Hieu-Hien commited on
Commit
ee20e85
·
verified ·
1 Parent(s): 7929cd2

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<CTX>": 50266,
3
+ "<PS>": 50265,
4
+ "<SEP>": 50267
5
+ }
all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_train_loss": 0.04834188323334924, "eval_epoch": 49, "eval_step": 35000}
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.44.2",
73
+ "use_cache": true,
74
+ "vocab_size": 50268
75
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.44.2"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb495b43c9853ea48e8f17b1efc48c5d21170d22530d213098115435e852639
3
+ size 557921848
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
summarization_no_trainer/1727493994.5291088/events.out.tfevents.1727493994.node-dgx001.3757216.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e842c3b327781bab16b18365ac662675d67f47c2d20f410bc0d14115ae746880
3
+ size 2025
summarization_no_trainer/1727493994.5401182/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adv_change_rate: 0.2
2
+ adv_init_mag: 0.05
3
+ adv_lr: 0.03
4
+ adv_max_norm: 0
5
+ adv_norm_type: l2
6
+ adv_steps: 2
7
+ checkpointing_steps: null
8
+ config_name: null
9
+ dataset_config_name: null
10
+ dataset_name: conv_ai_2
11
+ do_eval: false
12
+ do_predict: false
13
+ do_train: true
14
+ gradient_accumulation_steps: 1
15
+ hub_model_id: null
16
+ hub_token: null
17
+ ignore_pad_token_for_loss: true
18
+ learning_rate: 5.0e-05
19
+ lr_scheduler_type: linear
20
+ max_grad_norm: 1
21
+ max_source_length: 1024
22
+ max_target_length: 128
23
+ max_train_steps: 35000
24
+ model_name_or_path: facebook/bart-base
25
+ model_type: null
26
+ num_beams: null
27
+ num_train_epochs: 50
28
+ num_warmup_steps: 0
29
+ output_dir: checkpoint/pgd-bart-base-cv2
30
+ overwrite_cache: false
31
+ pad_to_max_length: false
32
+ per_device_eval_batch_size: 16
33
+ per_device_train_batch_size: 16
34
+ preprocessing_num_workers: null
35
+ push_to_hub: false
36
+ report_to: all
37
+ resume_from_checkpoint: null
38
+ seed: null
39
+ source_prefix: null
40
+ summary_column: null
41
+ text_column: null
42
+ tokenizer_name: null
43
+ train_file: null
44
+ trust_remote_code: false
45
+ use_slow_tokenizer: false
46
+ val_max_target_length: 30
47
+ validation_file: null
48
+ weight_decay: 0.0
49
+ with_tracking: true
summarization_no_trainer/1727676557.254271/events.out.tfevents.1727676557.node-dgx001.2394869.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0878902b5d3381d032fd9db6ec78653a62c4b9dc8d6a24e4df374009c9267f5
3
+ size 2025
summarization_no_trainer/1727676557.257796/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adv_change_rate: 0.2
2
+ adv_init_mag: 0.05
3
+ adv_lr: 0.03
4
+ adv_max_norm: 0
5
+ adv_norm_type: l2
6
+ adv_steps: 2
7
+ checkpointing_steps: null
8
+ config_name: null
9
+ dataset_config_name: null
10
+ dataset_name: conv_ai_2
11
+ do_eval: false
12
+ do_predict: false
13
+ do_train: true
14
+ gradient_accumulation_steps: 1
15
+ hub_model_id: null
16
+ hub_token: null
17
+ ignore_pad_token_for_loss: true
18
+ learning_rate: 5.0e-05
19
+ lr_scheduler_type: linear
20
+ max_grad_norm: 1
21
+ max_source_length: 1024
22
+ max_target_length: 128
23
+ max_train_steps: 35000
24
+ model_name_or_path: facebook/bart-base
25
+ model_type: null
26
+ num_beams: null
27
+ num_train_epochs: 50
28
+ num_warmup_steps: 0
29
+ output_dir: checkpoint/pgd-bart-base-cv2
30
+ overwrite_cache: false
31
+ pad_to_max_length: false
