adamjweintraut commited on
Commit
230c9bc
1 Parent(s): 37186ec

bart-finetuned-lyrlen-512

Browse files
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/bart-large
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: bart-finetuned-lyrlen-512
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-finetuned-lyrlen-512
15
+
16
+ This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.7206
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 2.221 | 0.04 | 500 | 1.9667 |
50
+ | 2.0336 | 0.08 | 1000 | 1.8762 |
51
+ | 1.9563 | 0.12 | 1500 | 1.8565 |
52
+ | 1.9555 | 0.17 | 2000 | 1.8392 |
53
+ | 1.9072 | 0.21 | 2500 | 1.8214 |
54
+ | 1.8796 | 0.25 | 3000 | 1.8246 |
55
+ | 1.8955 | 0.29 | 3500 | 1.8050 |
56
+ | 1.8254 | 0.33 | 4000 | 1.8069 |
57
+ | 1.8518 | 0.38 | 4500 | 1.7873 |
58
+ | 1.8471 | 0.42 | 5000 | 1.7880 |
59
+ | 1.8536 | 0.46 | 5500 | 1.7736 |
60
+ | 1.8075 | 0.5 | 6000 | 1.7772 |
61
+ | 1.8143 | 0.54 | 6500 | 1.7724 |
62
+ | 1.8383 | 0.58 | 7000 | 1.7670 |
63
+ | 1.746 | 0.62 | 7500 | 1.7741 |
64
+ | 1.7844 | 0.67 | 8000 | 1.7608 |
65
+ | 1.7761 | 0.71 | 8500 | 1.7680 |
66
+ | 1.7367 | 0.75 | 9000 | 1.7555 |
67
+ | 1.7656 | 0.79 | 9500 | 1.7508 |
68
+ | 1.7467 | 0.83 | 10000 | 1.7558 |
69
+ | 1.7744 | 0.88 | 10500 | 1.7449 |
70
+ | 1.7513 | 0.92 | 11000 | 1.7462 |
71
+ | 1.7482 | 0.96 | 11500 | 1.7576 |
72
+ | 1.724 | 1.0 | 12000 | 1.7525 |
73
+ | 1.7043 | 1.04 | 12500 | 1.7746 |
74
+ | 1.6869 | 1.08 | 13000 | 1.7531 |
75
+ | 1.7405 | 1.12 | 13500 | 1.7473 |
76
+ | 1.7343 | 1.17 | 14000 | 1.7396 |
77
+ | 1.649 | 1.21 | 14500 | 1.7384 |
78
+ | 1.7208 | 1.25 | 15000 | 1.7368 |
79
+ | 1.6931 | 1.29 | 15500 | 1.7404 |
80
+ | 1.5941 | 1.33 | 16000 | 1.8223 |
81
+ | 1.6651 | 1.38 | 16500 | 1.7287 |
82
+ | 1.6649 | 1.42 | 17000 | 1.7413 |
83
+ | 1.7108 | 1.46 | 17500 | 1.7304 |
84
+ | 1.713 | 1.5 | 18000 | 1.7263 |
85
+ | 1.6866 | 1.54 | 18500 | 1.7139 |
86
+ | 1.6461 | 1.58 | 19000 | 1.7221 |
87
+ | 1.6886 | 1.62 | 19500 | 1.7159 |
88
+ | 1.6511 | 1.67 | 20000 | 1.7302 |
89
+ | 1.6626 | 1.71 | 20500 | 1.7182 |
90
+ | 1.7052 | 1.75 | 21000 | 1.7163 |
91
+ | 1.6831 | 1.79 | 21500 | 1.7168 |
92
+ | 1.6057 | 1.83 | 22000 | 1.7151 |
93
+ | 1.6761 | 1.88 | 22500 | 1.7117 |
94
+ | 1.6668 | 1.92 | 23000 | 1.7164 |
95
+ | 1.612 | 1.96 | 23500 | 1.7122 |
96
+ | 1.6617 | 2.0 | 24000 | 1.7131 |
97
+ | 1.641 | 2.04 | 24500 | 1.7277 |
98
+ | 1.6595 | 2.08 | 25000 | 1.7289 |
99
+ | 1.6723 | 2.12 | 25500 | 1.7192 |
100
+ | 1.6347 | 2.17 | 26000 | 1.7259 |
101
+ | 1.6684 | 2.21 | 26500 | 1.7211 |
102
+ | 1.6098 | 2.25 | 27000 | 1.7316 |
103
+ | 1.6025 | 2.29 | 27500 | 1.7213 |
104
+ | 1.5567 | 2.33 | 28000 | 1.7238 |
105
+ | 1.6564 | 2.38 | 28500 | 1.7185 |
106
+ | 1.7078 | 2.42 | 29000 | 1.7393 |
107
+ | 1.6308 | 2.46 | 29500 | 1.7234 |
108
+ | 1.6402 | 2.5 | 30000 | 1.7319 |
109
+ | 1.6333 | 2.54 | 30500 | 1.7197 |
110
+ | 1.6249 | 2.58 | 31000 | 1.7298 |
111
+ | 1.6366 | 2.62 | 31500 | 1.7235 |
112
+ | 1.6245 | 2.67 | 32000 | 1.7289 |
113
+ | 1.6044 | 2.71 | 32500 | 1.7160 |
114
+ | 1.6095 | 2.75 | 33000 | 1.7172 |
