Commit
•
ab2027c
1
Parent(s):
cfe29b9
Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/deberta-v3-large
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- reward-trainer
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: deberta-v3-large-reward-model
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# deberta-v3-large-reward-model
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0106
|
| 23 |
+
- Accuracy: 0.995
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 1.41e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 10.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 56 |
+
| 0.0213 | 2.0 | 100 | 0.0205 | 0.995 |
|
| 57 |
+
| 0.002 | 4.0 | 200 | 0.0128 | 0.995 |
|
| 58 |
+
| 0.0005 | 6.0 | 300 | 0.0107 | 0.995 |
|
| 59 |
+
| 0.0001 | 8.0 | 400 | 0.0110 | 0.995 |
|
| 60 |
+
| 0.0001 | 10.0 | 500 | 0.0106 | 0.995 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.41.2
|
| 66 |
+
- Pytorch 2.3.0
|
| 67 |
+
- Datasets 2.19.1
|
| 68 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1740300340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00cba1421b67d47716ed4e531c6d00916ed26665f537dd69ca5b2172286781e2
|
| 3 |
size 1740300340
|
runs/Jun12_14-19-25_cla-99m41v9m/events.out.tfevents.1718216369.cla-99m41v9m.97976.0
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 sha256:7c7a8564a4968a7ce6c9b5ab066aa5d980548dc51817a549c3ca0d3139857ad9
|
| 3 |
+
size 17582
|