Hugging Face's logo

C0uchP0tat0
/
gpt2medium-finetuned

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
Denis commited on
Commit
c0ee957
·
1 Parent(s): 5ba1eb0

End of training

Browse files
Files changed (6) hide show
  1. README.md +6 -7
  2. model.safetensors +1 -1
  3. runs/Dec22_19-47-21_3eb6c8de2272/events.out.tfevents.1703274446.3eb6c8de2272.747.2 +3 -0
  4. runs/Dec22_19-48-02_3eb6c8de2272/events.out.tfevents.1703274489.3eb6c8de2272.747.3 +3 -0
  5. tokenizer.json +1 -1
  6. training_args.bin +1 -1
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 [ai-forever/rugpt3medium_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3medium_based_on_gpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.3788
18
 
19
  ## Model description
20
 
@@ -42,18 +42,17 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_steps: 1000
45
- - num_epochs: 40
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 2.0413 | 6.98 | 100 | 0.4247 |
53
- | 0.858 | 13.95 | 200 | 0.4355 |
54
- | 0.7697 | 20.93 | 300 | 0.3482 |
55
- | 0.6343 | 27.91 | 400 | 0.3125 |
56
- | 0.5486 | 34.88 | 500 | 0.3788 |
57
 
58
 
59
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [ai-forever/rugpt3medium_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3medium_based_on_gpt2) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.1913
18
 
19
  ## Model description
20
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_steps: 1000
45
+ - num_epochs: 22
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 3.0464 | 5.0 | 5 | 2.7436 |
53
+ | 2.2106 | 10.0 | 10 | 1.6388 |
54
+ | 1.1598 | 15.0 | 15 | 0.6276 |
55
+ | 0.3638 | 20.0 | 20 | 0.1913 |
 
56
 
57
 
58
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec537447e6aacbae0ef5403f98d16ae87f0401bab3e5ca8b6072edada1e55aa5
3
  size 1423517184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73d3f4910db0bf4a3241b21c7e732930382dbeb47fb29f96ed28d6c22b90b73
3
  size 1423517184
runs/Dec22_19-47-21_3eb6c8de2272/events.out.tfevents.1703274446.3eb6c8de2272.747.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802f219acc27317a5543b16803dfb6f134f32d015f2629f5fac675a2229b8351
3
+ size 4892
runs/Dec22_19-48-02_3eb6c8de2272/events.out.tfevents.1703274489.3eb6c8de2272.747.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76b8717bf359b5a8aba797878f0045fad5b4a9950dc6c057aad8c8aca383cb9
3
+ size 6570
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Left",
5
- "max_length": 8,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Left",
5
+ "max_length": 64,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0de7fd704906bbd1651828a08d4985b88ae85a99f603e7868d3c32b33f102320
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faae4fc2e0fb34d4b6340062456eaaddd125e5bc1e07b31daedb606977009d7
3
  size 4536