Upload 13 files
Browse files- config.json +126 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +86 -0
- trainer_state.json +412 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMv3ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"coordinate_size": 128,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"has_relative_attention_bias": true,
|
12 |
+
"has_spatial_attention_bias": true,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "others",
|
18 |
+
"1": "issuer_name",
|
19 |
+
"2": "issuer_address",
|
20 |
+
"3": "issuer_zipcode",
|
21 |
+
"4": "issuer_city",
|
22 |
+
"5": "issuer_state",
|
23 |
+
"6": "issuer_tel",
|
24 |
+
"7": "issuer_fax",
|
25 |
+
"8": "issuer_email",
|
26 |
+
"9": "issuer_id",
|
27 |
+
"10": "issuer_vat",
|
28 |
+
"11": "client_name",
|
29 |
+
"12": "client_address",
|
30 |
+
"13": "client_zipcode",
|
31 |
+
"14": "client_city",
|
32 |
+
"15": "client_state",
|
33 |
+
"16": "client_tel",
|
34 |
+
"17": "client_vat",
|
35 |
+
"18": "client_email",
|
36 |
+
"19": "doc_nr",
|
37 |
+
"20": "file_nr",
|
38 |
+
"21": "transport_date",
|
39 |
+
"22": "client_nr",
|
40 |
+
"23": "pl_nr",
|
41 |
+
"24": "transport_nr",
|
42 |
+
"25": "transport_from",
|
43 |
+
"26": "transport_to",
|
44 |
+
"27": "detail_weight_um",
|
45 |
+
"28": "detail_grossw",
|
46 |
+
"29": "detail_netw",
|
47 |
+
"30": "detail_packtype",
|
48 |
+
"31": "detail_qty",
|
49 |
+
"32": "detail_tot_qty",
|
50 |
+
"33": "detail_vol",
|
51 |
+
"34": "detail_tot_vol",
|
52 |
+
"35": "detail_vol_um",
|
53 |
+
"36": "detail_artcode",
|
54 |
+
"37": "detail_desc",
|
55 |
+
"38": "detail_packnr",
|
56 |
+
"39": "shipment_nr",
|
57 |
+
"40": "container_nr"
|
58 |
+
},
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"input_size": 224,
|
61 |
+
"intermediate_size": 3072,
|
62 |
+
"label2id": {
|
63 |
+
"client_address": 12,
|
64 |
+
"client_city": 14,
|
65 |
+
"client_email": 18,
|
66 |
+
"client_name": 11,
|
67 |
+
"client_nr": 22,
|
68 |
+
"client_state": 15,
|
69 |
+
"client_tel": 16,
|
70 |
+
"client_vat": 17,
|
71 |
+
"client_zipcode": 13,
|
72 |
+
"container_nr": 40,
|
73 |
+
"detail_artcode": 36,
|
74 |
+
"detail_desc": 37,
|
75 |
+
"detail_grossw": 28,
|
76 |
+
"detail_netw": 29,
|
77 |
+
"detail_packnr": 38,
|
78 |
+
"detail_packtype": 30,
|
79 |
+
"detail_qty": 31,
|
80 |
+
"detail_tot_qty": 32,
|
81 |
+
"detail_tot_vol": 34,
|
82 |
+
"detail_vol": 33,
|
83 |
+
"detail_vol_um": 35,
|
84 |
+
"detail_weight_um": 27,
|
85 |
+
"doc_nr": 19,
|
86 |
+
"file_nr": 20,
|
87 |
+
"issuer_address": 2,
|
88 |
+
"issuer_city": 4,
|
89 |
+
"issuer_email": 8,
|
90 |
+
"issuer_fax": 7,
|
91 |
+
"issuer_id": 9,
|
92 |
+
"issuer_name": 1,
|
93 |
+
"issuer_state": 5,
|
94 |
+
"issuer_tel": 6,
|
95 |
+
"issuer_vat": 10,
|
96 |
+
"issuer_zipcode": 3,
|
97 |
+
"others": 0,
|
98 |
+
"pl_nr": 23,
|
99 |
+
"shipment_nr": 39,
|
100 |
+
"transport_date": 21,
|
101 |
+
"transport_from": 25,
|
102 |
+
"transport_nr": 24,
|
103 |
+
"transport_to": 26
|
104 |
+
},
|
105 |
+
"layer_norm_eps": 1e-05,
|
106 |
+
"max_2d_position_embeddings": 1024,
|
107 |
+
"max_position_embeddings": 514,
|
108 |
+
"max_rel_2d_pos": 256,
|
109 |
+
"max_rel_pos": 128,
|
110 |
+
"model_type": "layoutlmv3",
|
111 |
+
"num_attention_heads": 12,
|
112 |
+
"num_channels": 3,
|
113 |
+
"num_hidden_layers": 12,
|
114 |
+
"pad_token_id": 1,
|
115 |
+
"patch_size": 16,
|
116 |
+
"rel_2d_pos_bins": 64,
|
117 |
+
