assamim commited on
Commit
0d75c74
1 Parent(s): 6f1be7a

Training in progress epoch 0

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_keras_callback
4
+ model-index:
5
+ - name: assamim/mt5-pukulenam-summarization
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
+ # assamim/mt5-pukulenam-summarization
13
+
14
+ This model is a fine-tuned version of [csebuetnlp/mT5_multilingual_XLSum](https://huggingface.co/csebuetnlp/mT5_multilingual_XLSum) on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Train Loss: 1.7639
17
+ - Validation Loss: 1.8188
18
+ - Train Rouge1: 36.5639
19
+ - Train Rouge2: 17.0888
20
+ - Train Rougel: 31.0462
21
+ - Train Rougelsum: 31.1825
22
+ - Train Gen Len: 30.735
23
+ - Epoch: 0
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - 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': 0.01}
43
+ - training_precision: float32
44
+
45
+ ### Training results
46
+
47
+ | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
48
+ |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
49
+ | 1.7639 | 1.8188 | 36.5639 | 17.0888 | 31.0462 | 31.1825 | 30.735 | 0 |
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.19.2
55
+ - TensorFlow 2.8.2
56
+ - Datasets 2.2.2
57
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "length_penalty": 0.6,
17
+ "max_length": 84,
18
+ "model_type": "mt5",
19
+ "no_repeat_ngram_size": 2,
20
+ "num_beams": 4,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "T5Tokenizer",
30
+ "transformers_version": "4.19.2",
31
+ "use_cache": true,
32
+ "vocab_size": 250112
33
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c36bd4556dae16c64be5d468f060cbedaab94e00a6bc574f80ea2a8a562adf3
3
+ size 2330179728
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faaa6405f5f79c9e788c7980874a9a3b5b0aea07b53bd9243bf1abb8f5c49c81
3
+ size 16330467
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "csebuetnlp/mT5_multilingual_XLSum", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}