sibyl commited on
Commit
5993c05
1 Parent(s): 93b732d
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - gem
6
+ model_index:
7
+ - name: BART-commongen
8
+ results:
9
+ - task:
10
+ name: Sequence-to-sequence Language Modeling
11
+ type: text2text-generation
12
+ dataset:
13
+ name: gem
14
+ type: gem
15
+ args: common_gen
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # BART-commongen
22
+
23
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the gem dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 1.1263
26
+ - Spice: 0.4178
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 0.0001
46
+ - train_batch_size: 32
47
+ - eval_batch_size: 32
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 1000
52
+ - training_steps: 6317
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Spice |
57
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
58
+ | 9.0971 | 0.05 | 100 | 4.1336 | 0.3218 |
59
+ | 3.5348 | 0.09 | 200 | 1.5467 | 0.3678 |
60
+ | 1.5099 | 0.14 | 300 | 1.1280 | 0.3821 |
61
+ | 1.2395 | 0.19 | 400 | 1.1178 | 0.3917 |
62
+ | 1.1827 | 0.24 | 500 | 1.0919 | 0.4086 |
63
+ | 1.1545 | 0.28 | 600 | 1.1028 | 0.4035 |
64
+ | 1.1363 | 0.33 | 700 | 1.1021 | 0.4187 |
65
+ | 1.1156 | 0.38 | 800 | 1.1231 | 0.4103 |
66
+ | 1.1077 | 0.43 | 900 | 1.1221 | 0.4117 |
67
+ | 1.0964 | 0.47 | 1000 | 1.1169 | 0.4088 |
68
+ | 1.0704 | 0.52 | 1100 | 1.1143 | 0.4133 |
69
+ | 1.0483 | 0.57 | 1200 | 1.1085 | 0.4058 |
70
+ | 1.0556 | 0.62 | 1300 | 1.1059 | 0.4249 |
71
+ | 1.0343 | 0.66 | 1400 | 1.0992 | 0.4102 |
72
+ | 1.0123 | 0.71 | 1500 | 1.1126 | 0.4104 |
73
+ | 1.0108 | 0.76 | 1600 | 1.1140 | 0.4177 |
74
+ | 1.005 | 0.81 | 1700 | 1.1264 | 0.4078 |
75
+ | 0.9822 | 0.85 | 1800 | 1.1256 | 0.4158 |
76
+ | 0.9918 | 0.9 | 1900 | 1.1345 | 0.4118 |
77
+ | 0.9664 | 0.95 | 2000 | 1.1087 | 0.4073 |
78
+ | 0.9532 | 1.0 | 2100 | 1.1217 | 0.4063 |
79
+ | 0.8799 | 1.04 | 2200 | 1.1229 | 0.4115 |
80
+ | 0.8665 | 1.09 | 2300 | 1.1263 | 0.4178 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.9.2
86
+ - Pytorch 1.9.0+cu102
87
+ - Datasets 1.11.1.dev0
88
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-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": 1024,
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": "4.9.2",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ea4feded6288d8744f4aca916b90bded2e42592889eaf6d68e8367f12354b8
3
+ size 557979193
runs/Aug09_21-33-49_fa8375b74541/1628544834.0341637/events.out.tfevents.1628544834.fa8375b74541.61.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:678e1038f9e1eff5c5743b15ecfbc3c259f8f7c5e26566026d8f231be90692ca
3
+ size 4317
runs/Aug09_21-33-49_fa8375b74541/events.out.tfevents.1628544834.fa8375b74541.61.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb84111af615c31f99c895ef951904d1b45615c34f0b90b2a1e761a8a341b200
3
+ size 15362
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbbe5ea35b2856ba5b764d962e2bc7f7ff889311a2cf5539d0924ffab2258765
3
+ size 2735
vocab.json ADDED
The diff for this file is too large to render. See raw diff