Commit
•
9dfcfb6
1
Parent(s):
cb0bc0a
End of training
Browse files- README.md +31 -21
- generation_config.json +0 -1
- merges.txt +0 -0
- model.safetensors +1 -1
- runs/Jul08_05-06-57_b1c2816422db/events.out.tfevents.1720415219.b1c2816422db.3255.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +1 -1
- vocab.json +0 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
3 |
base_model: facebook/bart-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: BARTModel_ExerciseLog
|
8 |
results: []
|
@@ -15,7 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,32 +42,35 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 2e-05
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
-
|
49 |
-
| No log | 1.0 |
|
50 |
-
| No log | 2.0 |
|
51 |
-
| No log | 3.0 |
|
52 |
-
| No log | 4.0 |
|
53 |
-
| No log | 5.0 | 5 |
|
54 |
-
| No log | 6.0 |
|
55 |
-
| No log | 7.0 |
|
56 |
-
| No log | 8.0 |
|
57 |
-
| No log | 9.0 |
|
58 |
-
| No log | 10.0 |
|
59 |
-
| No log | 11.0 |
|
60 |
-
| No log | 12.0 |
|
61 |
-
| No log | 13.0 |
|
62 |
-
| No log | 14.0 |
|
63 |
-
| No log | 15.0 |
|
|
|
|
|
|
|
64 |
|
65 |
|
66 |
### Framework versions
|
|
|
3 |
base_model: facebook/bart-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
model-index:
|
9 |
- name: BARTModel_ExerciseLog
|
10 |
results: []
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 4.3574
|
21 |
+
- Rouge1: 0.8531
|
22 |
+
- Rouge2: 0.581
|
23 |
+
- Rougel: 0.8531
|
24 |
+
- Rougelsum: 0.8531
|
25 |
+
- Gen Len: 7.2857
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
42 |
|
43 |
The following hyperparameters were used during training:
|
44 |
- learning_rate: 2e-05
|
45 |
+
- train_batch_size: 16
|
46 |
+
- eval_batch_size: 16
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 18
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
56 |
+
| No log | 1.0 | 2 | 7.5886 | 0.4437 | 0.1117 | 0.4458 | 0.4459 | 16.5714 |
|
57 |
+
| No log | 2.0 | 4 | 6.4463 | 0.4127 | 0.1117 | 0.4136 | 0.4155 | 16.0 |
|
58 |
+
| No log | 3.0 | 6 | 5.9474 | 0.5136 | 0.0952 | 0.5102 | 0.5204 | 8.2857 |
|
59 |
+
| No log | 4.0 | 8 | 5.6884 | 0.5537 | 0.2381 | 0.5459 | 0.5459 | 8.0 |
|
60 |
+
| No log | 5.0 | 10 | 5.5303 | 0.55 | 0.2381 | 0.5452 | 0.5452 | 6.5714 |
|
61 |
+
| No log | 6.0 | 12 | 5.4149 | 0.55 | 0.2381 | 0.5452 | 0.5452 | 6.7143 |
|
62 |
+
| No log | 7.0 | 14 | 5.2489 | 0.5286 | 0.2 | 0.5197 | 0.5197 | 7.0 |
|
63 |
+
| No log | 8.0 | 16 | 5.0956 | 0.5388 | 0.2 | 0.5286 | 0.5286 | 7.0 |
|
64 |
+
| No log | 9.0 | 18 | 4.9528 | 0.5388 | 0.2 | 0.5286 | 0.5286 | 7.0 |
|
65 |
+
| No log | 10.0 | 20 | 4.8291 | 0.5388 | 0.2 | 0.5286 | 0.5286 | 7.1429 |
|
66 |
+
| No log | 11.0 | 22 | 4.7158 | 0.5748 | 0.2714 | 0.567 | 0.5667 | 7.4286 |
|
67 |
+
| No log | 12.0 | 24 | 4.6173 | 0.7388 | 0.3429 | 0.7388 | 0.7388 | 7.2857 |
|
68 |
+
| No log | 13.0 | 26 | 4.5333 | 0.8531 | 0.581 | 0.8531 | 0.8531 | 7.2857 |
|
69 |
+
| No log | 14.0 | 28 | 4.4660 | 0.8531 | 0.581 | 0.8531 | 0.8531 | 7.2857 |
|
70 |
+
| No log | 15.0 | 30 | 4.4177 | 0.8531 | 0.581 | 0.8531 | 0.8531 | 7.2857 |
|
71 |
+
| No log | 16.0 | 32 | 4.3857 | 0.8531 | 0.581 | 0.8531 | 0.8531 | 7.2857 |
|
72 |
+
| No log | 17.0 | 34 | 4.3660 | 0.8531 | 0.581 | 0.8531 | 0.8531 | 7.2857 |
|
73 |
+
| No log | 18.0 | 36 | 4.3574 | 0.8531 | 0.581 | 0.8531 | 0.8531 | 7.2857 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
generation_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"decoder_start_token_id": 2,
|
5 |
"early_stopping": true,
|
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 0,
|
3 |
"decoder_start_token_id": 2,
|
4 |
"early_stopping": true,
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557912620
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29cdae06334a4fb2b73f20701bf53cfabb2ea8a84133b57e353075e6aae27728
|
3 |
size 557912620
|
runs/Jul08_05-06-57_b1c2816422db/events.out.tfevents.1720415219.b1c2816422db.3255.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4f747cdfb259df37eab14218cbbdcd435650d860acf9ba8dd67d1e99242c8c6
|
3 |
+
size 15672
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 1024,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "BartTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76fdfd7d7b2b808c2185946ed13ef92924b603d33fe4d1f355a4cbad108ec799
|
3 |
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|