roequitz commited on
Commit
0a772df
1 Parent(s): 526c5f6

End of training

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-4-maxep-6
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-4-maxep-6
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: 2.3615
19
+ - Rouge/rouge1: 0.4759
20
+ - Rouge/rouge2: 0.2278
21
+ - Rouge/rougel: 0.407
22
+ - Rouge/rougelsum: 0.4084
23
+ - Bertscore/bertscore-precision: 0.898
24
+ - Bertscore/bertscore-recall: 0.8937
25
+ - Bertscore/bertscore-f1: 0.8957
26
+ - Meteor: 0.4311
27
+ - Gen Len: 37.0
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: 4
48
+ - eval_batch_size: 4
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 6
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
+ | 2.3606 | 1.0 | 217 | 2.0792 | 0.44 | 0.2028 | 0.3696 | 0.3707 | 0.8966 | 0.8883 | 0.8923 | 0.3866 | 37.3636 |
60
+ | 1.6544 | 2.0 | 434 | 1.9952 | 0.4521 | 0.2171 | 0.3902 | 0.3909 | 0.8991 | 0.8912 | 0.895 | 0.4007 | 34.6636 |
61
+ | 1.2907 | 3.0 | 651 | 2.0614 | 0.4661 | 0.2212 | 0.399 | 0.4008 | 0.9006 | 0.8929 | 0.8966 | 0.4128 | 35.2636 |
62
+ | 1.0179 | 4.0 | 868 | 2.1396 | 0.479 | 0.2295 | 0.4121 | 0.4137 | 0.9024 | 0.8933 | 0.8977 | 0.4142 | 34.7182 |
63
+ | 0.8112 | 5.0 | 1085 | 2.2658 | 0.4737 | 0.2237 | 0.4046 | 0.405 | 0.8989 | 0.8931 | 0.8959 | 0.4126 | 35.4273 |
64
+ | 0.6745 | 6.0 | 1302 | 2.3615 | 0.4759 | 0.2278 | 0.407 | 0.4084 | 0.898 | 0.8937 | 0.8957 | 0.4311 | 37.0 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.44.0
70
+ - Pytorch 2.4.0
71
+ - Datasets 2.21.0
72
+ - 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 sha256:99ad88b972296c01a587b369f4fd495ca187ee8301cd86745cecf9d309222ad8
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 sha256:8e468c6cd9ed0edb9fc86c65c1110330342ca7af8fb953487460ca970adf011f
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff