raygx commited on
Commit
31554f5
1 Parent(s): e5680fe

Finetuned raygx/GPT2-Nepali-Casual-LM model for generating Covid-News; 10 Epochs

Browse files
Files changed (4) hide show
  1. README.md +56 -0
  2. config.json +52 -0
  3. generation_config.json +9 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_keras_callback
4
+ model-index:
5
+ - name: Covid-News-Headline-Generator
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
10
+ probably proofread and complete it, then remove this comment. -->
11
+
12
+ # Covid-News-Headline-Generator
13
+
14
+ This model was trained from scratch on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Train Loss: 6.2871
17
+ - Validation Loss: 6.6830
18
+ - Epoch: 4
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - 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}
38
+ - training_precision: float32
39
+
40
+ ### Training results
41
+
42
+ | Train Loss | Validation Loss | Epoch |
43
+ |:----------:|:---------------:|:-----:|
44
+ | 6.6684 | 6.9298 | 0 |
45
+ | 6.5617 | 6.8545 | 1 |
46
+ | 6.4641 | 6.7858 | 2 |
47
+ | 6.3725 | 6.7307 | 3 |
48
+ | 6.2871 | 6.6830 | 4 |
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.28.1
54
+ - TensorFlow 2.11.0
55
+ - Datasets 2.1.0
56
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/nepali-trained-gpt2-casual-language-model/gpt2NepaliCasualLM",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 1,
10
+ "do_sample": true,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 2,
13
+ "id2label": {
14
+ "0": "NEUTRAL",
15
+ "1": "POSITIVE",
16
+ "2": "NEGATIVE"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "NEGATIVE": 2,
21
+ "NEUTRAL": 0,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_epsilon": 1e-05,
25
+ "max_length": 50,
26
+ "model_type": "gpt2",
27
+ "n_ctx": 1024,
28
+ "n_embd": 768,
29
+ "n_head": 12,
30
+ "n_inner": null,
31
+ "n_layer": 6,
32
+ "n_positions": 1024,
33
+ "pad_token_id": 3,
34
+ "reorder_and_upcast_attn": false,
35
+ "resid_pdrop": 0.1,
36
+ "scale_attn_by_inverse_layer_idx": false,
37
+ "scale_attn_weights": true,
38
+ "summary_activation": null,
39
+ "summary_first_dropout": 0.1,
40
+ "summary_proj_to_labels": true,
41
+ "summary_type": "cls_index",
42
+ "summary_use_proj": true,
43
+ "task_specific_params": {
44
+ "text-generation": {
45
+ "do_sample": true,
46
+ "max_length": 50
47
+ }
48
+ },
49
+ "transformers_version": "4.28.1",
50
+ "use_cache": true,
51
+ "vocab_size": 30000
52
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 50,
7
+ "pad_token_id": 3,
8
+ "transformers_version": "4.28.1"
9
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3f75b590baa62b8099ee67c4c4c637089385611ccb93759010b0848a320924
3
+ size 357679600