assamim commited on
Commit
200c2b4
1 Parent(s): 0d6d059

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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: assamim/mt5-small-indonesian-sum
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
+ # assamim/mt5-small-indonesian-sum
14
+
15
+ This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 4.6665
18
+ - Validation Loss: 2.6526
19
+ - Train Rouge1: 19.7876
20
+ - Train Rouge2: 6.6344
21
+ - Train Rougel: 16.7880
22
+ - Train Rougelsum: 16.8459
23
+ - Train Gen Len: 18.92
24
+ - Epoch: 0
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - 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}
44
+ - training_precision: float32
45
+
46
+ ### Training results
47
+
48
+ | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
49
+ |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
50
+ | 4.6665 | 2.6526 | 19.7876 | 6.6344 | 16.7880 | 16.8459 | 18.92 | 0 |
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.19.2
56
+ - TensorFlow 2.8.0
57
+ - Datasets 2.2.2
58
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
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
+ "model_type": "mt5",
17
+ "num_decoder_layers": 8,
18
+ "num_heads": 6,
19
+ "num_layers": 8,
20
+ "pad_token_id": 0,
21
+ "relative_attention_max_distance": 128,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "tokenizer_class": "T5Tokenizer",
25
+ "transformers_version": "4.19.2",
26
+ "use_cache": true,
27
+ "vocab_size": 250112
28
+ }
logs/train/events.out.tfevents.1653153234.2f046ff2789a.72.0.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2515323e35f8956a4f2e1c43ec512723795f43b4c6ecbddedee996c359cfc8c8
3
+ size 4382193
logs/validation/events.out.tfevents.1653159778.2f046ff2789a.72.1.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4ad2a10857c9bd394d07b36ebf2c9e9690c9569c6608d497445274bd22d4f2
3
+ size 195
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 sha256:9bed6c1f63606b278c3dc2d47aaa59df26db730d06644824ec13fdab4057f26f
3
+ size 1201092992
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": "/root/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}