phoen1x commited on
Commit
e57e1d0
1 Parent(s): 333e60b
Files changed (3) hide show
  1. README.md +52 -1
  2. config.json +66 -0
  3. tf_model.h5 +3 -0
README.md CHANGED
@@ -1,3 +1,54 @@
1
  ---
2
- license: mit
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: T5-Finetuned-BBCNewsSummary
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
+ # T5-Finetuned-BBCNewsSummary
14
+
15
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 1.0783
18
+ - Validation Loss: 0.4735
19
+ - Train Rougel: tf.Tensor(0.18200324, shape=(), dtype=float32)
20
+ - Epoch: 0
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
40
+ - training_precision: float32
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Train Rougel | Epoch |
45
+ |:----------:|:---------------:|:----------------------------------------------:|:-----:|
46
+ | 1.0783 | 0.4735 | tf.Tensor(0.18200324, shape=(), dtype=float32) | 0 |
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.20.0
52
+ - TensorFlow 2.12.0
53
+ - Datasets 2.12.0
54
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "early_stopping": true,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "length_penalty": 2.0,
20
+ "max_length": 200,
21
+ "min_length": 30,
22
+ "model_type": "t5",
23
+ "n_positions": 512,
24
+ "no_repeat_ngram_size": 3,
25
+ "num_beams": 4,
26
+ "num_decoder_layers": 6,
27
+ "num_heads": 8,
28
+ "num_layers": 6,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "prefix": "summarize: ",
32
+ "relative_attention_max_distance": 128,
33
+ "relative_attention_num_buckets": 32,
34
+ "task_specific_params": {
35
+ "summarization": {
36
+ "early_stopping": true,
37
+ "length_penalty": 2.0,
38
+ "max_length": 200,
39
+ "min_length": 30,
40
+ "no_repeat_ngram_size": 3,
41
+ "num_beams": 4,
42
+ "prefix": "summarize: "
43
+ },
44
+ "translation_en_to_de": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to German: "
49
+ },
50
+ "translation_en_to_fr": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to French: "
55
+ },
56
+ "translation_en_to_ro": {
57
+ "early_stopping": true,
58
+ "max_length": 300,
59
+ "num_beams": 4,
60
+ "prefix": "translate English to Romanian: "
61
+ }
62
+ },
63
+ "transformers_version": "4.20.0",
64
+ "use_cache": true,
65
+ "vocab_size": 32128
66
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac72ac56253448e1184ef975df1a1a803d24519d2e2397a8677afa8e263f2001
3
+ size 242301696