msarmento commited on
Commit
e4dd898
1 Parent(s): c207e93

Training complete

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/mt5-small
4
+ tags:
5
+ - summarization
6
+ - generated_from_trainer
7
+ metrics:
8
+ - rouge
9
+ model-index:
10
+ - name: mt5-small-finetuned-xlsum-pt
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # mt5-small-finetuned-xlsum-pt
18
+
19
+ This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.0986
22
+ - Rouge1: 16.5756
23
+ - Rouge2: 13.7639
24
+ - Rougel: 15.7445
25
+ - Rougelsum: 16.5112
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5.6e-05
45
+ - train_batch_size: 8
46
+ - eval_batch_size: 8
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 10
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|
56
+ | 0.7681 | 1.0 | 125 | 0.1393 | 12.9432 | 9.5039 | 12.2871 | 12.7291 |
57
+ | 0.5282 | 2.0 | 250 | 0.1231 | 13.4575 | 10.0697 | 12.6449 | 13.2 |
58
+ | 0.4132 | 3.0 | 375 | 0.1134 | 16.6964 | 14.0187 | 15.7338 | 16.6025 |
59
+ | 0.3534 | 4.0 | 500 | 0.1077 | 16.8961 | 14.2203 | 15.9187 | 16.7712 |
60
+ | 0.3126 | 5.0 | 625 | 0.1039 | 16.993 | 14.0876 | 15.8914 | 16.9277 |
61
+ | 0.283 | 6.0 | 750 | 0.1023 | 16.7431 | 13.9453 | 15.8758 | 16.6413 |
62
+ | 0.2675 | 7.0 | 875 | 0.1008 | 16.6566 | 13.8639 | 15.775 | 16.5481 |
63
+ | 0.2509 | 8.0 | 1000 | 0.0987 | 16.6829 | 13.935 | 15.872 | 16.6222 |
64
+ | 0.2441 | 9.0 | 1125 | 0.0987 | 16.6085 | 13.7884 | 15.7896 | 16.5412 |
65
+ | 0.2401 | 10.0 | 1250 | 0.0986 | 16.5756 | 13.7639 | 15.7445 | 16.5112 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.37.2
71
+ - Pytorch 2.1.0+cu121
72
+ - Datasets 2.17.1
73
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 8,
21
+ "num_heads": 6,
22
+ "num_layers": 8,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "tokenizer_class": "T5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.37.2",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.37.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e03c9a201208265c0e0bcd754be8b4a0253e83d1535e51ba1b3e6dc883a61058
3
+ size 1200729512
runs/Feb23_00-17-26_92ee6bb81a5e/events.out.tfevents.1708647457.92ee6bb81a5e.5245.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb31e513eb63687df7833a55c021f564b1a9c548ca08076fd1205b7c0db85db
3
+ size 21739
runs/Feb23_00-17-26_92ee6bb81a5e/events.out.tfevents.1708649376.92ee6bb81a5e.5245.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87e6619c35e3727e4bd719af90f9cd62e79272dcddc167c5b2fa62d55f4adee
3
+ size 562
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ba321e55174326871149897696a427dd068c06285e22519c973aa53b8cffde
3
+ size 16330660
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<pad>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ba8747dae917e11ce847960b972837f507d3a0c757cff9d3f59499db77c52f
3
+ size 4856