jgibb commited on
Commit
a5e29e5
1 Parent(s): bfc2a38

training completed[prod]: T5-base-lora

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: google/pegasus-xsum
6
+ model-index:
7
+ - name: T5-lora-legalease
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # T5-lora-legalease
15
+
16
+ This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.5452
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0002
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 2
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 0.18 | 250 | 4.1826 |
51
+ | 4.6756 | 0.35 | 500 | 3.8860 |
52
+ | 4.6756 | 0.53 | 750 | 3.7923 |
53
+ | 3.8476 | 0.71 | 1000 | 3.7309 |
54
+ | 3.8476 | 0.89 | 1250 | 3.6762 |
55
+ | 3.7406 | 1.06 | 1500 | 3.6374 |
56
+ | 3.7406 | 1.24 | 1750 | 3.6072 |
57
+ | 3.6278 | 1.42 | 2000 | 3.5841 |
58
+ | 3.6278 | 1.6 | 2250 | 3.5630 |
59
+ | 3.6359 | 1.77 | 2500 | 3.5509 |
60
+ | 3.6359 | 1.95 | 2750 | 3.5452 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - PEFT 0.10.0
66
+ - Transformers 4.38.2
67
+ - Pytorch 2.2.1+cu121
68
+ - Datasets 2.18.0
69
+ - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4142f437d00acf59f12b9be98667108480174663bebdb218c32c9aa08c2d0725
3
  size 419559360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f2b53e1f0ef1fba74cf82b23b67ee87be840a6d424d843cb9fca5ab87262f8
3
  size 419559360
runs/Apr02_05-19-37_ba3afbe869fb/events.out.tfevents.1712035211.ba3afbe869fb.232.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c43c9fd4f01f2e43cc16c7133becf2cf322937d71e6802b393f8173791f0d29f
3
- size 7321
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589737b8764902118158d860f4bedf8ff2f422c8cbefa2efc6fff633ffb33d48
3
+ size 10205