"rel_pos_bins": 32,
|
118 |
+
"second_input_size": 112,
|
119 |
+
"shape_size": 128,
|
120 |
+
"text_embed": true,
|
121 |
+
"torch_dtype": "float32",
|
122 |
+
"transformers_version": "4.28.0",
|
123 |
+
"type_vocab_size": 1,
|
124 |
+
"visual_embed": true,
|
125 |
+
"vocab_size": 50265
|
126 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:427d385547ae4f341ab739e5fb1e78a409739194be3244295bf6d7657bd358f4
|
3 |
+
size 1007719930
|
preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"feature_extractor_type": "LayoutLMv3FeatureExtractor",
|
7 |
+
"image_mean": [
|
8 |
+
0.5,
|
9 |
+
0.5,
|
10 |
+
0.5
|
11 |
+
],
|
12 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
13 |
+
"image_std": [
|
14 |
+
0.5,
|
15 |
+
0.5,
|
16 |
+
0.5
|
17 |
+
],
|
18 |
+
"ocr_lang": null,
|
19 |
+
"processor_class": "LayoutLMv3Processor",
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": {
|
23 |
+
"height": 224,
|
24 |
+
"width": 224
|
25 |
+
},
|
26 |
+
"tesseract_config": ""
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ac0e611714215571de88b8abb5be806b155e173c377ae5d34632ee6f78df10e
|
3 |
+
size 503875822
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbc27a531e221708289ba8be4f043e8c5858b2d6d7e3158b16119adcda0c4e24
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83dfa121da899e973c6667babb6508df5dd22807d809ecc30a872a16ce2b0bbf
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
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,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"apply_ocr": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"cls_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"cls_token_box": [
|
22 |
+
0,
|
23 |
+
0,
|
24 |
+
0,
|
25 |
+
0
|
26 |
+
],
|
27 |
+
"eos_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "</s>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"errors": "replace",
|
36 |
+
"mask_token": {
|
37 |
+
"__type": "AddedToken",
|
38 |
+
"content": "<mask>",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"model_max_length": 512,
|
45 |
+
"only_label_first_subword": true,
|
46 |
+
"pad_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "<pad>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"pad_token_box": [
|
55 |
+
0,
|
56 |
+
0,
|
57 |
+
0,
|
58 |
+
0
|
59 |
+
],
|
60 |
+
"pad_token_label": -100,
|
61 |
+
"processor_class": "LayoutLMv3Processor",
|
62 |
+
"sep_token": {
|
63 |
+
"__type": "AddedToken",
|
64 |
+
"content": "</s>",
|
65 |
+
"lstrip": false,
|
66 |
+
"normalized": true,
|
67 |
+
"rstrip": false,
|
68 |
+
"single_word": false
|
69 |
+
},
|
70 |
+
"sep_token_box": [
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0,
|
74 |
+
0
|
75 |
+
],
|
76 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
77 |
+
"trim_offsets": true,
|
78 |
+
"unk_token": {
|
79 |
+
"__type": "AddedToken",
|
80 |
+
"content": "<unk>",
|
81 |
+
"lstrip": false,
|
82 |
+
"normalized": true,
|
83 |
+
"rstrip": false,
|
84 |
+
"single_word": false
|
85 |
+
}
|
86 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9174279061436503,
|
3 |
+
"best_model_checkpoint": "DynamicFreightPackinglist_Jun24/checkpoint-3000",
|
4 |
+
"epoch": 2.657218777679362,
|
5 |
+
"global_step": 3000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.09,
|
12 |
+
"eval_accuracy": 0.8657594809519709,
|
13 |
+
"eval_f1": 0.294485668558126,
|
14 |
+
"eval_loss": 0.6096277832984924,
|
15 |
+
"eval_precision": 0.3776119402985075,