115
+ | 1.6621 | 2.79 | 33500 | 1.7210 |
116
+ | 1.6883 | 2.83 | 34000 | 1.7169 |
117
+ | 1.6449 | 2.88 | 34500 | 1.7155 |
118
+ | 1.6439 | 2.92 | 35000 | 1.7201 |
119
+ | 1.6358 | 2.96 | 35500 | 1.7188 |
120
+ | 1.6033 | 3.0 | 36000 | 1.7206 |
121
+
122
+
123
+ ### Framework versions
124
+
125
+ - Transformers 4.39.0.dev0
126
+ - Pytorch 2.1.0.dev20230621+cu117
127
+ - Datasets 2.18.0
128
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
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": 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
+ "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
+ "num_beams": 4,
47
+ "num_hidden_layers": 12,
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": "4.39.0.dev0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
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": "4.39.0.dev0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f7b851017d62331d028f18ffb07e73b2bd94dd380479db4b4923ebee96f405
3
+ size 1625426996
runs/Mar18_05-25-37_92c4f17e2945/events.out.tfevents.1710739538.92c4f17e2945.310.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ecfe9daf69e156d41c133b1d61dc3c55e52ed8739ac7162ee4e11c5301a4a2d
3
+ size 6043
runs/Mar18_05-32-19_92c4f17e2945/events.out.tfevents.1710739939.92c4f17e2945.146068.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78653c3d39af290faf6cf90d8a16122a94f603fb5a79744fd10e91938d20df6a
3
+ size 6043
runs/Mar18_05-50-21_92c4f17e2945/events.out.tfevents.1710741021.92c4f17e2945.150465.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cef3c48ea488047dc21cc1569c5a92d5ba19cf5694cd772e0dc1a74ac1124ed
3
+ size 6043
runs/Mar18_06-00-02_92c4f17e2945/events.out.tfevents.1710741602.92c4f17e2945.150465.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f19bbd109b711ef71498b0b8c97e466e1f98c6b2d86b96e3ff684d01795aabd0
3
+ size 88
runs/Mar18_06-01-45_92c4f17e2945/events.out.tfevents.1710741706.92c4f17e2945.154608.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9f2c2072b56815503424ec0f5a37ac4814e2700bf0c4c3ae4951c797e18e67
3
+ size 6043
runs/Mar18_06-14-01_92c4f17e2945/events.out.tfevents.1710742442.92c4f17e2945.158290.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26213e20d42f44e0017a00dd75a56f51187a34648bf9ed2a1e353b9836fa2c77
3
+ size 88
runs/Mar18_06-16-46_92c4f17e2945/events.out.tfevents.1710742606.92c4f17e2945.159188.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b15934eb672ba2db34a0e113b2d353fe23839c0156c27688c61d37821a7ab00
3
+ size 25610
runs/Mar19_01-42-19_c3b1bfc63467/events.out.tfevents.1710812596.c3b1bfc63467.209.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7802c982a96223b0dc60dc992403a845805f55bafb74b576712bd7e3930c7c
3
+ size 10493
runs/Mar19_06-46-01_c3b1bfc63467/events.out.tfevents.1710830796.c3b1bfc63467.118597.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0e7047c2909a10015f1ba99d99a76d3d2919a69150bc39609aa0432a5b0a42
3
+ size 18247
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d59b57789e0457cbbcc4731527b4fc44795495c0fbfa437c26e4d33bbfb9bbb4
3
+ size 5368