slplab commited on
Commit
f159bce
1 Parent(s): f794984

End of training

Browse files
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: slplab/polyglot-ko-1.3b-pretrained-asd
6
+ model-index:
7
+ - name: pretrain-asd_w-cot_w-asd_text-features
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
+ # pretrain-asd_w-cot_w-asd_text-features
15
+
16
+ This model was trained from scratch on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.2919
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: 3e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 4
42
+ - total_train_batch_size: 8
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:-----:|:---------------:|
52
+ | 0.5331 | 0.1725 | 1000 | 0.3109 |
53
+ | 0.3076 | 0.3450 | 2000 | 0.3025 |
54
+ | 0.2963 | 0.5174 | 3000 | 0.3007 |
55
+ | 0.3008 | 0.6899 | 4000 | 0.2992 |
56
+ | 0.2969 | 0.8624 | 5000 | 0.2984 |
57
+ | 0.2956 | 1.0349 | 6000 | 0.2977 |
58
+ | 0.2943 | 1.2074 | 7000 | 0.3000 |
59
+ | 0.2973 | 1.3798 | 8000 | 0.2968 |
60
+ | 0.2927 | 1.5523 | 9000 | 0.2953 |
61
+ | 0.2949 | 1.7248 | 10000 | 0.2943 |
62
+ | 0.2915 | 1.8973 | 11000 | 0.2931 |
63
+ | 0.2897 | 2.0698 | 12000 | 0.2937 |
64
+ | 0.2885 | 2.2422 | 13000 | 0.2926 |
65
+ | 0.2945 | 2.4147 | 14000 | 0.2928 |
66
+ | 0.2907 | 2.5872 | 15000 | 0.2923 |
67
+ | 0.292 | 2.7597 | 16000 | 0.2922 |
68
+ | 0.2899 | 2.9322 | 17000 | 0.2919 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - PEFT 0.11.1
74
+ - Transformers 4.41.1
75
+ - Pytorch 2.3.0+cu121
76
+ - Datasets 2.19.1
77
+ - Tokenizers 0.19.1
runs/Aug09_16-55-40_oem-WS-C621E-SAGE-Series/events.out.tfevents.1723190144.oem-WS-C621E-SAGE-Series.2300426.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24ad938248186423dfb79ab02586f4a48a6dd753056837bd2a0150d4672b4765
3
- size 12417
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4430e7234881ed2ed6c2c02710ec2dbe025ac4e37ac7490cdbcfafffd373dd6
3
+ size 13750