Hugging Face's logo

adamjweintraut
/
bart-finetuned-eli5_lfqa

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
adamjweintraut commited on
Commit
39f8b4b
•
1 Parent(s): 58358b6

adamjweintraut/bart-finetuned-eli5_lfqa

Browse files
Files changed (18) hide show
  1. README.md +57 -0
  2. config.json +74 -0
  3. generation_config.json +13 -0
  4. model.safetensors +3 -0
  5. runs/Nov27_00-07-45_0b1296441323/events.out.tfevents.1701043666.0b1296441323.458.0 +3 -0
  6. runs/Nov27_07-02-13_0b1296441323/events.out.tfevents.1701068534.0b1296441323.458.1 +3 -0
  7. runs/Nov27_07-56-23_0b1296441323/events.out.tfevents.1701071784.0b1296441323.458.2 +3 -0
  8. runs/Nov27_08-58-29_0b1296441323/events.out.tfevents.1701075509.0b1296441323.458.3 +3 -0
  9. runs/Nov27_09-02-49_0b1296441323/events.out.tfevents.1701075770.0b1296441323.139000.0 +3 -0
  10. runs/Nov27_11-49-48_0b1296441323/events.out.tfevents.1701085788.0b1296441323.181187.0 +3 -0
  11. runs/Nov27_17-22-17_0b1296441323/events.out.tfevents.1701105738.0b1296441323.263535.0 +3 -0
  12. runs/Nov27_17-28-12_0b1296441323/events.out.tfevents.1701106093.0b1296441323.265554.0 +3 -0
  13. runs/Nov27_17-50-20_0b1296441323/events.out.tfevents.1701107421.0b1296441323.265554.1 +3 -0
  14. runs/Nov27_17-52-01_0b1296441323/events.out.tfevents.1701107521.0b1296441323.265554.2 +3 -0
  15. runs/Nov27_18-06-03_0b1296441323/events.out.tfevents.1701108363.0b1296441323.274988.0 +3 -0
  16. runs/Nov27_18-10-31_0b1296441323/events.out.tfevents.1701108632.0b1296441323.276715.0 +3 -0
  17. runs/Nov27_18-20-53_0b1296441323/events.out.tfevents.1701109253.0b1296441323.279430.0 +3 -0
  18. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-eli5_lfqa
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-eli5_lfqa
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: 2.7775
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: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 1
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.8956 | 1.0 | 1251 | 2.7775 |
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.35.2
55
+ - Pytorch 2.1.0+cu118
56
+ - Datasets 2.15.0
57
+ - Tokenizers 0.15.0
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": "4.35.2",
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": "4.35.2"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac28cc8dd2717f8346b5b740abf953488fbc7598ddbd837f2f332b5514e5a76b
3
+ size 1625426996
runs/Nov27_00-07-45_0b1296441323/events.out.tfevents.1701043666.0b1296441323.458.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23e131bfb2bcccb949d917117d93eb2bb45239361db6caa421669c98135c2a6
3
+ size 7429
runs/Nov27_07-02-13_0b1296441323/events.out.tfevents.1701068534.0b1296441323.458.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8806b9bda6b2ed7f2cebe72226361cb902abd3cec7096f4c7aee77191701d5
3
+ size 5859
runs/Nov27_07-56-23_0b1296441323/events.out.tfevents.1701071784.0b1296441323.458.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbe0b2a05e117882953855017ae7bb6082291d608f946e3bd70078e304bd880
3
+ size 5859
runs/Nov27_08-58-29_0b1296441323/events.out.tfevents.1701075509.0b1296441323.458.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82df5243f2e2c04fd8243dfb51a46c5207dfc7338e0e38a3a3f890f82c54bee6
3
+ size 5545
runs/Nov27_09-02-49_0b1296441323/events.out.tfevents.1701075770.0b1296441323.139000.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7fb011bb31c724af7b22545e818940c5c20fad35e434d2e7800c1228e21baa
3
+ size 5859
runs/Nov27_11-49-48_0b1296441323/events.out.tfevents.1701085788.0b1296441323.181187.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46110be48cf1647e4ac51d93527db7daacb9c6d8034eba1bb146caacd1fee96
3
+ size 5859
runs/Nov27_17-22-17_0b1296441323/events.out.tfevents.1701105738.0b1296441323.263535.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460b5360e1d7213c9a116888e6c6eac532b6f6c2ce27fb9dfdd6629848765dfb
3
+ size 5544
runs/Nov27_17-28-12_0b1296441323/events.out.tfevents.1701106093.0b1296441323.265554.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c190c1a6b073ec477e9d7350e384a8254b39f914fb4c9998d8426c0f4b89528a
3
+ size 5544
runs/Nov27_17-50-20_0b1296441323/events.out.tfevents.1701107421.0b1296441323.265554.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055c11ad3ec0d6fb8c1832a8851cb8d99a3c5b68200951e50eac22a5cbeaeeb6
3
+ size 5544
runs/Nov27_17-52-01_0b1296441323/events.out.tfevents.1701107521.0b1296441323.265554.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d286d45e61610f277e3c08311b3fd69572492cf84494c3620241e140f9d5b9d0
3
+ size 5544
runs/Nov27_18-06-03_0b1296441323/events.out.tfevents.1701108363.0b1296441323.274988.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc0e2e688e539c4e4ecb7cb202c4d7d7b0170a1fa6ce772205a67e2b1c678aa
3
+ size 88
runs/Nov27_18-10-31_0b1296441323/events.out.tfevents.1701108632.0b1296441323.276715.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40bf07de5955ef996abbb00669ba1e21630d509cba08eff175f9b4cbedfad96
3
+ size 5544
runs/Nov27_18-20-53_0b1296441323/events.out.tfevents.1701109253.0b1296441323.279430.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f1b94426898ca331641560d6062bc71093aa31320ca72b952b7f05645b77df
3
+ size 6483
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4afb5a09abbacc331fff79343d36a69199ff7051528e726cb2185ec59e600eea
3
+ size 4792