aegrif commited on
Commit
ec99223
1 Parent(s): aa4c322

Upload TFT5ForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +69 -0
  2. config.json +59 -0
  3. generation_config.json +7 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: CIS6930_DAAGR_T5_emo
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
+ # CIS6930_DAAGR_T5_emo
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: 0.3698
18
+ - Train Accuracy: 0.9584
19
+ - Validation Loss: 0.4586
20
+ - Validation Accuracy: 0.9472
21
+ - Epoch: 14
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - 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': 0.001, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
41
+ - training_precision: float32
42
+
43
+ ### Training results
44
+
45
+ | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
+ |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.5130 | 0.9390 | 0.4789 | 0.9431 | 0 |
48
+ | 0.4570 | 0.9456 | 0.4682 | 0.9446 | 1 |
49
+ | 0.4434 | 0.9477 | 0.4624 | 0.9454 | 2 |
50
+ | 0.4334 | 0.9490 | 0.4594 | 0.9459 | 3 |
51
+ | 0.4250 | 0.9503 | 0.4570 | 0.9464 | 4 |
52
+ | 0.4180 | 0.9513 | 0.4556 | 0.9466 | 5 |
53
+ | 0.4114 | 0.9523 | 0.4545 | 0.9469 | 6 |
54
+ | 0.4052 | 0.9532 | 0.4537 | 0.9471 | 7 |
55
+ | 0.3997 | 0.9540 | 0.4541 | 0.9471 | 8 |
56
+ | 0.3943 | 0.9548 | 0.4533 | 0.9473 | 9 |
57
+ | 0.3891 | 0.9556 | 0.4538 | 0.9474 | 10 |
58
+ | 0.3838 | 0.9563 | 0.4549 | 0.9474 | 11 |
59
+ | 0.3791 | 0.9570 | 0.4558 | 0.9474 | 12 |
60
+ | 0.3744 | 0.9577 | 0.4573 | 0.9473 | 13 |
61
+ | 0.3698 | 0.9584 | 0.4586 | 0.9472 | 14 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.27.4
67
+ - TensorFlow 2.11.0
68
+ - Datasets 2.11.0
69
+ - Tokenizers 0.13.2
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 6,
21
+ "num_heads": 8,
22
+ "num_layers": 6,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "transformers_version": "4.27.4",
57
+ "use_cache": true,
58
+ "vocab_size": 32128
59
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.27.4"
7
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d56c03a6c1d3166e909dcb8720eacd2b15180bbf9025f4476f72a17590aae75
3
+ size 373902664