Hugging Face's logo

augustocsc
/
gpt-m-multi-var

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
augustocsc commited on
Commit
d90b8e2
•
1 Parent(s): dcd92c4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -24
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [augustocsc/gpt-m](https://huggingface.co/augustocsc/gpt-m) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0023
18
 
19
  ## Model description
20
 
@@ -39,32 +39,22 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - training_steps: 10000
43
 
44
  ### Training results
45
 
46
- | Training Loss | Epoch | Step | Validation Loss |
47
- |:-------------:|:-----:|:-----:|:---------------:|
48
- | 0.0089 | 0.61 | 500 | 0.0193 |
49
- | 0.0051 | 1.22 | 1000 | 0.0030 |
50
- | 0.0039 | 1.83 | 1500 | 0.0032 |
51
- | 0.0034 | 2.44 | 2000 | 0.0027 |
52
- | 0.0033 | 3.05 | 2500 | 0.0028 |
53
- | 0.0031 | 3.66 | 3000 | 0.0029 |
54
- | 0.0032 | 4.27 | 3500 | 0.0026 |
55
- | 0.0029 | 4.88 | 4000 | 0.0028 |
56
- | 0.0027 | 5.49 | 4500 | 0.0025 |
57
- | 0.0034 | 6.11 | 5000 | 0.0025 |
58
- | 0.0028 | 6.72 | 5500 | 0.0026 |
59
- | 0.0027 | 7.33 | 6000 | 0.0024 |
60
- | 0.0028 | 7.94 | 6500 | 0.0025 |
61
- | 0.0035 | 8.55 | 7000 | 0.0023 |
62
- | 0.0026 | 9.16 | 7500 | 0.0023 |
63
- | 0.0026 | 9.77 | 8000 | 0.0023 |
64
- | 0.0026 | 10.38 | 8500 | 0.0023 |
65
- | 0.0026 | 10.99 | 9000 | 0.0023 |
66
- | 0.0025 | 11.6 | 9500 | 0.0023 |
67
- | 0.0025 | 12.21 | 10000 | 0.0023 |
68
 
69
 
70
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [augustocsc/gpt-m](https://huggingface.co/augustocsc/gpt-m) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0017
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - training_steps: 5000
43
 
44
  ### Training results
45
 
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 0.0065 | 0.55 | 500 | 0.0027 |
49
+ | 0.0086 | 1.1 | 1000 | 0.0020 |
50
+ | 0.0023 | 1.65 | 1500 | 0.0020 |
51
+ | 0.002 | 2.2 | 2000 | 0.0019 |
52
+ | 0.0021 | 2.75 | 2500 | 0.0018 |
53
+ | 0.0021 | 3.3 | 3000 | 0.0019 |
54
+ | 0.002 | 3.85 | 3500 | 0.0017 |
55
+ | 0.0019 | 4.4 | 4000 | 0.0018 |
56
+ | 0.002 | 4.95 | 4500 | 0.0017 |
57
+ | 0.0019 | 5.5 | 5000 | 0.0017 |
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions