tanatapanun commited on
Commit
acaaecb
1 Parent(s): 046fe92

Training in progress, step 500

Browse files
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: GanjinZero/biobart-v2-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: fine-tuned-2048-inputs-30-epochs
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
+ # fine-tuned-2048-inputs-30-epochs
17
+
18
+ This model is a fine-tuned version of [GanjinZero/biobart-v2-base](https://huggingface.co/GanjinZero/biobart-v2-base) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8273
21
+ - Rouge1: 0.2933
22
+ - Rouge2: 0.1173
23
+ - Rougel: 0.2662
24
+ - Rougelsum: 0.2653
25
+ - Gen Len: 15.53
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: 8
46
+ - eval_batch_size: 8
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 30
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
56
+ | No log | 1.0 | 151 | 0.7529 | 0.2082 | 0.0781 | 0.1878 | 0.1884 | 13.16 |
57
+ | No log | 2.0 | 302 | 0.7144 | 0.2589 | 0.0817 | 0.2239 | 0.2244 | 13.76 |
58
+ | No log | 3.0 | 453 | 0.6993 | 0.2409 | 0.0773 | 0.2135 | 0.2136 | 14.52 |
59
+ | 0.7226 | 4.0 | 604 | 0.6957 | 0.2891 | 0.1014 | 0.262 | 0.2618 | 14.27 |
60
+ | 0.7226 | 5.0 | 755 | 0.7037 | 0.2925 | 0.1167 | 0.2656 | 0.267 | 14.73 |
61
+ | 0.7226 | 6.0 | 906 | 0.6971 | 0.2778 | 0.1124 | 0.2511 | 0.2501 | 14.92 |
62
+ | 0.4948 | 7.0 | 1057 | 0.7117 | 0.2816 | 0.1139 | 0.2558 | 0.2553 | 14.93 |
63
+ | 0.4948 | 8.0 | 1208 | 0.7185 | 0.2948 | 0.1192 | 0.2683 | 0.2679 | 14.45 |
64
+ | 0.4948 | 9.0 | 1359 | 0.7250 | 0.3039 | 0.1108 | 0.2748 | 0.2738 | 14.76 |
65
+ | 0.368 | 10.0 | 1510 | 0.7343 | 0.3187 | 0.1267 | 0.2921 | 0.2919 | 14.67 |
66
+ | 0.368 | 11.0 | 1661 | 0.7418 | 0.3067 | 0.1205 | 0.278 | 0.2772 | 15.23 |
67
+ | 0.368 | 12.0 | 1812 | 0.7521 | 0.3023 | 0.1134 | 0.2764 | 0.2756 | 14.91 |
68
+ | 0.368 | 13.0 | 1963 | 0.7556 | 0.2945 | 0.1143 | 0.272 | 0.2713 | 15.01 |
69
+ | 0.2865 | 14.0 | 2114 | 0.7636 | 0.3163 | 0.1246 | 0.2943 | 0.2942 | 15.44 |
70
+ | 0.2865 | 15.0 | 2265 | 0.7722 | 0.2987 | 0.1105 | 0.2705 | 0.2703 | 14.93 |
71
+ | 0.2865 | 16.0 | 2416 | 0.7788 | 0.3047 | 0.1091 | 0.2745 | 0.2744 | 15.29 |
72
+ | 0.2221 | 17.0 | 2567 | 0.7834 | 0.2973 | 0.113 | 0.2698 | 0.269 | 15.11 |
73
+ | 0.2221 | 18.0 | 2718 | 0.7905 | 0.2933 | 0.1139 | 0.2612 | 0.2595 | 15.1 |
74
+ | 0.2221 | 19.0 | 2869 | 0.7945 | 0.2936 | 0.1036 | 0.2637 | 0.2624 | 15.5 |
75
+ | 0.1825 | 20.0 | 3020 | 0.8033 | 0.3167 | 0.1216 | 0.2839 | 0.2837 | 15.54 |
76
+ | 0.1825 | 21.0 | 3171 | 0.8009 | 0.3056 | 0.1139 | 0.2753 | 0.2747 | 15.69 |
77
+ | 0.1825 | 22.0 | 3322 | 0.8085 | 0.2974 | 0.113 | 0.2632 | 0.2621 | 15.37 |
78
+ | 0.1825 | 23.0 | 3473 | 0.8120 | 0.3063 | 0.1191 | 0.2746 | 0.2749 | 15.48 |
79
+ | 0.1498 | 24.0 | 3624 | 0.8163 | 0.3045 | 0.1114 | 0.2736 | 0.2724 | 15.47 |
80
+ | 0.1498 | 25.0 | 3775 | 0.8197 | 0.3091 | 0.1147 | 0.2789 | 0.2788 | 15.51 |
81
+ | 0.1498 | 26.0 | 3926 | 0.8212 | 0.3003 | 0.1211 | 0.2715 | 0.2718 | 15.59 |
82
+ | 0.1329 | 27.0 | 4077 | 0.8230 | 0.3046 | 0.1158 | 0.2751 | 0.275 | 15.5 |
83
+ | 0.1329 | 28.0 | 4228 | 0.8250 | 0.2871 | 0.1118 | 0.2614 | 0.2599 | 15.49 |
84
+ | 0.1329 | 29.0 | 4379 | 0.8275 | 0.303 | 0.1109 | 0.2734 | 0.2737 | 15.57 |
85
+ | 0.1226 | 30.0 | 4530 | 0.8273 | 0.2933 | 0.1173 | 0.2662 | 0.2653 | 15.53 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.36.2
91
+ - Pytorch 1.12.1+cu113
92
+ - Datasets 2.15.0
93
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "GanjinZero/biobart-v2-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_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 2048,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.36.2",
72
+ "use_cache": true,
73
+ "vocab_size": 85401
74
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "no_repeat_ngram_size": 3,
8
+ "num_beams": 4,
9
+ "pad_token_id": 1,
10
+ "transformers_version": "4.36.2"
11
+ }
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:b7cd86985a9ec7ca447572602ac485d328b94f5d9fa86a1c2c64413a84424521
3
+ size 665990956
runs/Dec19_19-43-32_william-gpu-3090-10-rxldr/events.out.tfevents.1703015016.william-gpu-3090-10-rxldr.16230.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e288673745958c141416176f714c664926725be5f2ac099d74b28a442b488ac
3
+ size 5652
runs/Dec19_19-46-45_william-gpu-3090-10-rxldr/events.out.tfevents.1703015210.william-gpu-3090-10-rxldr.16318.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5694964f90c9ab7575b6ced9f18fba9422f3b5f6326c7d55c65a175856b9dea8
3
+ size 10480
runs/Dec20_00-20-07_william-gpu-3090-10-rxldr/events.out.tfevents.1703031698.william-gpu-3090-10-rxldr.17060.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2562b4139ec7b39c7dcc017bec5596e4c7476c6a58dc77716ddc868be04588b
3
+ size 23169
runs/Dec27_00-49-11_william-gpu-3090-10-rxldr/events.out.tfevents.1703638154.william-gpu-3090-10-rxldr.17060.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc65bef394cb0f3e5496a2c5ccabff1c43da68e5f79cd576488f9ba347f07de5
3
+ size 88
runs/Dec27_00-49-53_william-gpu-3090-10-rxldr/events.out.tfevents.1703638196.william-gpu-3090-10-rxldr.48922.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21dafba8c562eaa3ecc08f128371c3170992f59b6ef7dce7c2bcbaefaecbde51
3
+ size 7384
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_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2048,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0592780dbf776fde9718d021f049f161089dcfe0e0be170a4b63fbce710b0291
3
+ size 4463
vocab.json ADDED
The diff for this file is too large to render. See raw diff