summervent
commited on
Commit
•
5422338
1
Parent(s):
243e2e2
Upload 19 files
Browse files- README.md +56 -0
- added_tokens.json +4 -0
- all_results.json +15 -0
- config.json +34 -0
- eval_results.json +10 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Feb04_10-45-09_anaslan/1675507566.4468966/events.out.tfevents.1675507566.anaslan.31123.1 +3 -0
- runs/Feb04_10-45-09_anaslan/events.out.tfevents.1675507566.anaslan.31123.0 +3 -0
- runs/Feb04_10-47-45_anaslan/1675507678.0166109/events.out.tfevents.1675507678.anaslan.31153.1 +3 -0
- runs/Feb04_10-47-45_anaslan/events.out.tfevents.1675507677.anaslan.31153.0 +3 -0
- runs/Feb04_10-48-56_anaslan/1675507748.4822354/events.out.tfevents.1675507748.anaslan.31175.1 +3 -0
- runs/Feb04_10-48-56_anaslan/events.out.tfevents.1675507748.anaslan.31175.0 +3 -0
- runs/Feb04_10-48-56_anaslan/events.out.tfevents.1675512703.anaslan.31175.2 +3 -0
- special_tokens_map.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- train_results.json +8 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: spell
|
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 |
+
# spell
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [sberbank-ai/rugpt3small_based_on_gpt2](https://huggingface.co/sberbank-ai/rugpt3small_based_on_gpt2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.4051
|
19 |
+
- Accuracy: 0.6097
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3.0
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.27.0.dev0
|
54 |
+
- Pytorch 1.7.1+cu110
|
55 |
+
- Datasets 2.9.0
|
56 |
+
- Tokenizers 0.13.2
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 50257,
|
3 |
+
"==>": 50258
|
4 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.609682229056006,
|
4 |
+
"eval_loss": 2.405073642730713,
|
5 |
+
"eval_runtime": 0.9514,
|
6 |
+
"eval_samples": 42,
|
7 |
+
"eval_samples_per_second": 44.146,
|
8 |
+
"eval_steps_per_second": 44.146,
|
9 |
+
"perplexity": 11.079246158085713,
|
10 |
+
"train_loss": 2.4779672030492494,
|
11 |
+
"train_runtime": 4952.7178,
|
12 |
+
"train_samples": 20804,
|
13 |
+
"train_samples_per_second": 12.602,
|
14 |
+
"train_steps_per_second": 12.602
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 2048,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 2048,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.27.0.dev0",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 50264
|
34 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.609682229056006,
|
4 |
+
"eval_loss": 2.405073642730713,
|
5 |
+
"eval_runtime": 0.9514,
|
6 |
+
"eval_samples": 42,
|
7 |
+
"eval_samples_per_second": 44.146,
|
8 |
+
"eval_steps_per_second": 44.146,
|
9 |
+
"perplexity": 11.079246158085713
|
10 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.27.0.dev0"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f4a21309fe0ee749687abf15f5700d13f1593f5d808c8e5f0a637556d114937
|
3 |
+
size 551315232
|
runs/Feb04_10-45-09_anaslan/1675507566.4468966/events.out.tfevents.1675507566.anaslan.31123.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:401f896bad692803325efd1da7fad841ad5a6bfc2bb7700a0a55633b67b69df6
|
3 |
+
size 5707
|
runs/Feb04_10-45-09_anaslan/events.out.tfevents.1675507566.anaslan.31123.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d4f57f979549f330ba0f6689c6bc55af9be632da989d8faeb4e7d8950a92f2
|
3 |
+
size 12638
|
runs/Feb04_10-47-45_anaslan/1675507678.0166109/events.out.tfevents.1675507678.anaslan.31153.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1e815f837c4dca0f42422733aca60ca1441837afec89f48812937d67918e07c
|
3 |
+
size 5707
|
runs/Feb04_10-47-45_anaslan/events.out.tfevents.1675507677.anaslan.31153.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dba686e1fff57906f672e7973e06f1e6b9fc8d31173c6be735e732ee1fc3dd8
|
3 |
+
size 11383
|
runs/Feb04_10-48-56_anaslan/1675507748.4822354/events.out.tfevents.1675507748.anaslan.31175.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9cb52ea6f15496e26e59e99f24320d88cff027a8611f0643de8683e080100d3
|
3 |
+
size 5707
|
runs/Feb04_10-48-56_anaslan/events.out.tfevents.1675507748.anaslan.31175.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc53afde625d2e4280e25b5b83cc30e3869070d4b4baf83fd457d315df28fd03
|
3 |
+
size 998011
|
runs/Feb04_10-48-56_anaslan/events.out.tfevents.1675512703.anaslan.31175.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50192c45759dbe3c307ac12c6c59e2823c1a8318bb26325271c160d47d49b29e
|
3 |
+
size 369
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"sep_token": "==>",
|
5 |
+
"unk_token": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
}
|
12 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.4779672030492494,
|
4 |
+
"train_runtime": 4952.7178,
|
5 |
+
"train_samples": 20804,
|
6 |
+
"train_samples_per_second": 12.602,
|
7 |
+
"train_steps_per_second": 12.602
|
8 |
+
}
|