End of training
Browse files- README.md +3 -3
- generation_config.json +2 -0
- model.safetensors +1 -1
- preprocessor_config.json +4 -4
- runs/Dec12_18-00-13_40d7ca79ae6a/events.out.tfevents.1702404014.40d7ca79ae6a.14238.1 +2 -2
- special_tokens_map.json +44 -20
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# donut-base-balancesheet
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
|
|
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 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: priteshkj/donut-base-balancesheet
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
15 |
|
16 |
# donut-base-balancesheet
|
17 |
|
18 |
+
This model is a fine-tuned version of [priteshkj/donut-base-balancesheet](https://huggingface.co/priteshkj/donut-base-balancesheet) on the imagefolder dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 500
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
generation_config.json
CHANGED
@@ -1,8 +1,10 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
|
|
4 |
"eos_token_id": 2,
|
5 |
"forced_eos_token_id": 2,
|
|
|
6 |
"pad_token_id": 1,
|
7 |
"transformers_version": "4.36.0.dev0"
|
8 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 0,
|
5 |
"eos_token_id": 2,
|
6 |
"forced_eos_token_id": 2,
|
7 |
+
"max_length": 512,
|
8 |
"pad_token_id": 1,
|
9 |
"transformers_version": "4.36.0.dev0"
|
10 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 809070744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d16f53f18892f4998269ecf6dddb912bcdb1e7091faad775fd229a553eba1006
|
3 |
size 809070744
|
preprocessor_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"processor_class": "DonutProcessor",
|
20 |
"resample": 2,
|
21 |
"rescale_factor": 0.00392156862745098,
|
22 |
-
"size":
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
}
|
|
|
19 |
"processor_class": "DonutProcessor",
|
20 |
"resample": 2,
|
21 |
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": {
|
23 |
+
"height": 960,
|
24 |
+
"width": 720
|
25 |
+
}
|
26 |
}
|
runs/Dec12_18-00-13_40d7ca79ae6a/events.out.tfevents.1702404014.40d7ca79ae6a.14238.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:894b252d86b58ee8c4601bc464147e11fe39460e2fbff84729a1ef7eea81e240
|
3 |
+
size 12290
|
special_tokens_map.json
CHANGED
@@ -1,23 +1,29 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
|
4 |
-
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "<s>",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": false,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
}
|
17 |
],
|
18 |
-
"bos_token":
|
19 |
-
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"mask_token": {
|
22 |
"content": "<mask>",
|
23 |
"lstrip": true,
|
@@ -25,7 +31,25 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false
|
27 |
},
|
28 |
-
"pad_token":
|
29 |
-
|
30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
}
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"</s>",
|
4 |
+
"<s>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<s>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"cls_token": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
"mask_token": {
|
28 |
"content": "<mask>",
|
29 |
"lstrip": true,
|
|
|
31 |
"rstrip": false,
|
32 |
"single_word": false
|
33 |
},
|
34 |
+
"pad_token": {
|
35 |
+
"content": "<pad>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
},
|
41 |
+
"sep_token": {
|
42 |
+
"content": "</s>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"unk_token": {
|
49 |
+
"content": "<unk>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": false,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
}
|
55 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -74,11 +74,18 @@
|
|
74 |
"cls_token": "<s>",
|
75 |
"eos_token": "</s>",
|
76 |
"mask_token": "<mask>",
|
|
|
77 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
78 |
"pad_token": "<pad>",
|
|
|
|
|
79 |
"processor_class": "DonutProcessor",
|
80 |
"sep_token": "</s>",
|
81 |
"sp_model_kwargs": {},
|
|
|
82 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
83 |
"unk_token": "<unk>"
|
84 |
}
|
|
|
74 |
"cls_token": "<s>",
|
75 |
"eos_token": "</s>",
|
76 |
"mask_token": "<mask>",
|
77 |
+
"max_length": 512,
|
78 |
"model_max_length": 1000000000000000019884624838656,
|
79 |
+
"pad_to_multiple_of": null,
|
80 |
"pad_token": "<pad>",
|
81 |
+
"pad_token_type_id": 0,
|
82 |
+
"padding_side": "right",
|
83 |
"processor_class": "DonutProcessor",
|
84 |
"sep_token": "</s>",
|
85 |
"sp_model_kwargs": {},
|
86 |
+
"stride": 0,
|
87 |
"tokenizer_class": "XLMRobertaTokenizer",
|
88 |
+
"truncation_side": "right",
|
89 |
+
"truncation_strategy": "longest_first",
|
90 |
"unk_token": "<unk>"
|
91 |
}
|