roequitz commited on
Commit
26ec202
1 Parent(s): c942bb1

End of training

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: sshleifer/distilbart-xsum-12-6
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: bart-abs-1509-0313-lr-3e-05-bs-2-maxep-10
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # bart-abs-1509-0313-lr-3e-05-bs-2-maxep-10
15
+
16
+ This model is a fine-tuned version of [sshleifer/distilbart-xsum-12-6](https://huggingface.co/sshleifer/distilbart-xsum-12-6) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 4.0180
19
+ - Rouge/rouge1: 0.4724
20
+ - Rouge/rouge2: 0.2094
21
+ - Rouge/rougel: 0.3964
22
+ - Rouge/rougelsum: 0.3976
23
+ - Bertscore/bertscore-precision: 0.8964
24
+ - Bertscore/bertscore-recall: 0.8932
25
+ - Bertscore/bertscore-f1: 0.8947
26
+ - Meteor: 0.4217
27
+ - Gen Len: 36.8818
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 3e-05
47
+ - train_batch_size: 2
48
+ - eval_batch_size: 2
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 10
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Rouge/rouge1 | Rouge/rouge2 | Rouge/rougel | Rouge/rougelsum | Bertscore/bertscore-precision | Bertscore/bertscore-recall | Bertscore/bertscore-f1 | Meteor | Gen Len |
58
+ |:-------------:|:-----:|:----:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-----------------------------:|:--------------------------:|:----------------------:|:------:|:-------:|
59
+ | 0.6813 | 1.0 | 434 | 2.4588 | 0.4636 | 0.2101 | 0.3907 | 0.3921 | 0.8975 | 0.8904 | 0.8937 | 0.4099 | 35.0727 |
60
+ | 0.6702 | 2.0 | 868 | 2.5377 | 0.4448 | 0.1862 | 0.3725 | 0.3735 | 0.8942 | 0.8887 | 0.8913 | 0.3825 | 35.7273 |
61
+ | 0.4591 | 3.0 | 1302 | 2.8762 | 0.4533 | 0.1916 | 0.3767 | 0.3778 | 0.8961 | 0.8897 | 0.8928 | 0.3911 | 35.2091 |
62
+ | 0.3165 | 4.0 | 1736 | 3.2129 | 0.4519 | 0.1976 | 0.3803 | 0.3806 | 0.8936 | 0.891 | 0.8922 | 0.4023 | 37.6364 |
63
+ | 0.2222 | 5.0 | 2170 | 3.4971 | 0.47 | 0.2049 | 0.392 | 0.3924 | 0.8959 | 0.8926 | 0.8941 | 0.4107 | 36.5545 |
64
+ | 0.1596 | 6.0 | 2604 | 3.6405 | 0.4607 | 0.2101 | 0.3853 | 0.3879 | 0.8943 | 0.8908 | 0.8924 | 0.4021 | 37.2273 |
65
+ | 0.1166 | 7.0 | 3038 | 3.7827 | 0.4759 | 0.2191 | 0.4086 | 0.4106 | 0.8988 | 0.8928 | 0.8956 | 0.4173 | 35.5727 |
66
+ | 0.0891 | 8.0 | 3472 | 3.9388 | 0.4677 | 0.2047 | 0.3905 | 0.3925 | 0.8933 | 0.8927 | 0.8929 | 0.417 | 38.7 |
67
+ | 0.0695 | 9.0 | 3906 | 3.9583 | 0.4775 | 0.2116 | 0.4032 | 0.4051 | 0.8981 | 0.8931 | 0.8955 | 0.4228 | 36.3182 |
68
+ | 0.0592 | 10.0 | 4340 | 4.0180 | 0.4724 | 0.2094 | 0.3964 | 0.3976 | 0.8964 | 0.8932 | 0.8947 | 0.4217 | 36.8818 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.44.0
74
+ - Pytorch 2.4.0
75
+ - Datasets 2.21.0
76
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sshleifer/distilbart-xsum-12-6",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "BartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "eos_token_ids": [
29
+ 2
30
+ ],
31
+ "extra_pos_embeddings": 2,
32
+ "forced_eos_token_id": 2,
33
+ "gradient_checkpointing": false,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "length_penalty": 0.5,
47
+ "max_length": 62,
48
+ "max_position_embeddings": 1024,
49
+ "min_length": 11,
50
+ "model_type": "bart",
51
+ "no_repeat_ngram_size": 3,
52
+ "normalize_before": false,
53
+ "normalize_embedding": true,
54
+ "num_beams": 6,
55
+ "num_hidden_layers": 12,
56
+ "output_past": true,
57
+ "pad_token_id": 1,
58
+ "prefix": " ",
59
+ "replacing_rate": 0,
60
+ "save_step": 58,
61
+ "scale_embedding": false,
62
+ "static_position_embeddings": false,
63
+ "student_decoder_layers": null,
64
+ "student_encoder_layers": null,
65
+ "task_specific_params": {},
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.44.0",
68
+ "use_cache": true,
69
+ "vocab_size": 50264
70
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "length_penalty": 0.5,
8
+ "max_length": 62,
9
+ "min_length": 11,
10
+ "no_repeat_ngram_size": 3,
11
+ "num_beams": 6,
12
+ "pad_token_id": 1,
13
+ "transformers_version": "4.44.0"
14
+ }
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 sha256:14203651334b8a4033e5d318833eb7616346aaf31de85cef7c1e0b97fd8413e9
3
+ size 1222284056
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
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 sha256:430837014bd3d4c38a418d6333059fa6471144c1409988829af2c0156d4b0821
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff