End of training
Browse files- README.md +4 -8
- model.safetensors +1 -1
- runs/Apr12_13-54-57_96da360eae6f/events.out.tfevents.1712930107.96da360eae6f.222.0 +3 -0
- runs/Apr12_14-00-11_96da360eae6f/events.out.tfevents.1712930417.96da360eae6f.222.1 +3 -0
- runs/Apr12_14-22-39_96da360eae6f/events.out.tfevents.1712931765.96da360eae6f.222.2 +3 -0
- runs/Apr12_14-23-58_96da360eae6f/events.out.tfevents.1712931844.96da360eae6f.222.3 +3 -0
- runs/Apr12_14-39-13_96da360eae6f/events.out.tfevents.1712932759.96da360eae6f.222.4 +3 -0
- runs/Apr12_14-51-18_96da360eae6f/events.out.tfevents.1712933486.96da360eae6f.222.5 +3 -0
- runs/Apr12_14-53-29_96da360eae6f/events.out.tfevents.1712933623.96da360eae6f.222.6 +3 -0
- special_tokens_map.json +6 -42
- tokenizer_config.json +0 -7
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -34,23 +34,19 @@ More information needed
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
-
- learning_rate:
|
38 |
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
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 |
-
| 0.
|
50 |
-
| 0.0076 | 2.0 | 148 | 0.2757 |
|
51 |
-
| 0.0074 | 3.0 | 222 | 0.2882 |
|
52 |
-
| 0.006 | 4.0 | 296 | 0.2913 |
|
53 |
-
| 0.0057 | 5.0 | 370 | 0.2923 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2479
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 1e-05
|
38 |
- train_batch_size: 8
|
39 |
- eval_batch_size: 8
|
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 |
+
| 0.0089 | 1.0 | 74 | 0.2479 |
|
|
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625422896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2324c70205a74e3065d55248cdeb74a13cb3c6c37e24c7d5bdea0b1e933af3d1
|
3 |
size 1625422896
|
runs/Apr12_13-54-57_96da360eae6f/events.out.tfevents.1712930107.96da360eae6f.222.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b78a2b4ef790e9e2d99cfefd0d1296ac13adb16a0d3592bd263ae459882de731
|
3 |
+
size 12377
|
runs/Apr12_14-00-11_96da360eae6f/events.out.tfevents.1712930417.96da360eae6f.222.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7288102d333992279eb4d0f1b2f8052e5ac5c0b202564420ee7cd8d2381fed83
|
3 |
+
size 27103
|
runs/Apr12_14-22-39_96da360eae6f/events.out.tfevents.1712931765.96da360eae6f.222.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe74c3cbcdbdcda0606155deaa2cb9c84d5a462021c3174562d90b28209c4396
|
3 |
+
size 11405
|
runs/Apr12_14-23-58_96da360eae6f/events.out.tfevents.1712931844.96da360eae6f.222.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67c190d70719120199e1f5a363c271e3716066d555c3312ea9e64c4d0884b9cc
|
3 |
+
size 26240
|
runs/Apr12_14-39-13_96da360eae6f/events.out.tfevents.1712932759.96da360eae6f.222.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6ce66da0059f30b28e8179ee203a59ac6149ec670ae93e17956153d62e47158
|
3 |
+
size 20556
|
runs/Apr12_14-51-18_96da360eae6f/events.out.tfevents.1712933486.96da360eae6f.222.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28c263417eb5fe8cf044eabafe379631431c099f6d3b849b03db9a9ad265c7b3
|
3 |
+
size 17149
|
runs/Apr12_14-53-29_96da360eae6f/events.out.tfevents.1712933623.96da360eae6f.222.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50774c155f22db499719c65176912627743e4cc5304ccec5fc196dbba054d103
|
3 |
+
size 18798
|
special_tokens_map.json
CHANGED
@@ -1,25 +1,7 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "<s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "</s>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"mask_token": {
|
24 |
"content": "<mask>",
|
25 |
"lstrip": true,
|
@@ -27,25 +9,7 @@
|
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
},
|
30 |
-
"pad_token":
|
31 |
-
|
32 |
-
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "</s>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": true,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
-
"unk_token": {
|
45 |
-
"content": "<unk>",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": true,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false
|
50 |
-
}
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
|
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
+
"pad_token": "</s>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
tokenizer_config.json
CHANGED
@@ -48,17 +48,10 @@
|
|
48 |
"eos_token": "</s>",
|
49 |
"errors": "replace",
|
50 |
"mask_token": "<mask>",
|
51 |
-
"max_length": 1024,
|
52 |
"model_max_length": 1024,
|
53 |
-
"pad_to_multiple_of": null,
|
54 |
"pad_token": "</s>",
|
55 |
-
"pad_token_type_id": 0,
|
56 |
-
"padding_side": "right",
|
57 |
"sep_token": "</s>",
|
58 |
-
"stride": 0,
|
59 |
"tokenizer_class": "BartTokenizer",
|
60 |
"trim_offsets": true,
|
61 |
-
"truncation_side": "right",
|
62 |
-
"truncation_strategy": "longest_first",
|
63 |
"unk_token": "<unk>"
|
64 |
}
|
|
|
48 |
"eos_token": "</s>",
|
49 |
"errors": "replace",
|
50 |
"mask_token": "<mask>",
|
|
|
51 |
"model_max_length": 1024,
|
|
|
52 |
"pad_token": "</s>",
|
|
|
|
|
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 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaab8f6839611646cd1e04f0420ccbbfd656b3c0809526d65b26306384c1f39d
|
3 |
size 4920
|