Model save
Browse files- README.md +41 -44
- all_results.json +4 -17
- train_results.json +4 -4
- trainer_state.json +0 -0
README.md
CHANGED
@@ -1,10 +1,7 @@
|
|
1 |
---
|
2 |
base_model: TII-Frontier-Team/falcon3-3b-instruct
|
3 |
-
datasets:
|
4 |
-
- TII-Frontier-Team/Reasoning_DPO
|
5 |
library_name: peft
|
6 |
tags:
|
7 |
-
- alignment-handbook
|
8 |
- trl
|
9 |
- dpo
|
10 |
- generated_from_trainer
|
@@ -18,17 +15,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# zephyr-7b-dpo-qlora
|
20 |
|
21 |
-
This model is a fine-tuned version of [TII-Frontier-Team/
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Rewards/chosen: -4.
|
25 |
-
- Rewards/rejected: -10.
|
26 |
-
- Rewards/accuracies: 0.
|
27 |
-
- Rewards/margins: 5.
|
28 |
-
- Logps/rejected: -
|
29 |
-
- Logps/chosen: -
|
30 |
-
- Logits/rejected:
|
31 |
-
- Logits/chosen: 2.
|
32 |
|
33 |
## Model description
|
34 |
|
@@ -65,37 +62,37 @@ The following hyperparameters were used during training:
|
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
67 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
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 |
|
100 |
|
101 |
### Framework versions
|
|
|
1 |
---
|
2 |
base_model: TII-Frontier-Team/falcon3-3b-instruct
|
|
|
|
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- generated_from_trainer
|
|
|
15 |
|
16 |
# zephyr-7b-dpo-qlora
|
17 |
|
18 |
+
This model is a fine-tuned version of [TII-Frontier-Team/falcon3-3b-instruct](https://huggingface.co/TII-Frontier-Team/falcon3-3b-instruct) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0299
|
21 |
+
- Rewards/chosen: -4.6289
|
22 |
+
- Rewards/rejected: -10.4404
|
23 |
+
- Rewards/accuracies: 0.9302
|
24 |
+
- Rewards/margins: 5.8116
|
25 |
+
- Logps/rejected: -1079.9603
|
26 |
+
- Logps/chosen: -495.6860
|
27 |
+
- Logits/rejected: 2.0537
|
28 |
+
- Logits/chosen: 2.2623
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
+
| 0.6913 | 0.0315 | 100 | 0.6911 | 0.0007 | -0.0036 | 0.6220 | 0.0042 | -36.2718 | -32.7285 | -1.6824 | -1.6348 |
|
66 |
+
| 0.6742 | 0.0629 | 200 | 0.6751 | 0.0003 | -0.0454 | 0.6276 | 0.0458 | -40.4596 | -32.7631 | -1.5097 | -1.4586 |
|
67 |
+
| 0.6081 | 0.0944 | 300 | 0.5872 | -0.5193 | -0.8644 | 0.6619 | 0.3451 | -122.3552 | -84.7303 | -0.4701 | -0.3830 |
|
68 |
+
| 0.4463 | 0.1258 | 400 | 0.3978 | -2.0312 | -3.2212 | 0.7190 | 1.1900 | -358.0407 | -235.9217 | -0.3673 | -0.2101 |
|
69 |
+
| 0.3548 | 0.1573 | 500 | 0.3048 | -2.5142 | -4.1605 | 0.7698 | 1.6464 | -451.9689 | -284.2137 | 0.4417 | 0.6033 |
|
70 |
+
| 0.3014 | 0.1887 | 600 | 0.2395 | -2.7662 | -4.8033 | 0.7963 | 2.0371 | -516.2451 | -309.4138 | 1.0026 | 1.1670 |
|
71 |
+
| 0.25 | 0.2202 | 700 | 0.1989 | -3.1039 | -5.4194 | 0.8235 | 2.3155 | -577.8538 | -343.1828 | 1.3421 | 1.5051 |
|
72 |
+
| 0.2163 | 0.2517 | 800 | 0.1564 | -3.4535 | -6.3881 | 0.8369 | 2.9346 | -674.7255 | -378.1511 | 1.8084 | 1.9697 |
|
73 |
+
| 0.178 | 0.2831 | 900 | 0.1349 | -3.4355 | -6.5411 | 0.8586 | 3.1056 | -690.0276 | -376.3503 | 1.7688 | 1.9492 |
|
74 |
+
| 0.1736 | 0.3146 | 1000 | 0.1127 | -3.5471 | -6.9599 | 0.8668 | 3.4128 | -731.9055 | -387.5069 | 2.0848 | 2.2440 |
|
75 |
+
| 0.1474 | 0.3460 | 1100 | 0.0982 | -3.6177 | -7.2322 | 0.8799 | 3.6145 | -759.1403 | -394.5700 | 1.8280 | 2.0076 |
|
76 |
+
| 0.1382 | 0.3775 | 1200 | 0.0819 | -4.3123 | -8.3603 | 0.8862 | 4.0480 | -871.9455 | -464.0287 | 2.0966 | 2.2833 |
|
77 |
+
| 0.1133 | 0.4089 | 1300 | 0.0714 | -4.0671 | -8.3309 | 0.8955 | 4.2638 | -869.0029 | -439.5055 | 1.9082 | 2.1044 |
|
78 |
+
| 0.1209 | 0.4404 | 1400 | 0.0634 | -4.8366 | -9.4739 | 0.8933 | 4.6374 | -983.3081 | -516.4533 | 2.0574 | 2.2678 |
|
79 |
