AhsenKacar
commited on
Commit
•
3f203f9
1
Parent(s):
035d801
Training in progress epoch 0
Browse files- README.md +11 -6
- config.json +2 -2
- special_tokens_map.json +1 -0
- tf_model.h5 +2 -2
- tokenizer.json +6 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -1,22 +1,24 @@
|
|
1 |
---
|
2 |
-
base_model: AhsenKacar/TurkishReviews-ds-mini
|
3 |
library_name: transformers
|
4 |
license: mit
|
|
|
5 |
tags:
|
6 |
- generated_from_keras_callback
|
7 |
model-index:
|
8 |
-
- name: TurkishReviews-ds-mini
|
9 |
results: []
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
13 |
probably proofread and complete it, then remove this comment. -->
|
14 |
|
15 |
-
# TurkishReviews-ds-mini
|
16 |
|
17 |
-
This model is a fine-tuned version of [
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,11 +37,14 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- optimizer: {'
|
39 |
- training_precision: mixed_float16
|
40 |
|
41 |
### Training results
|
42 |
|
|
|
|
|
|
|
43 |
|
44 |
|
45 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
library_name: transformers
|
3 |
license: mit
|
4 |
+
base_model: gpt2
|
5 |
tags:
|
6 |
- generated_from_keras_callback
|
7 |
model-index:
|
8 |
+
- name: AhsenKacar/TurkishReviews-ds-mini
|
9 |
results: []
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
13 |
probably proofread and complete it, then remove this comment. -->
|
14 |
|
15 |
+
# AhsenKacar/TurkishReviews-ds-mini
|
16 |
|
17 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Train Loss: 8.7685
|
20 |
+
- Validation Loss: 7.6386
|
21 |
+
- Epoch: 0
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
37 |
### Training hyperparameters
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 43, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
41 |
- training_precision: mixed_float16
|
42 |
|
43 |
### Training results
|
44 |
|
45 |
+
| Train Loss | Validation Loss | Epoch |
|
46 |
+
|:----------:|:---------------:|:-----:|
|
47 |
+
| 8.7685 | 7.6386 | 0 |
|
48 |
|
49 |
|
50 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -34,5 +34,5 @@
|
|
34 |
},
|
35 |
"transformers_version": "4.44.2",
|
36 |
"use_cache": true,
|
37 |
-
"vocab_size":
|
38 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
34 |
},
|
35 |
"transformers_version": "4.44.2",
|
36 |
"use_cache": true,
|
37 |
+
"vocab_size": 52000
|
38 |
}
|
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<|endoftext|>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0f55340b50784449b5cf6d58607c29975f4641942b787618d8091c31e7a792f
|
3 |
+
size 503289936
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 40,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -16,7 +16,7 @@
|
|
16 |
"eos_token": "<|endoftext|>",
|
17 |
"errors": "replace",
|
18 |
"model_max_length": 1024,
|
19 |
-
"pad_token":
|
20 |
"tokenizer_class": "GPT2Tokenizer",
|
21 |
"unk_token": "<|endoftext|>"
|
22 |
}
|
|
|
16 |
"eos_token": "<|endoftext|>",
|
17 |
"errors": "replace",
|
18 |
"model_max_length": 1024,
|
19 |
+
"pad_token": "<|endoftext|>",
|
20 |
"tokenizer_class": "GPT2Tokenizer",
|
21 |
"unk_token": "<|endoftext|>"
|
22 |
}
|