Hugging Face's logo

Pyro-X2
/
polish_wikipedia_model

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neox
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Pyro-X2 commited on
Commit
14a9fcd
•
1 Parent(s): 21c9580

End of training

Browse files
Files changed (4) hide show
  1. README.md +33 -13
  2. model.safetensors +1 -1
  3. runs/Jun03_12-10-09_c4a222934390/events.out.tfevents.1717416611.c4a222934390.167.4 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: EleutherAI/pythia-70m
6
  model-index:
7
  - name: polish_wikipedia_model
8
  results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0404
19
 
20
  ## Model description
21
 
@@ -40,22 +40,42 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 10
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 133 | 0.4825 |
50
- | No log | 2.0 | 266 | 0.4049 |
51
- | No log | 3.0 | 399 | 0.4124 |
52
- | 0.4774 | 4.0 | 532 | 0.2849 |
53
- | 0.4774 | 5.0 | 665 | 0.2543 |
54
- | 0.4774 | 6.0 | 798 | 0.1860 |
55
- | 0.4774 | 7.0 | 931 | 0.1209 |
56
- | 0.2561 | 8.0 | 1064 | 0.0836 |
57
- | 0.2561 | 9.0 | 1197 | 0.0530 |
58
- | 0.2561 | 10.0 | 1330 | 0.0404 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: EleutherAI/pythia-70m
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: polish_wikipedia_model
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0319
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 30
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 133 | 0.4322 |
50
+ | No log | 2.0 | 266 | 0.3766 |
51
+ | No log | 3.0 | 399 | 0.3599 |
52
+ | 0.4669 | 4.0 | 532 | 0.3247 |
53
+ | 0.4669 | 5.0 | 665 | 0.2830 |
54
+ | 0.4669 | 6.0 | 798 | 0.2628 |
55
+ | 0.4669 | 7.0 | 931 | 0.2573 |
56
+ | 0.3481 | 8.0 | 1064 | 0.2443 |
57
+ | 0.3481 | 9.0 | 1197 | 0.1904 |
58
+ | 0.3481 | 10.0 | 1330 | 0.1799 |
59
+ | 0.3481 | 11.0 | 1463 | 0.1475 |
60
+ | 0.2502 | 12.0 | 1596 | 0.1292 |
61
+ | 0.2502 | 13.0 | 1729 | 0.1168 |
62
+ | 0.2502 | 14.0 | 1862 | 0.1103 |
63
+ | 0.2502 | 15.0 | 1995 | 0.0989 |
64
+ | 0.1572 | 16.0 | 2128 | 0.0890 |
65
+ | 0.1572 | 17.0 | 2261 | 0.0736 |
66
+ | 0.1572 | 18.0 | 2394 | 0.0672 |
67
+ | 0.1007 | 19.0 | 2527 | 0.0592 |
68
+ | 0.1007 | 20.0 | 2660 | 0.0550 |
69
+ | 0.1007 | 21.0 | 2793 | 0.0517 |
70
+ | 0.1007 | 22.0 | 2926 | 0.0497 |
71
+ | 0.0674 | 23.0 | 3059 | 0.0458 |
72
+ | 0.0674 | 24.0 | 3192 | 0.0421 |
73
+ | 0.0674 | 25.0 | 3325 | 0.0394 |
74
+ | 0.0674 | 26.0 | 3458 | 0.0378 |
75
+ | 0.0491 | 27.0 | 3591 | 0.0357 |
76
+ | 0.0491 | 28.0 | 3724 | 0.0337 |
77
+ | 0.0491 | 29.0 | 3857 | 0.0323 |
78
+ | 0.0491 | 30.0 | 3990 | 0.0319 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12698b7b59b958f659da901f9e1e4194b27b0643292b80ad3c355f980a049289
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:235c4e440f2c71c2e96ff8d219da8cfa791dc929ca1c7df51f76eb7f74a21959
3
  size 281715176
runs/Jun03_12-10-09_c4a222934390/events.out.tfevents.1717416611.c4a222934390.167.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4868fad21726fee063717331e91a3d444c19b29bb91bec73ecff2a6c23ca55c0
3
+ size 14885
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:875e2ed0068d7bed07c05f5271ed7f755fe5407a2d7a8921bc6f07bd4488d233
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2be04d922dfbec40dba786b2af32ba5d7698e6fd00eaf6d77250bc1da61514
3
  size 5112