VictorNGomes commited on
Commit
48b8407
1 Parent(s): b2d5fc2

End of training

Browse files
README.md CHANGED
@@ -1,3 +1,54 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: google/pegasus-cnn_dailymail
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: pegasus-dailymail-pt-br
7
+ results: []
8
  ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # pegasus-dailymail-pt-br
14
+
15
+ This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 1
36
+ - eval_batch_size: 1
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 16
39
+ - total_train_batch_size: 16
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_steps: 500
43
+ - num_epochs: 1
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.36.1
52
+ - Pytorch 2.1.0+cu121
53
+ - Datasets 2.15.0
54
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/pegasus-cnn_dailymail",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "PegasusForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 16,
18
+ "decoder_start_token_id": 0,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 16,
24
+ "eos_token_id": 1,
25
+ "extra_pos_embeddings": 1,
26
+ "forced_eos_token_id": 1,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1",
30
+ "2": "LABEL_2"
31
+ },
32
+ "init_std": 0.02,
33
+ "is_encoder_decoder": true,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1,
37
+ "LABEL_2": 2
38
+ },
39
+ "length_penalty": 0.8,
40
+ "max_length": 128,
41
+ "max_position_embeddings": 1024,
42
+ "min_length": 32,
43
+ "model_type": "pegasus",
44
+ "normalize_before": true,
45
+ "normalize_embedding": false,
46
+ "num_beams": 8,
47
+ "num_hidden_layers": 16,
48
+ "pad_token_id": 0,
49
+ "scale_embedding": true,
50
+ "static_position_embeddings": true,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.36.1",
53
+ "use_cache": true,
54
+ "vocab_size": 96103
55
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 1,
6
+ "forced_eos_token_id": 1,
7
+ "length_penalty": 0.8,
8
+ "max_length": 128,
9
+ "min_length": 32,
10
+ "num_beams": 8,
11
+ "pad_token_id": 0,
12
+ "transformers_version": "4.36.1"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98de6dc2d88b10a6e8d0bd939f29843ed2c53d90f8a105db3e6fe792118f14aa
3
+ size 2283652852
runs/Dec16_01-28-12_7774d8e21ec8/events.out.tfevents.1702690112.7774d8e21ec8.21369.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30b97b56c52b1db927373961913a9fc6e8295cfcc401649acbf45a6a0b3c1ea
3
+ size 5378
runs/Dec16_01-33-16_7774d8e21ec8/events.out.tfevents.1702690406.7774d8e21ec8.21369.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380362d624023d3c630d777e267047231b360201ee92fd98a18a4aace2465cef
3
+ size 4184
runs/Dec16_01-35-27_7774d8e21ec8/events.out.tfevents.1702690539.7774d8e21ec8.23422.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01fddb9908021a431511b31b7dc5e8c7c46ba75810c1491199baea156175c557
3
+ size 5378
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8744ade2879e5f8f243f06a112155975768f36713a643ed8bf67edd5f1f6666
3
+ size 4792
vocab.txt ADDED
The diff for this file is too large to render. See raw diff