Glow-01 commited on
Commit
53cb724
1 Parent(s): 3a9bd4d

End of training

Browse files
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/bart-large-cnn
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: finetuned_bart_large_custom
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # finetuned_bart_large_custom
17
+
18
+ This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 4.8324
21
+ - Rouge1: 39.9143
22
+ - Rouge2: 10.7144
23
+ - Rougel: 21.1537
24
+ - Rougelsum: 35.81
25
+ - Gen Len: 131.6667
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: 2e-05
45
+ - train_batch_size: 2
46
+ - eval_batch_size: 2
47
+ - seed: 42
48
+ - gradient_accumulation_steps: 2
49
+ - total_train_batch_size: 4
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 30
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
57
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
58
+ | No log | 1.0 | 16 | 4.3093 | 39.1367 | 9.9819 | 21.0796 | 35.3746 | 132.0741 |
59
+ | No log | 2.0 | 32 | 4.2921 | 39.0619 | 9.8356 | 21.7437 | 35.6597 | 131.7037 |
60
+ | No log | 3.0 | 48 | 4.3876 | 39.5314 | 10.337 | 21.0096 | 35.9973 | 131.2593 |
61
+ | No log | 4.0 | 64 | 4.4020 | 39.3551 | 9.9689 | 21.4343 | 35.3958 | 131.1481 |
62
+ | No log | 5.0 | 80 | 4.3744 | 39.7603 | 10.4124 | 21.6535 | 35.4996 | 132.963 |
63
+ | No log | 6.0 | 96 | 4.4821 | 39.9859 | 11.0712 | 22.2449 | 35.7868 | 132.4074 |
64
+ | No log | 7.0 | 112 | 4.6017 | 38.765 | 10.3317 | 20.9319 | 34.6675 | 132.2593 |
65
+ | No log | 8.0 | 128 | 4.4419 | 39.9964 | 10.3341 | 20.9618 | 35.8621 | 130.2222 |
66
+ | No log | 9.0 | 144 | 4.4990 | 39.8075 | 10.3829 | 21.3509 | 35.9882 | 128.7407 |
67
+ | No log | 10.0 | 160 | 4.7017 | 38.6152 | 9.9282 | 20.4588 | 34.4487 | 131.9259 |
68
+ | No log | 11.0 | 176 | 4.5497 | 39.0296 | 9.9429 | 20.8087 | 34.4624 | 132.6296 |
69
+ | No log | 12.0 | 192 | 4.7301 | 38.8819 | 9.5937 | 20.929 | 34.7983 | 131.4444 |
70
+ | No log | 13.0 | 208 | 4.5114 | 38.4163 | 9.6869 | 20.373 | 34.1491 | 123.8519 |
71
+ | No log | 14.0 | 224 | 4.7097 | 38.4294 | 9.5615 | 20.1514 | 35.0332 | 131.7407 |
72
+ | No log | 15.0 | 240 | 4.6300 | 38.9564 | 9.6386 | 20.0618 | 34.8298 | 129.963 |
73
+ | No log | 16.0 | 256 | 4.6916 | 38.5582 | 10.136 | 20.8347 | 34.4795 | 129.8519 |
74
+ | No log | 17.0 | 272 | 4.6959 | 38.3264 | 9.5281 | 20.5576 | 34.6148 | 128.2963 |
75
+ | No log | 18.0 | 288 | 4.6756 | 37.5569 | 9.123 | 19.8291 | 33.5111 | 126.6667 |
76
+ | No log | 19.0 | 304 | 4.7579 | 38.5704 | 9.3654 | 20.1826 | 34.8297 | 131.4815 |
77
+ | No log | 20.0 | 320 | 4.8128 | 40.158 | 10.3889 | 20.9267 | 36.8965 | 130.1852 |
78
+ | No log | 21.0 | 336 | 4.7659 | 39.4144 | 10.2445 | 20.4763 | 35.328 | 134.2593 |
79
+ | No log | 22.0 | 352 | 4.7983 | 40.2859 | 11.0388 | 21.1643 | 36.0311 | 131.9259 |
80
+ | No log | 23.0 | 368 | 4.7954 | 39.2676 | 10.5795 | 21.1116 | 35.3949 | 130.1481 |
81
+ | No log | 24.0 | 384 | 4.7991 | 39.8126 | 10.3955 | 21.2952 | 35.7538 | 130.5926 |
82
+ | No log | 25.0 | 400 | 4.8371 | 39.3481 | 10.2857 | 20.9862 | 35.1724 | 125.1481 |
83
+ | No log | 26.0 | 416 | 4.8589 | 40.0988 | 10.4426 | 21.7284 | 35.7289 | 130.3333 |
84
+ | No log | 27.0 | 432 | 4.8423 | 39.9233 | 10.3253 | 21.5853 | 36.1194 | 131.1111 |
85
+ | No log | 28.0 | 448 | 4.8274 | 40.0388 | 10.1713 | 20.991 | 35.3966 | 130.4444 |
86
+ | No log | 29.0 | 464 | 4.8313 | 39.8516 | 10.6207 | 21.0394 | 35.6627 | 130.8148 |
87
+ | No log | 30.0 | 480 | 4.8324 | 39.9143 | 10.7144 | 21.1537 | 35.81 | 131.6667 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - Transformers 4.37.0
93
+ - Pytorch 2.1.2
94
+ - Datasets 2.1.0
95
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "length_penalty": 2.0,
44
+ "max_length": 142,
45
+ "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.37.0",
68
+ "use_cache": true,
69
+ "vocab_size": 50264
70
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 0,
7
+ "forced_eos_token_id": 2,
8
+ "length_penalty": 2.0,
9
+ "max_length": 142,
10
+ "min_length": 56,
11
+ "no_repeat_ngram_size": 3,
12
+ "num_beams": 4,
13
+ "pad_token_id": 1,
14
+ "transformers_version": "4.37.0"
15
+ }
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 sha256:62d8da203162a28b047706ce28ac6aad203986a047ad9032da56decd50889562
3
+ size 1625422896
runs/Mar11_04-16-47_55d0af0b0666/events.out.tfevents.1710130744.55d0af0b0666.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0eeee73929d095cbd164903e26e67a1e5af0f3140d0818dda327651b80c6d7
3
+ size 21630
runs/Mar11_04-16-47_55d0af0b0666/events.out.tfevents.1710133069.55d0af0b0666.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9936d23b208e247ea7b5b15d5e7b33c76eb903addc953dfeb6957c79138f03c9
3
+ size 613
runs/Mar11_05-07-24_55d0af0b0666/events.out.tfevents.1710133662.55d0af0b0666.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74ba592669539f4dcd551e7ed9c1f3ac5b7b888b19ed8034652a61d6703b1f8
3
+ size 21658
runs/Mar11_05-07-24_55d0af0b0666/events.out.tfevents.1710135748.55d0af0b0666.34.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b22536721b2137217dc5587ff4adf406280505ce684c427e48666e9f02134a1
3
+ size 613
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
+ }
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
+ "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
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804c935f6bfd7e17fe4b01f63c524c5fafdbaa7cbc1045e1b5884f98f1ca6fd1
3
+ size 4984
vocab.json ADDED
The diff for this file is too large to render. See raw diff