32
+ per_device_eval_batch_size: 32
33
+ per_device_train_batch_size: 32
34
+ preprocessing_num_workers: null
35
+ push_to_hub: false
36
+ report_to: all
37
+ resume_from_checkpoint: null
38
+ seed: null
39
+ source_prefix: null
40
+ summary_column: null
41
+ text_column: null
42
+ tokenizer_name: null
43
+ train_file: null
44
+ trust_remote_code: false
45
+ use_slow_tokenizer: false
46
+ val_max_target_length: 30
47
+ validation_file: null
48
+ weight_decay: 0.0
49
+ with_tracking: true
summarization_no_trainer/1727676972.9772224/events.out.tfevents.1727676972.node-dgx001.2409822.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cbf04b9e66058feab80c17f629ab9da8a079d3df2cc904c41d4c56718bf1231
3
+ size 2025
summarization_no_trainer/1727676972.995761/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adv_change_rate: 0.2
2
+ adv_init_mag: 0.05
3
+ adv_lr: 0.03
4
+ adv_max_norm: 0
5
+ adv_norm_type: l2
6
+ adv_steps: 2
7
+ checkpointing_steps: null
8
+ config_name: null
9
+ dataset_config_name: null
10
+ dataset_name: conv_ai_2
11
+ do_eval: false
12
+ do_predict: false
13
+ do_train: true
14
+ gradient_accumulation_steps: 1
15
+ hub_model_id: null
16
+ hub_token: null
17
+ ignore_pad_token_for_loss: true
18
+ learning_rate: 5.0e-05
19
+ lr_scheduler_type: linear
20
+ max_grad_norm: 1
21
+ max_source_length: 1024
22
+ max_target_length: 128
23
+ max_train_steps: 35000
24
+ model_name_or_path: facebook/bart-base
25
+ model_type: null
26
+ num_beams: null
27
+ num_train_epochs: 50
28
+ num_warmup_steps: 0
29
+ output_dir: checkpoint/pgd-bart-base-cv2
30
+ overwrite_cache: false
31
+ pad_to_max_length: false
32
+ per_device_eval_batch_size: 32
33
+ per_device_train_batch_size: 32
34
+ preprocessing_num_workers: null
35
+ push_to_hub: false
36
+ report_to: all
37
+ resume_from_checkpoint: null
38
+ seed: null
39
+ source_prefix: null
40
+ summary_column: null
41
+ text_column: null
42
+ tokenizer_name: null
43
+ train_file: null
44
+ trust_remote_code: false
45
+ use_slow_tokenizer: false
46
+ val_max_target_length: 30
47
+ validation_file: null
48
+ weight_decay: 0.0
49
+ with_tracking: true
summarization_no_trainer/events.out.tfevents.1727493982.node-dgx001.3757216.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c21afff0faa706ae7e083440edb43d7885e05a017f19d45da5a606c099e593
3
+ size 88
summarization_no_trainer/events.out.tfevents.1727676546.node-dgx001.2394869.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d65985b0304a2b65329445275c4b4ef04d77d5c1ed4da8b1c35fa9014bf5fe1
3
+ size 88
summarization_no_trainer/events.out.tfevents.1727676961.node-dgx001.2409822.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e157bf17654d61430f995f9dae7f6f8e55a29c934b7eed20187a21681e8ed09
3
+ size 6969
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<PS>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "<CTX>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50267": {
61
+ "content": "<SEP>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ }
68
+ },
69
+ "bos_token": "<s>",
70
+ "clean_up_tokenization_spaces": true,
71
+ "cls_token": "<s>",
72
+ "eos_token": "</s>",
73
+ "errors": "replace",
74
+ "mask_token": "<mask>",
75
+ "model_max_length": 1000000000000000019884624838656,
76
+ "pad_token": "<pad>",
77
+ "sep_token": "</s>",
78
+ "tokenizer_class": "BartTokenizer",
79
+ "trim_offsets": true,
80
+ "unk_token": "<unk>"
81
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff