raygx commited on
Commit
ba46a60
1 Parent(s): fb03380

Upload TFGPT2ForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +55 -0
  2. config.json +50 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: raygx/Nepali-DistilGPT2
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: distilGPT-NepSA
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # distilGPT-NepSA
14
+
15
+ This model is a fine-tuned version of [raygx/Nepali-DistilGPT2](https://huggingface.co/raygx/Nepali-DistilGPT2) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.6059
18
+ - Validation Loss: 0.6725
19
+ - Epoch: 2
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
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.001}
39
+ - training_precision: float32
40
+
41
+ ### Training results
42
+
43
+ | Train Loss | Validation Loss | Epoch |
44
+ |:----------:|:---------------:|:-----:|
45
+ | 0.8286 | 0.7084 | 0 |
46
+ | 0.6756 | 0.6550 | 1 |
47
+ | 0.6059 | 0.6725 | 2 |
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.31.0
53
+ - TensorFlow 2.12.0
54
+ - Datasets 2.14.4
55
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "raygx/Nepali-DistilGPT2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2ForSequenceClassification"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 1,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 2,
12
+ "id2label": {
13
+ "0": "NEUTRAL",
14
+ "1": "POSITIVE",
15
+ "2": "NEGATIVE"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "label2id": {
19
+ "NEGATIVE": 2,
20
+ "NEUTRAL": 0,
21
+ "POSITIVE": 1
22
+ },
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "gpt2",
25
+ "n_ctx": 1024,
26
+ "n_embd": 768,
27
+ "n_head": 6,
28
+ "n_inner": null,
29
+ "n_layer": 6,
30
+ "n_positions": 1024,
31
+ "pad_token_id": 3,
32
+ "reorder_and_upcast_attn": false,
33
+ "resid_pdrop": 0.1,
34
+ "scale_attn_by_inverse_layer_idx": false,
35
+ "scale_attn_weights": true,
36
+ "summary_activation": null,
37
+ "summary_first_dropout": 0.1,
38
+ "summary_proj_to_labels": true,
39
+ "summary_type": "cls_index",
40
+ "summary_use_proj": true,
41
+ "task_specific_params": {
42
+ "text-generation": {
43
+ "do_sample": true,
44
+ "max_length": 50
45
+ }
46
+ },
47
+ "transformers_version": "4.31.0",
48
+ "use_cache": true,
49
+ "vocab_size": 50000
50
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5d636e8158f79a7a90b86c9e3728baf0ca21cd18d1a7f7a9a490fd5a28fc4b
3
+ size 326968664