|
16 |
+
"eval_recall": 0.24135463868352014,
|
17 |
+
"eval_runtime": 37.7163,
|
18 |
+
"eval_samples_per_second": 10.181,
|
19 |
+
"eval_steps_per_second": 5.091,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.18,
|
24 |
+
"eval_accuracy": 0.9066833175437086,
|
25 |
+
"eval_f1": 0.42788946412963086,
|
26 |
+
"eval_loss": 0.466012567281723,
|
27 |
+
"eval_precision": 0.49051950053954063,
|
28 |
+
"eval_recall": 0.37944192702122587,
|
29 |
+
"eval_runtime": 37.9564,
|
30 |
+
"eval_samples_per_second": 10.117,
|
31 |
+
"eval_steps_per_second": 5.058,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.27,
|
36 |
+
"eval_accuracy": 0.9190566416903511,
|
37 |
+
"eval_f1": 0.45627078849540204,
|
38 |
+
"eval_loss": 0.3901040554046631,
|
39 |
+
"eval_precision": 0.5035267021736001,
|
40 |
+
"eval_recall": 0.4171237777247794,
|
41 |
+
"eval_runtime": 37.9745,
|
42 |
+
"eval_samples_per_second": 10.112,
|
43 |
+
"eval_steps_per_second": 5.056,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.35,
|
48 |
+
"eval_accuracy": 0.9322768638934343,
|
49 |
+
"eval_f1": 0.5466886577010912,
|
50 |
+
"eval_loss": 0.3380320370197296,
|
51 |
+
"eval_precision": 0.5840336134453782,
|
52 |
+
"eval_recall": 0.5138325781063677,
|
53 |
+
"eval_runtime": 37.9718,
|
54 |
+
"eval_samples_per_second": 10.113,
|
55 |
+
"eval_steps_per_second": 5.056,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.44,
|
60 |
+
"learning_rate": 8.333333333333334e-06,
|
61 |
+
"loss": 0.4269,
|
62 |
+
"step": 500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.44,
|
66 |
+
"eval_accuracy": 0.9360233112278586,
|
67 |
+
"eval_f1": 0.5705544933078396,
|
68 |
+
"eval_loss": 0.2771761417388916,
|
69 |
+
"eval_precision": 0.6128148959474261,
|
70 |
+
"eval_recall": 0.5337467207250179,
|
71 |
+
"eval_runtime": 38.0237,
|
72 |
+
"eval_samples_per_second": 10.099,
|
73 |
+
"eval_steps_per_second": 5.049,
|
74 |
+
"step": 500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.53,
|
78 |
+
"eval_accuracy": 0.9542962133608934,
|
79 |
+
"eval_f1": 0.6891029650944577,
|
80 |
+
"eval_loss": 0.2250644564628601,
|
81 |
+
"eval_precision": 0.7247368421052631,
|
82 |
+
"eval_recall": 0.6568089673264965,
|
83 |
+
"eval_runtime": 37.8718,
|
84 |
+
"eval_samples_per_second": 10.139,
|
85 |
+
"eval_steps_per_second": 5.07,
|
86 |
+
"step": 600
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.62,
|
90 |
+
"eval_accuracy": 0.9598082278299314,
|
91 |
+
"eval_f1": 0.730193368491241,
|
92 |
+
"eval_loss": 0.2054944485425949,
|
93 |
+
"eval_precision": 0.7425718160522747,
|
94 |
+
"eval_recall": 0.7182208442642499,
|
95 |
+
"eval_runtime": 37.7502,
|
96 |
+
"eval_samples_per_second": 10.172,
|
97 |
+
"eval_steps_per_second": 5.086,
|
98 |
+
"step": 700
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.71,
|
102 |
+
"eval_accuracy": 0.9699853587115667,
|
103 |
+
"eval_f1": 0.7988021024324654,
|
104 |
+
"eval_loss": 0.16418181359767914,
|
105 |
+
"eval_precision": 0.819332998996991,
|
106 |
+
"eval_recall": 0.7792749821130456,
|
107 |
+
"eval_runtime": 37.9005,
|
108 |
+
"eval_samples_per_second": 10.132,
|
109 |
+
"eval_steps_per_second": 5.066,
|
110 |
+
"step": 800
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.8,
|
114 |
+
"eval_accuracy": 0.9699710045072202,
|
115 |
+
"eval_f1": 0.7916867469879518,
|
116 |
+
"eval_loss": 0.1568066030740738,
|
117 |
+
"eval_precision": 0.7999756513270027,
