adamjweintraut
commited on
Commit
•
1ef652f
1
Parent(s):
4f12505
adamjweintraut/bart-finetuned-eli5_lfqa_best
Browse files- README.md +76 -0
- config.json +74 -0
- generation_config.json +13 -0
- model.safetensors +3 -0
- runs/Dec06_05-21-50_47083d7e7ed1/events.out.tfevents.1701840111.47083d7e7ed1.15543.0 +0 -0
- runs/Dec06_18-13-33_372ea576bba3/events.out.tfevents.1701886415.372ea576bba3.609.0 +3 -0
- runs/Dec06_22-46-41_372ea576bba3/events.out.tfevents.1701902802.372ea576bba3.609.1 +3 -0
- runs/Dec06_22-48-34_372ea576bba3/events.out.tfevents.1701902914.372ea576bba3.72821.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_best
|
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_best
|
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: 1.1110
|
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: 2
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 1.4105 | 0.1 | 500 | 1.1626 |
|
50 |
+
| 1.3387 | 0.2 | 1000 | 1.1793 |
|
51 |
+
| 1.3238 | 0.3 | 1500 | 1.1547 |
|
52 |
+
| 1.2922 | 0.4 | 2000 | 1.1490 |
|
53 |
+
| 1.207 | 0.5 | 2500 | 1.1547 |
|
54 |
+
| 1.2783 | 0.6 | 3000 | 1.1411 |
|
55 |
+
| 1.1547 | 0.7 | 3500 | 1.1533 |
|
56 |
+
| 1.2059 | 0.8 | 4000 | 1.1394 |
|
57 |
+
| 1.1619 | 0.9 | 4500 | 1.1336 |
|
58 |
+
| 1.1446 | 1.0 | 5000 | 1.1416 |
|
59 |
+
| 1.1214 | 1.1 | 5500 | 1.1288 |
|
60 |
+
| 1.0627 | 1.2 | 6000 | 1.1438 |
|
61 |
+
| 1.0972 | 1.3 | 6500 | 1.1215 |
|
62 |
+
| 1.083 | 1.4 | 7000 | 1.1511 |
|
63 |
+
| 1.0687 | 1.5 | 7500 | 1.1294 |
|
64 |
+
| 1.1295 | 1.6 | 8000 | 1.1119 |
|
65 |
+
| 1.0645 | 1.7 | 8500 | 1.1202 |
|
66 |
+
| 1.0281 | 1.8 | 9000 | 1.1277 |
|
67 |
+
| 1.0819 | 1.9 | 9500 | 1.1072 |
|
68 |
+
| 1.0306 | 2.0 | 10000 | 1.1110 |
|
69 |
+
|
70 |
+
|
71 |
+
### Framework versions
|
72 |
+
|
73 |
+
- Transformers 4.36.0.dev0
|
74 |
+
- Pytorch 2.1.0+cu118
|
75 |
+
- Datasets 2.15.0
|
76 |
+
- 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": "4.36.0.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": "4.36.0.dev0"
|
13 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3800abb297e8c39878d0b3ec8448ddb368d49802e40e99fbcd6744dee4657059
|
3 |
+
size 1625426996
|
runs/Dec06_05-21-50_47083d7e7ed1/events.out.tfevents.1701840111.47083d7e7ed1.15543.0
ADDED
File without changes
|
runs/Dec06_18-13-33_372ea576bba3/events.out.tfevents.1701886415.372ea576bba3.609.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b4305a99dfd0b0b7c5da459f14886fbb62b02e7e6bc0d9b57af648683ba5390
|
3 |
+
size 13561
|
runs/Dec06_22-46-41_372ea576bba3/events.out.tfevents.1701902802.372ea576bba3.609.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34ef8e8370ddc0a3612792a20e9e9dd05221e0ec9627630c7d77745a4870687e
|
3 |
+
size 88
|
runs/Dec06_22-48-34_372ea576bba3/events.out.tfevents.1701902914.372ea576bba3.72821.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b2b91763273564e0b1fbaf29ba3a809ac2054bc3a1bf8f13cc9f37b82291180
|
3 |
+
size 14614
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c1f88909f8a806ff759956779c08fd9d178f28e76eb8844f0b6162a34c2ce9e
|
3 |
+
size 4984
|