Hugging Face's logo

slplab
/
pretrained-asd_wo-cot_w-asd

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
slplab commited on
Commit
a747578
·
verified ·
1 Parent(s): 6194070

End of training

Browse files
Files changed (3) hide show
  1. README.md +82 -0
  2. adapter_model.safetensors +1 -1
  3. runs/Jul30_21-18-14_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722341897.oem-WS-C621E-SAGE-Series.2700248.0 +2 -2
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: slplab/polyglot-ko-1.3b_pretrained-asd
7
+ model-index:
8
+ - name: pretrained-asd_wo-cot_w-asd
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # pretrained-asd_wo-cot_w-asd
16
+
17
+ This model is a fine-tuned version of [slplab/polyglot-ko-1.3b_pretrained-asd](https://huggingface.co/slplab/polyglot-ko-1.3b_pretrained-asd) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 10.9440
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 3e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 8
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 13.2673 | 0.1290 | 1 | 13.2282 |
54
+ | 13.2184 | 0.2581 | 2 | 13.1124 |
55
+ | 13.0976 | 0.3871 | 3 | 12.9704 |
56
+ | 12.9545 | 0.5161 | 4 | 12.8240 |
57
+ | 12.8232 | 0.6452 | 5 | 12.6843 |
58
+ | 12.6522 | 0.7742 | 6 | 12.5389 |
59
+ | 12.5444 | 0.9032 | 7 | 12.3854 |
60
+ | 12.3496 | 1.0323 | 8 | 12.2316 |
61
+ | 12.2126 | 1.1613 | 9 | 12.0854 |
62
+ | 12.0724 | 1.2903 | 10 | 11.9376 |
63
+ | 11.9188 | 1.4194 | 11 | 11.7927 |
64
+ | 11.7615 | 1.5484 | 12 | 11.6542 |
65
+ | 11.6456 | 1.6774 | 13 | 11.5224 |
66
+ | 11.5276 | 1.8065 | 14 | 11.4017 |
67
+ | 11.3736 | 1.9355 | 15 | 11.2929 |
68
+ | 11.281 | 2.0645 | 16 | 11.1996 |
69
+ | 11.15 | 2.1935 | 17 | 11.1171 |
70
+ | 11.0963 | 2.3226 | 18 | 11.0492 |
71
+ | 11.0646 | 2.4516 | 19 | 10.9964 |
72
+ | 10.9801 | 2.5806 | 20 | 10.9614 |
73
+ | 10.9325 | 2.7097 | 21 | 10.9440 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - PEFT 0.11.1
79
+ - Transformers 4.41.1
80
+ - Pytorch 2.3.0+cu121
81
+ - Datasets 2.19.1
82
+ - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09f2c753414b699f0d5879c27fdfbd62499e956ab4e7c9f2d4e2b15840efebb6
3
  size 25192400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13db6779b8f43fcb9921a3af9c33d7827dca685aa64f1fc84fd45d61756d7cab
3
  size 25192400
runs/Jul30_21-18-14_oem-WS-C621E-SAGE-Series/events.out.tfevents.1722341897.oem-WS-C621E-SAGE-Series.2700248.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c5c304142d2b6c3c540e0d53aeb7d60540a6be91a08883f766f9908beb6f01b
3
- size 14583
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb37dace8be5623105fb3f65b7cdf24b4a40843a3e4e651d085bf2f14da6e8fe
3
+ size 15404