+
| 0.1057 | 0.4718 | 1500 | 0.0575 | -4.1835 | -8.8581 | 0.9019 | 4.6746 | -921.7241 | -451.1488 | 2.0907 | 2.2780 |
|
80 |
+
| 0.1057 | 0.5033 | 1600 | 0.0536 | -4.2093 | -8.9250 | 0.9131 | 4.7157 | -928.4156 | -453.7231 | 2.0198 | 2.2136 |
|
81 |
+
| 0.0881 | 0.5348 | 1700 | 0.0490 | -4.4577 | -9.3694 | 0.9101 | 4.9118 | -972.8605 | -478.5644 | 1.8760 | 2.0804 |
|
82 |
+
| 0.0847 | 0.5662 | 1800 | 0.0441 | -4.2531 | -9.4108 | 0.9131 | 5.1578 | -977.0005 | -458.1054 | 2.0999 | 2.2904 |
|
83 |
+
| 0.0713 | 0.5977 | 1900 | 0.0411 | -4.4101 | -9.6543 | 0.9168 | 5.2442 | -1001.3448 | -473.8065 | 2.0887 | 2.2861 |
|
84 |
+
| 0.0553 | 0.6291 | 2000 | 0.0378 | -4.9687 | -10.5782 | 0.9123 | 5.6095 | -1093.7402 | -529.6686 | 2.0469 | 2.2608 |
|
85 |
+
| 0.0668 | 0.6606 | 2100 | 0.0362 | -4.7485 | -10.3227 | 0.9190 | 5.5741 | -1068.1823 | -507.6488 | 2.1354 | 2.3368 |
|
86 |
+
| 0.0528 | 0.6920 | 2200 | 0.0356 | -4.6766 | -10.2170 | 0.9175 | 5.5404 | -1057.6173 | -500.4605 | 1.9572 | 2.1594 |
|
87 |
+
| 0.0596 | 0.7235 | 2300 | 0.0340 | -4.6180 | -10.2121 | 0.9235 | 5.5942 | -1057.1299 | -494.5929 | 2.0041 | 2.2117 |
|
88 |
+
| 0.063 | 0.7550 | 2400 | 0.0328 | -4.5357 | -10.1876 | 0.9257 | 5.6519 | -1054.6713 | -486.3653 | 2.1493 | 2.3488 |
|
89 |
+
| 0.0558 | 0.7864 | 2500 | 0.0311 | -4.7155 | -10.5680 | 0.9261 | 5.8526 | -1092.7185 | -504.3435 | 2.1208 | 2.3275 |
|
90 |
+
| 0.0552 | 0.8179 | 2600 | 0.0312 | -4.6574 | -10.3658 | 0.9254 | 5.7084 | -1072.4943 | -498.5399 | 2.0544 | 2.2592 |
|
91 |
+
| 0.066 | 0.8493 | 2700 | 0.0305 | -4.6506 | -10.4766 | 0.9287 | 5.8259 | -1083.5740 | -497.8611 | 2.0914 | 2.2968 |
|
92 |
+
| 0.0568 | 0.8808 | 2800 | 0.0302 | -4.6423 | -10.4629 | 0.9302 | 5.8206 | -1082.2051 | -497.0266 | 2.0957 | 2.3026 |
|
93 |
+
| 0.0602 | 0.9122 | 2900 | 0.0299 | -4.6260 | -10.4608 | 0.9299 | 5.8348 | -1081.9958 | -495.3989 | 2.0861 | 2.2911 |
|
94 |
+
| 0.0634 | 0.9437 | 3000 | 0.0298 | -4.6454 | -10.4843 | 0.9313 | 5.8389 | -1084.3455 | -497.3409 | 2.0655 | 2.2739 |
|
95 |
+
| 0.0602 | 0.9751 | 3100 | 0.0299 | -4.6289 | -10.4404 | 0.9302 | 5.8116 | -1079.9603 | -495.6860 | 2.0537 | 2.2623 |
|
96 |
|
97 |
|
98 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,22 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_logits/chosen": 2.140789270401001,
|
4 |
-
"eval_logits/rejected": 1.9412086009979248,
|
5 |
-
"eval_logps/chosen": -503.5469665527344,
|
6 |
-
"eval_logps/rejected": -1102.4208984375,
|
7 |
-
"eval_loss": 0.028598472476005554,
|
8 |
-
"eval_rewards/accuracies": 0.9253731369972229,
|
9 |
-
"eval_rewards/chosen": -4.707759380340576,
|
10 |
-
"eval_rewards/margins": 5.957462787628174,
|
11 |
-
"eval_rewards/rejected": -10.66522216796875,
|
12 |
-
"eval_runtime": 214.7372,
|
13 |
-
"eval_samples": 21417,
|
14 |
-
"eval_samples_per_second": 99.736,
|
15 |
-
"eval_steps_per_second": 1.56,
|
16 |
"total_flos": 0.0,
|
17 |
-
"train_loss": 0.
|
18 |
-
"train_runtime":
|
19 |
"train_samples": 406907,
|
20 |
-
"train_samples_per_second": 25.
|
21 |
-
"train_steps_per_second": 0.
|
22 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.18858218038370866,
|
5 |
+
"train_runtime": 16104.4918,
|
6 |
"train_samples": 406907,
|
7 |
+
"train_samples_per_second": 25.267,
|
8 |
+
"train_steps_per_second": 0.197
|
9 |
}
|
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": 406907,
|
7 |
-
"train_samples_per_second": 25.
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.18858218038370866,
|
5 |
+
"train_runtime": 16104.4918,
|
6 |
"train_samples": 406907,
|
7 |
+
"train_samples_per_second": 25.267,
|
8 |
+
"train_steps_per_second": 0.197
|
9 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|