jeanlucmarsh
commited on
Commit
•
4edce55
1
Parent(s):
da6fb78
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- glue
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
base_model: facebook/opt-125m
|
11 |
+
model-index:
|
12 |
+
- name: opt-125m-pattern-based_finetuning_with_lora-mnli-d2_fs2
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# opt-125m-pattern-based_finetuning_with_lora-mnli-d2_fs2
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the glue dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.7543
|
24 |
+
- Accuracy: 0.5155
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 2e-06
|
44 |
+
- train_batch_size: 16
|
45 |
+
- eval_batch_size: 16
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 5
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
55 |
+
| 0.7301 | 1.0 | 1 | 0.7543 | 0.5155 |
|
56 |
+
| 0.6991 | 2.0 | 2 | 0.7541 | 0.5149 |
|
57 |
+
| 0.5798 | 3.0 | 3 | 0.7539 | 0.5148 |
|
58 |
+
| 0.6508 | 4.0 | 4 | 0.7538 | 0.5143 |
|
59 |
+
| 0.7139 | 5.0 | 5 | 0.7537 | 0.5145 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- PEFT 0.7.1.dev0
|
65 |
+
- Transformers 4.36.0.dev0
|
66 |
+
- Pytorch 2.1.0+cu118
|
67 |
+
- Datasets 2.15.0
|
68 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2372216
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b69904e4139ffe6e374326e2045ef9754644f7a9c88cfe75cc7155d8ba173884
|
3 |
size 2372216
|
runs/Dec10_00-03-41_ea4b281b211c/events.out.tfevents.1702166801.ea4b281b211c.281.30
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18098cc54d7ee6d9895ae87ce7c440056de19cf12aa42ca7e4c06fb220f98d29
|
3 |
+
size 405
|