8191 | -459.7086 | -399.6889 | -1.9105 | -2.0252 |
|
79 |
+
| 0.5855 | 0.42 | 1600 | 0.5227 | -1.0359 | -1.7628 | 0.7345 | 0.7269 | -439.5246 | -388.7278 | -1.9276 | -2.0403 |
|
80 |
+
| 0.5333 | 0.44 | 1700 | 0.5155 | -1.1618 | -1.9731 | 0.7310 | 0.8113 | -460.5566 | -401.3148 | -1.9572 | -2.0732 |
|
81 |
+
| 0.5055 | 0.47 | 1800 | 0.5181 | -1.1105 | -1.8968 | 0.7330 | 0.7863 | -452.9257 | -396.1870 | -1.9572 | -2.0727 |
|
82 |
+
| 0.4687 | 0.5 | 1900 | 0.5198 | -1.4078 | -2.3064 | 0.7290 | 0.8986 | -493.8867 | -425.9163 | -1.8519 | -1.9678 |
|
83 |
+
| 0.4936 | 0.52 | 2000 | 0.5123 | -1.4097 | -2.2536 | 0.7290 | 0.8438 | -488.6001 | -426.1056 | -1.8371 | -1.9508 |
|
84 |
+
| 0.5058 | 0.55 | 2100 | 0.5121 | -1.4030 | -2.2804 | 0.7320 | 0.8773 | -491.2808 | -425.4353 | -1.8156 | -1.9302 |
|
85 |
+
| 0.491 | 0.58 | 2200 | 0.5102 | -1.2883 | -2.1172 | 0.7300 | 0.8289 | -474.9657 | -413.9656 | -1.8893 | -2.0053 |
|
86 |
+
| 0.4923 | 0.6 | 2300 | 0.5107 | -1.2460 | -2.0925 | 0.7320 | 0.8465 | -472.4916 | -409.7295 | -1.8949 | -2.0101 |
|
87 |
+
| 0.4718 | 0.63 | 2400 | 0.5093 | -1.3443 | -2.1905 | 0.7265 | 0.8462 | -482.2936 | -419.5653 | -1.8618 | -1.9757 |
|
88 |
+
| 0.5187 | 0.65 | 2500 | 0.5103 | -1.3233 | -2.2095 | 0.7285 | 0.8862 | -484.1988 | -417.4668 | -1.8641 | -1.9796 |
|
89 |
+
| 0.5025 | 0.68 | 2600 | 0.5115 | -1.2910 | -2.1842 | 0.7315 | 0.8932 | -481.6620 | -414.2359 | -1.8388 | -1.9538 |
|
90 |
+
| 0.4946 | 0.71 | 2700 | 0.5094 | -1.3454 | -2.2424 | 0.7300 | 0.8970 | -487.4804 | -419.6713 | -1.8200 | -1.9339 |
|
91 |
+
| 0.5054 | 0.73 | 2800 | 0.5085 | -1.4083 | -2.3252 | 0.7320 | 0.9169 | -495.7629 | -425.9614 | -1.8042 | -1.9180 |
|
92 |
+
| 0.5159 | 0.76 | 2900 | 0.5066 | -1.3467 | -2.2328 | 0.7320 | 0.8861 | -486.5227 | -419.8022 | -1.8193 | -1.9330 |
|
93 |
+
| 0.4671 | 0.79 | 3000 | 0.5062 | -1.4194 | -2.3064 | 0.7325 | 0.8870 | -493.8865 | -427.0751 | -1.8140 | -1.9274 |
|
94 |
+
| 0.4864 | 0.81 | 3100 | 0.5059 | -1.4248 | -2.3084 | 0.7330 | 0.8836 | -494.0863 | -427.6172 | -1.8158 | -1.9291 |
|
95 |
+
| 0.5101 | 0.84 | 3200 | 0.5056 | -1.4159 | -2.2981 | 0.7340 | 0.8821 | -493.0526 | -426.7279 | -1.8167 | -1.9300 |
|
96 |
+
| 0.5317 | 0.86 | 3300 | 0.5056 | -1.4029 | -2.2863 | 0.7355 | 0.8834 | -491.8742 | -425.4280 | -1.8139 | -1.9273 |
|
97 |
+
| 0.4668 | 0.89 | 3400 | 0.5055 | -1.4064 | -2.2921 | 0.7350 | 0.8857 | -492.4527 | -425.7719 | -1.8132 | -1.9266 |
|
98 |
+
| 0.5671 | 0.92 | 3500 | 0.5056 | -1.4036 | -2.2899 | 0.7345 | 0.8863 | -492.2395 | -425.4986 | -1.8158 | -1.9291 |
|
99 |
+
| 0.4708 | 0.94 | 3600 | 0.5056 | -1.4050 | -2.2912 | 0.7345 | 0.8862 | -492.3603 | -425.6342 | -1.8127 | -1.9261 |
|
100 |
+
| 0.4904 | 0.97 | 3700 | 0.5054 | -1.4047 | -2.2913 | 0.7355 | 0.8866 | -492.3736 | -425.6043 | -1.8155 | -1.9289 |
|
101 |
+
| 0.5001 | 0.99 | 3800 | 0.5056 | -1.4058 | -2.2921 | 0.7345 | 0.8863 | -492.4564 | -425.7130 | -1.8131 | -1.9265 |
|
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:e237784759ae82d05007c64de0d6b6905c61fbdaed669850c91f6ca78555089f
|
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": 0.
|
7 |
"train_steps_per_second": 0.046
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.5390157630246398,
|
4 |
+
"train_runtime": 82744.187,
|
5 |
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 0.739,
|
7 |
"train_steps_per_second": 0.046
|
8 |
}
|
runs/Apr05_19-58-41_allennlp-cirrascale-50.reviz.ai2.in/events.out.tfevents.1712372721.allennlp-cirrascale-50.reviz.ai2.in.49327.0
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 sha256:9e0c1bce4cedb7cff0133d1cbff2ee9d404c387bcc76b522de150a4ab7862798
|
3 |
+
size 297064
|
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": 0.
|
7 |
"train_steps_per_second": 0.046
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.5390157630246398,
|
4 |
+
"train_runtime": 82744.187,
|
5 |
"train_samples": 61134,
|
6 |
+
"train_samples_per_second": 0.739,
|
7 |
"train_steps_per_second": 0.046
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|