Hugging Face's logo

progs2002
/
star-trek-tng-script-generator

Text Generation
Transformers
TensorBoard
Safetensors
English
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
progs2002 commited on
Commit
cac99d8
·
verified ·
1 Parent(s): afca561

End of training

Browse files
Files changed (5) hide show
  1. README.md +29 -27
  2. model.safetensors +1 -1
  3. runs/Jan24_06-23-30_2545872ab51a/events.out.tfevents.1706077411.2545872ab51a.1303.0 +3 -0
  4. runs/Jan24_06-38-51_2545872ab51a/events.out.tfevents.1706078332.2545872ab51a.5361.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -6,22 +6,16 @@ tags:
6
  model-index:
7
  - name: star-trek-tng-script-generator
8
  results: []
9
- datasets:
10
- - progs2002/star-trek-tng-scripts
11
- language:
12
- - en
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
- # pre-processing and training code
18
- https://github.com/progs2002/StarTrekTNG-ScriptGenerator
19
 
20
  # star-trek-tng-script-generator
21
 
22
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 2.8036
25
 
26
  ## Model description
27
 
@@ -46,28 +40,36 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: cosine
49
- - lr_scheduler_warmup_steps: 100
50
- - num_epochs: 2
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:-----:|:----:|:---------------:|
56
- | 3.1852 | 0.13 | 500 | 3.0649 |
57
- | 3.0477 | 0.26 | 1000 | 3.0007 |
58
- | 2.9831 | 0.38 | 1500 | 2.9711 |
59
- | 2.9662 | 0.51 | 2000 | 2.9474 |
60
- | 2.9275 | 0.64 | 2500 | 2.9116 |
61
- | 2.8711 | 0.77 | 3000 | 2.8952 |
62
- | 2.8551 | 0.89 | 3500 | 2.8771 |
63
- | 2.7449 | 1.02 | 4000 | 2.8645 |
64
- | 2.4553 | 1.15 | 4500 | 2.8441 |
65
- | 2.4575 | 1.28 | 5000 | 2.8457 |
66
- | 2.4452 | 1.4 | 5500 | 2.8329 |
67
- | 2.4256 | 1.53 | 6000 | 2.8180 |
68
- | 2.3958 | 1.66 | 6500 | 2.8123 |
69
- | 2.4084 | 1.79 | 7000 | 2.8049 |
70
- | 2.3855 | 1.92 | 7500 | 2.8044 |
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
@@ -75,4 +77,4 @@ The following hyperparameters were used during training:
75
  - Transformers 4.35.2
76
  - Pytorch 2.1.0+cu121
77
  - Datasets 2.16.1
78
- - Tokenizers 0.15.0
 
6
  model-index:
7
  - name: star-trek-tng-script-generator
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
  # star-trek-tng-script-generator
15
 
16
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.8459
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: cosine
43
+ - lr_scheduler_warmup_steps: 50
44
+ - num_epochs: 3
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 3.1502 | 0.13 | 500 | 3.0233 |
51
+ | 3.0538 | 0.26 | 1000 | 2.9728 |
52
+ | 2.9951 | 0.38 | 1500 | 2.9437 |
53
+ | 2.9891 | 0.51 | 2000 | 2.9125 |
54
+ | 2.9289 | 0.64 | 2500 | 2.9159 |
55
+ | 2.9091 | 0.77 | 3000 | 2.9008 |
56
+ | 2.8916 | 0.89 | 3500 | 2.8752 |
57
+ | 2.8122 | 1.02 | 4000 | 2.8881 |
58
+ | 2.5224 | 1.15 | 4500 | 2.8896 |
59
+ | 2.5284 | 1.28 | 5000 | 2.8667 |
60
+ | 2.5191 | 1.4 | 5500 | 2.8599 |
61
+ | 2.5119 | 1.53 | 6000 | 2.8488 |
62
+ | 2.4808 | 1.66 | 6500 | 2.8296 |
63
+ | 2.4601 | 1.79 | 7000 | 2.8081 |
64
+ | 2.4331 | 1.91 | 7500 | 2.7993 |
65
+ | 2.3716 | 2.04 | 8000 | 2.8518 |
66
+ | 2.1528 | 2.17 | 8500 | 2.8634 |
67
+ | 2.1276 | 2.3 | 9000 | 2.8617 |
68
+ | 2.1329 | 2.43 | 9500 | 2.8489 |
69
+ | 2.1135 | 2.55 | 10000 | 2.8446 |
70
+ | 2.1259 | 2.68 | 10500 | 2.8461 |
71
+ | 2.1142 | 2.81 | 11000 | 2.8472 |
72
+ | 2.1071 | 2.94 | 11500 | 2.8459 |
73
 
74
 
75
  ### Framework versions
 
77
  - Transformers 4.35.2
78
  - Pytorch 2.1.0+cu121
79
  - Datasets 2.16.1
80
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9355cc23b5f74b3b858d4f402c43ad57fd3ec6e56c77a60baf506155c63cb4e3
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7924931408665a3a2ab6162c83aa658f758ddb6af955a05f0470024bb525eaf1
3
  size 497774208
runs/Jan24_06-23-30_2545872ab51a/events.out.tfevents.1706077411.2545872ab51a.1303.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1516ad00598b2f204c3b8bdb675e7917e5803de8aa940910a8e2521c8d2b9aae
3
+ size 10208
runs/Jan24_06-38-51_2545872ab51a/events.out.tfevents.1706078332.2545872ab51a.5361.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189e76e113a3560fca7b783af81302c893a7e68264b6395b06442873f5fe7d27
3
+ size 14685
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51e5e009e728175c03f3bd3ef428a6117521748fce818f4193725a2b7582feb2
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63fa78bc83d07658397fff0aab8e7f6ba9d6b4d5e46f07dc8f7c3bcf7eb06289
3
  size 4600