DrishtiSharma
commited on
Commit
•
686f43a
1
Parent(s):
429b81d
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- dpo
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: cognitivecomputations/dolphin-2.1-mistral-7b
|
9 |
+
model-index:
|
10 |
+
- name: doplhin-mistral-dpo-ultrafeedback-binarized-preferences-sigmoid
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# doplhin-mistral-dpo-ultrafeedback-binarized-preferences-sigmoid
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [cognitivecomputations/dolphin-2.1-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.1-mistral-7b) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6025
|
22 |
+
- Rewards/chosen: -7.8168
|
23 |
+
- Rewards/rejected: -14.5388
|
24 |
+
- Rewards/accuracies: 0.8310
|
25 |
+
- Rewards/margins: 6.7220
|
26 |
+
- Logps/rejected: -469.4976
|
27 |
+
- Logps/chosen: -438.1190
|
28 |
+
- Logits/rejected: -2.1911
|
29 |
+
- Logits/chosen: -2.3064
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 5e-05
|
49 |
+
- train_batch_size: 4
|
50 |
+
- eval_batch_size: 4
|
51 |
+
- seed: 42
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: cosine
|
54 |
+
- lr_scheduler_warmup_ratio: 0.1
|
55 |
+
- num_epochs: 1
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
61 |
+
| 1.0466 | 0.25 | 700 | 0.8185 | -6.6407 | -9.8742 | 0.7464 | 3.2335 | -422.8520 | -426.3579 | -2.3161 | -2.4530 |
|
62 |
+
| 0.7039 | 0.51 | 1400 | 0.7051 | -6.5305 | -12.5351 | 0.8085 | 6.0046 | -449.4607 | -425.2558 | -2.1415 | -2.2554 |
|
63 |
+
| 0.9519 | 0.76 | 2100 | 0.6025 | -7.8168 | -14.5388 | 0.8310 | 6.7220 | -469.4976 | -438.1190 | -2.1911 | -2.3064 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- PEFT 0.8.2
|
69 |
+
- Transformers 4.37.2
|
70 |
+
- Pytorch 2.1.2+cu121
|
71 |
+
- Datasets 2.16.1
|
72 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335605144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b43df3d4acb4e840cb7c32098306b6892429e6ceafb77a7e591f0471784b1197
|
3 |
size 335605144
|
runs/Feb22_15-19-47_a1a9d1cfe150/events.out.tfevents.1708615986.a1a9d1cfe150.387.0
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:c4187ce84f3143b7792663c596edbee7eb47a1c334b4af8a90c12472be2f3ccf
|
3 |
+
size 77158
|