|
118 |
+
"eval_recall": 0.783567851180539,
|
119 |
+
"eval_runtime": 37.6869,
|
120 |
+
"eval_samples_per_second": 10.189,
|
121 |
+
"eval_steps_per_second": 5.095,
|
122 |
+
"step": 900
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.89,
|
126 |
+
"learning_rate": 6.666666666666667e-06,
|
127 |
+
"loss": 0.2059,
|
128 |
+
"step": 1000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.89,
|
132 |
+
"eval_accuracy": 0.9699135876898344,
|
133 |
+
"eval_f1": 0.8125,
|
134 |
+
"eval_loss": 0.15771125257015228,
|
135 |
+
"eval_precision": 0.828826593897296,
|
136 |
+
"eval_recall": 0.7968041974719771,
|
137 |
+
"eval_runtime": 37.8726,
|
138 |
+
"eval_samples_per_second": 10.139,
|
139 |
+
"eval_steps_per_second": 5.07,
|
140 |
+
"step": 1000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.97,
|
144 |
+
"eval_accuracy": 0.9756839778371085,
|
145 |
+
"eval_f1": 0.844042306046341,
|
146 |
+
"eval_loss": 0.1233619749546051,
|
147 |
+
"eval_precision": 0.8660143018441852,
|
148 |
+
"eval_recall": 0.8231576436918674,
|
149 |
+
"eval_runtime": 37.8462,
|
150 |
+
"eval_samples_per_second": 10.146,
|
151 |
+
"eval_steps_per_second": 5.073,
|
152 |
+
"step": 1100
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.06,
|
156 |
+
"eval_accuracy": 0.9739327649068412,
|
157 |
+
"eval_f1": 0.8383422200678624,
|
158 |
+
"eval_loss": 0.13158756494522095,
|
159 |
+
"eval_precision": 0.852180339985218,
|
160 |
+
"eval_recall": 0.8249463391366564,
|
161 |
+
"eval_runtime": 37.9995,
|
162 |
+
"eval_samples_per_second": 10.105,
|
163 |
+
"eval_steps_per_second": 5.053,
|
164 |
+
"step": 1200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.15,
|
168 |
+
"eval_accuracy": 0.9773921281543364,
|
169 |
+
"eval_f1": 0.8546778437251422,
|
170 |
+
"eval_loss": 0.12233193963766098,
|
171 |
+
"eval_precision": 0.8777177328138746,
|
172 |
+
"eval_recall": 0.8328165990937276,
|
173 |
+
"eval_runtime": 37.8677,
|
174 |
+
"eval_samples_per_second": 10.141,
|
175 |
+
"eval_steps_per_second": 5.07,
|
176 |
+
"step": 1300
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.24,
|
180 |
+
"eval_accuracy": 0.9784830476846669,
|
181 |
+
"eval_f1": 0.8620398310199154,
|
182 |
+
"eval_loss": 0.1114952489733696,
|
183 |
+
"eval_precision": 0.8726783968719453,
|
184 |
+
"eval_recall": 0.8516575244455045,
|
185 |
+
"eval_runtime": 37.8077,
|
186 |
+
"eval_samples_per_second": 10.157,
|
187 |
+
"eval_steps_per_second": 5.078,
|
188 |
+
"step": 1400
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.33,
|
192 |
+
"learning_rate": 5e-06,
|
193 |
+
"loss": 0.1384,
|
194 |
+
"step": 1500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.33,
|
198 |
+
"eval_accuracy": 0.9778801711021158,
|
199 |
+
"eval_f1": 0.8650332474689989,
|
200 |
+
"eval_loss": 0.10301075130701065,
|
201 |
+
"eval_precision": 0.8691465029493198,
|
202 |
+
"eval_recall": 0.8609587407584068,
|
203 |
+
"eval_runtime": 37.7478,
|
204 |
+
"eval_samples_per_second": 10.173,
|
205 |
+
"eval_steps_per_second": 5.086,
|
206 |
+
"step": 1500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.42,
|
210 |
+
"eval_accuracy": 0.9811529296931071,
|
211 |
+
"eval_f1": 0.8748258947495913,
|
212 |
+
"eval_loss": 0.09539026767015457,
|
213 |
+
"eval_precision": 0.8887658422542144,
|
214 |
+
"eval_recall": 0.8613164798473647,
|
215 |
+
"eval_runtime": 37.6325,
|
216 |
+
"eval_samples_per_second": 10.204,
|
217 |
+
"eval_steps_per_second": 5.102,
