Trickshotblaster commited on
Commit
36fa7ef
1 Parent(s): 6951b5c

Upload TFT5ForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +62 -0
  2. config.json +66 -0
  3. generation_config.json +13 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: leetcoder-qa
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
+ # leetcoder-qa
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: 4.1922
18
+ - Validation Loss: 3.8900
19
+ - Epoch: 9
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': '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': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
39
+ - training_precision: float32
40
+
41
+ ### Training results
42
+
43
+ | Train Loss | Validation Loss | Epoch |
44
+ |:----------:|:---------------:|:-----:|
45
+ | 6.3985 | 4.7493 | 0 |
46
+ | 4.8760 | 4.4969 | 1 |
47
+ | 4.7016 | 4.3654 | 2 |
48
+ | 4.5848 | 4.2650 | 3 |
49
+ | 4.5086 | 4.1827 | 4 |
50
+ | 4.4307 | 4.1106 | 5 |
51
+ | 4.3581 | 4.0471 | 6 |
52
+ | 4.2923 | 3.9898 | 7 |
53
+ | 4.2397 | 3.9375 | 8 |
54
+ | 4.1922 | 3.8900 | 9 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.30.1
60
+ - TensorFlow 2.12.0
61
+ - Datasets 2.12.0
62
+ - Tokenizers 0.13.3
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": "4.30.1",
64
+ "use_cache": true,
65
+ "vocab_size": 32128
66
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "early_stopping": true,
5
+ "eos_token_id": 1,
6
+ "length_penalty": 2.0,
7
+ "max_length": 200,
8
+ "min_length": 30,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 0,
12
+ "transformers_version": "4.30.1"
13
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f900ac2d9e37b6bd915daa4694584651c13b59e9890ff9b8a43187818019061
3
+ size 373902664