Hugging Face's logo

toloka
/
gpt2-large-supervised-prompt-writing

Text Generation
Transformers
PyTorch
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
2
Nikita Pavlichenko commited on
Commit
9be7cca
·
1 Parent(s): 77dd825

Remove [BOS] from descriptions

Browse files
Files changed (7) hide show
  1. README.md +12 -12
  2. all_results.json +10 -10
  3. eval_results.json +6 -6
  4. pytorch_model.bin +1 -1
  5. train_results.json +4 -4
  6. trainer_state.json +0 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [gpt2-large](https://huggingface.co/gpt2-large) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.0773
20
- - Accuracy: 0.8482
21
 
22
  ## Model description
23
 
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
- | 2.4891 | 0.19 | 1000 | 2.4467 | 0.8446 |
53
- | 2.7019 | 0.37 | 2000 | 2.3208 | 0.8456 |
54
- | 2.5278 | 0.56 | 3000 | 2.2470 | 0.8464 |
55
- | 2.0687 | 0.74 | 4000 | 2.1953 | 0.8468 |
56
- | 2.1738 | 0.93 | 5000 | 2.1543 | 0.8472 |
57
- | 1.8554 | 1.12 | 6000 | 2.1500 | 0.8475 |
58
- | 1.9276 | 1.3 | 7000 | 2.1223 | 0.8477 |
59
- | 1.7988 | 1.49 | 8000 | 2.1120 | 0.8479 |
60
- | 2.0632 | 1.67 | 9000 | 2.0973 | 0.8480 |
61
- | 1.9586 | 1.86 | 10000 | 2.0826 | 0.8481 |
62
 
63
 
64
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [gpt2-large](https://huggingface.co/gpt2-large) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.0808
20
+ - Accuracy: 0.8556
21
 
22
  ## Model description
23
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 2.4827 | 0.19 | 1000 | 2.4565 | 0.8520 |
53
+ | 2.6468 | 0.37 | 2000 | 2.3303 | 0.8530 |
54
+ | 2.5106 | 0.56 | 3000 | 2.2487 | 0.8537 |
55
+ | 2.0732 | 0.74 | 4000 | 2.2020 | 0.8541 |
56
+ | 2.159 | 0.93 | 5000 | 2.1594 | 0.8545 |
57
+ | 1.856 | 1.12 | 6000 | 2.1518 | 0.8548 |
58
+ | 1.9138 | 1.3 | 7000 | 2.1261 | 0.8551 |
59
+ | 1.8055 | 1.49 | 8000 | 2.1126 | 0.8552 |
60
+ | 2.0385 | 1.67 | 9000 | 2.1008 | 0.8554 |
61
+ | 1.9648 | 1.86 | 10000 | 2.0858 | 0.8555 |
62
 
63
 
64
  ### Framework versions
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "epoch": 2.0,
3
- "eval_accuracy": 0.8481798046914326,
4
- "eval_loss": 2.0772647857666016,
5
- "eval_runtime": 129.398,
6
  "eval_samples": 10750,
7
- "eval_samples_per_second": 83.077,
8
- "eval_steps_per_second": 10.387,
9
- "perplexity": 7.982604892014763,
10
- "train_loss": 2.1184611846914603,
11
- "train_runtime": 4663.4223,
12
  "train_samples": 43003,
13
- "train_samples_per_second": 18.443,
14
- "train_steps_per_second": 2.306
15
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_accuracy": 0.8555773331979283,
4
+ "eval_loss": 2.0807912349700928,
5
+ "eval_runtime": 125.0813,
6
  "eval_samples": 10750,
7
+ "eval_samples_per_second": 85.944,
8
+ "eval_steps_per_second": 10.745,
9
+ "perplexity": 8.010804836289337,
10
+ "train_loss": 2.1236886782571673,
11
+ "train_runtime": 4504.4872,
12
  "train_samples": 43003,
13
+ "train_samples_per_second": 19.093,
14
+ "train_steps_per_second": 2.387
15
  }
eval_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "epoch": 2.0,
3
- "eval_accuracy": 0.8481798046914326,
4
- "eval_loss": 2.0772647857666016,
5
- "eval_runtime": 129.398,
6
  "eval_samples": 10750,
7
- "eval_samples_per_second": 83.077,
8
- "eval_steps_per_second": 10.387,
9
- "perplexity": 7.982604892014763
10
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_accuracy": 0.8555773331979283,
4
+ "eval_loss": 2.0807912349700928,
5
+ "eval_runtime": 125.0813,
6
  "eval_samples": 10750,
7
+ "eval_samples_per_second": 85.944,
8
+ "eval_steps_per_second": 10.745,
9
+ "perplexity": 8.010804836289337
10
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c68c6a4031f800eda2b9d1b40fe6faa1bd0d8c017a068f2c3c79fc7f83d4eca
3
  size 3134045245
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a854f911fcf67887abe92522ba2b32cb2eb42925c185792b4a089aaae7a38ae
3
  size 3134045245
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
- "train_loss": 2.1184611846914603,
4
- "train_runtime": 4663.4223,
5
  "train_samples": 43003,
6
- "train_samples_per_second": 18.443,
7
- "train_steps_per_second": 2.306
8
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "train_loss": 2.1236886782571673,
4
+ "train_runtime": 4504.4872,
5
  "train_samples": 43003,
6
+ "train_samples_per_second": 19.093,
7
+ "train_steps_per_second": 2.387
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2354ff3ec9e59058b3289218560a957a3cbc5faa14c40080e2daf94d9e8c0c3f
3
  size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4f0f455cfe353b38c6958e9dd682a9cb66e8e0afbc23961e3ce8be69bb0ab7
3
  size 3451