|
218 |
+
"step": 1600
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.51,
|
222 |
+
"eval_accuracy": 0.9819711193408549,
|
223 |
+
"eval_f1": 0.8838249516441005,
|
224 |
+
"eval_loss": 0.09302261471748352,
|
225 |
+
"eval_precision": 0.8961755332189262,
|
226 |
+
"eval_recall": 0.8718101597901264,
|
227 |
+
"eval_runtime": 37.72,
|
228 |
+
"eval_samples_per_second": 10.18,
|
229 |
+
"eval_steps_per_second": 5.09,
|
230 |
+
"step": 1700
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.59,
|
234 |
+
"eval_accuracy": 0.9812821175322252,
|
235 |
+
"eval_f1": 0.8815182901275221,
|
236 |
+
"eval_loss": 0.09258309751749039,
|
237 |
+
"eval_precision": 0.8851749428880606,
|
238 |
+
"eval_recall": 0.8778917243024088,
|
239 |
+
"eval_runtime": 37.682,
|
240 |
+
"eval_samples_per_second": 10.191,
|
241 |
+
"eval_steps_per_second": 5.095,
|
242 |
+
"step": 1800
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.68,
|
246 |
+
"eval_accuracy": 0.9810380960583355,
|
247 |
+
"eval_f1": 0.8837905834431532,
|
248 |
+
"eval_loss": 0.0902891755104065,
|
249 |
+
"eval_precision": 0.8879393355801637,
|
250 |
+
"eval_recall": 0.8796804197471977,
|
251 |
+
"eval_runtime": 37.6694,
|
252 |
+
"eval_samples_per_second": 10.194,
|
253 |
+
"eval_steps_per_second": 5.097,
|
254 |
+
"step": 1900
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.77,
|
258 |
+
"learning_rate": 3.3333333333333333e-06,
|
259 |
+
"loss": 0.0968,
|
260 |
+
"step": 2000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.77,
|
264 |
+
"eval_accuracy": 0.9826314127407918,
|
265 |
+
"eval_f1": 0.8884760592077666,
|
266 |
+
"eval_loss": 0.08607935905456543,
|
267 |
+
"eval_precision": 0.8930249367546079,
|
268 |
+
"eval_recall": 0.8839732888146912,
|
269 |
+
"eval_runtime": 37.6927,
|
270 |
+
"eval_samples_per_second": 10.188,
|
271 |
+
"eval_steps_per_second": 5.094,
|
272 |
+
"step": 2000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.86,
|
276 |
+
"eval_accuracy": 0.9845692303275629,
|
277 |
+
"eval_f1": 0.8967495219885278,
|
278 |
+
"eval_loss": 0.07529100030660629,
|
279 |
+
"eval_precision": 0.8986826347305389,
|
280 |
+
"eval_recall": 0.8948247078464107,
|
281 |
+
"eval_runtime": 37.5991,
|
282 |
+
"eval_samples_per_second": 10.213,
|
283 |
+
"eval_steps_per_second": 5.107,
|
284 |
+
"step": 2100
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.95,
|
288 |
+
"eval_accuracy": 0.9830046220537996,
|
289 |
+
"eval_f1": 0.8961644162982435,
|
290 |
+
"eval_loss": 0.08021637052297592,
|
291 |
+
"eval_precision": 0.8979885057471264,
|
292 |
+
"eval_recall": 0.8943477223944669,
|
293 |
+
"eval_runtime": 37.5671,
|
294 |
+
"eval_samples_per_second": 10.222,
|
295 |
+
"eval_steps_per_second": 5.111,
|
296 |
+
"step": 2200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.04,
|
300 |
+
"eval_accuracy": 0.9849137312318779,
|
301 |
+
"eval_f1": 0.9005910800644815,
|
302 |
+
"eval_loss": 0.07370590418577194,
|
303 |
+
"eval_precision": 0.9018294870261868,
|
304 |
+
"eval_recall": 0.899356069639876,
|
305 |
+
"eval_runtime": 37.6512,
|
306 |
+
"eval_samples_per_second": 10.199,
|
307 |
+
"eval_steps_per_second": 5.099,
|
308 |
+
"step": 2300
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 2.13,
|
312 |
+
"eval_accuracy": 0.9839807079493583,
|
313 |
+
"eval_f1": 0.9032528103324563,
|
314 |
+
"eval_loss": 0.07483410835266113,
|
315 |
+
"eval_precision": 0.9058527224754138,
|
316 |
+
"eval_recall": 0.9006677796327212,
|
317 |
+
"eval_runtime": 37.6471,
|
318 |
+
"eval_samples_per_second": 10.2,
|
319 |
+
"eval_steps_per_second": 5.1,
|
320 |
+
"step": 2400
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.21,
|
324 |
+
"learning_rate": 1.6666666666666667e-06,
|
325 |
+
"loss": 0.0918,
|
326 |
+
"step": 2500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.21,
|
330 |
+
"eval_accuracy": 0.985301294749232,
|
331 |
+
"eval_f1": 0.907269366092194,
|
332 |
+
"eval_loss": 0.07416214793920517,
|
333 |
+
"eval_precision": 0.9074317070261243,
|
334 |
+
"eval_recall": 0.9071070832339614,
|
335 |
+
"eval_runtime": 37.7271,
|
336 |
+
"eval_samples_per_second": 10.178,
|
337 |
+
"eval_steps_per_second": 5.089,
|
338 |
+
"step": 2500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.3,
|
342 |
+
"eval_accuracy": 0.986693652570838,
|
343 |
+
"eval_f1": 0.9162969180956949,
|
344 |
+
"eval_loss": 0.06871066987514496,
|
345 |
+
"eval_precision": 0.9214905933429812,
|
346 |
+
"eval_recall": 0.911161459575483,
|
347 |
+
"eval_runtime": 37.5742,
|
348 |
+
"eval_samples_per_second": 10.22,
|
349 |
+
"eval_steps_per_second": 5.11,
|
350 |
+
"step": 2600
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.39,
|
354 |
+
"eval_accuracy": 0.9862773806447909,
|
355 |
+
"eval_f1": 0.9115873679183333,
|
356 |
+
"eval_loss": 0.06786704063415527,
|
357 |
+
"eval_precision": 0.9127316198445905,
|
358 |
+
"eval_recall": 0.9104459813975674,
|
359 |
+
"eval_runtime": 37.6479,
|
360 |
+
"eval_samples_per_second": 10.2,
|
361 |
+
"eval_steps_per_second": 5.1,
|
362 |
+
"step": 2700
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 2.48,
|
366 |
+
"eval_accuracy": 0.9870381534751529,
|
367 |
+
"eval_f1": 0.9173381080274545,
|
368 |
+
"eval_loss": 0.06866415590047836,
|
369 |
+
"eval_precision": 0.9182698052336002,
|
370 |
+
"eval_recall": 0.9164082995468639,
|
371 |
+
"eval_runtime": 37.6027,
|
372 |
+
"eval_samples_per_second": 10.212,
|
373 |
+
"eval_steps_per_second": 5.106,
|
374 |
+
"step": 2800
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.57,
|
378 |
+
"eval_accuracy": 0.9870237992708064,
|
379 |
+
"eval_f1": 0.9173084960296136,
|
380 |
+
"eval_loss": 0.06812075525522232,
|
381 |
+
"eval_precision": 0.918569891187373,
|
382 |
+
"eval_recall": 0.916050560457906,
|
383 |
+
"eval_runtime": 37.5601,
|
384 |
+
"eval_samples_per_second": 10.224,
|
385 |
+
"eval_steps_per_second": 5.112,
|
386 |
+
"step": 2900
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.66,
|
390 |
+
"learning_rate": 0.0,
|
391 |
+
"loss": 0.074,
|
392 |
+
"step": 3000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.66,
|
396 |
+
"eval_accuracy": 0.9870812160881922,
|
397 |
+
"eval_f1": 0.9174279061436503,
|
398 |
+
"eval_loss": 0.06755248457193375,
|
399 |
+
"eval_precision": 0.9186894655028099,
|
400 |
+
"eval_recall": 0.916169806820892,
|
401 |
+
"eval_runtime": 37.5655,
|
402 |
+
"eval_samples_per_second": 10.222,
|
403 |
+
"eval_steps_per_second": 5.111,
|
404 |
+
"step": 3000
|
405 |
+
}
|
406 |
+
],
|
407 |
+
"max_steps": 3000,
|
408 |
+
"num_train_epochs": 3,
|
409 |
+
"total_flos": 1592999774208000.0,
|
410 |
+
"trial_name": null,
|
411 |
+
"trial_params": null
|
412 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe16165f95e5f6938612d61b1280970df467ca0696a83008a823a9642b5bbc9
|
3 |
+
size 4088
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|