Load model and tokenizer
Browse files- config.json +57 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -0
- trainer_state.json +622 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Jean-Baptiste/camembert-ner",
|
3 |
+
"architectures": [
|
4 |
+
"CamembertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 5,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 6,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O+O",
|
16 |
+
"1": "I-PER+O",
|
17 |
+
"2": "I-PER+i_TITREH",
|
18 |
+
"3": "I-ACT+O",
|
19 |
+
"4": "I-DESC+O",
|
20 |
+
"5": "I-DESC+i_ACT",
|
21 |
+
"6": "I-DESC+i_TITREP",
|
22 |
+
"7": "I-SPAT+O",
|
23 |
+
"8": "I-SPAT+i_LOC",
|
24 |
+
"9": "I-SPAT+i_CARDINAL",
|
25 |
+
"10": "I-SPAT+i_FT",
|
26 |
+
"11": "I-TITRE+O"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"I-ACT+O": 3,
|
32 |
+
"I-DESC+O": 4,
|
33 |
+
"I-DESC+i_ACT": 5,
|
34 |
+
"I-DESC+i_TITREP": 6,
|
35 |
+
"I-PER+O": 1,
|
36 |
+
"I-PER+i_TITREH": 2,
|
37 |
+
"I-SPAT+O": 7,
|
38 |
+
"I-SPAT+i_CARDINAL": 9,
|
39 |
+
"I-SPAT+i_FT": 10,
|
40 |
+
"I-SPAT+i_LOC": 8,
|
41 |
+
"I-TITRE+O": 11,
|
42 |
+
"O+O": 0
|
43 |
+
},
|
44 |
+
"layer_norm_eps": 1e-05,
|
45 |
+
"max_position_embeddings": 514,
|
46 |
+
"model_type": "camembert",
|
47 |
+
"num_attention_heads": 12,
|
48 |
+
"num_hidden_layers": 12,
|
49 |
+
"output_past": true,
|
50 |
+
"pad_token_id": 1,
|
51 |
+
"position_embedding_type": "absolute",
|
52 |
+
"torch_dtype": "float32",
|
53 |
+
"transformers_version": "4.25.1",
|
54 |
+
"type_vocab_size": 1,
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 32005
|
57 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0603da8d6f4fb9962d693720a4de6a4fdc1d8d7bc2e20d880f2ee3296e724d75
|
3 |
+
size 880440037
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92ff3b759478f884454f709a354cd54d2e9e5693f84718e2528700030ad9b248
|
3 |
+
size 440233393
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbbc8d82dece716534f3d80d3ce9d5165a75b635ae4db72f1e9ade39b238d9a4
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a826b0fc0a94e03e5562c2155c2c0f1124a34fcc021ef25f5fe11fbbe7f1f537
|
3 |
+
size 623
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
3 |
+
size 810912
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": "<mask>",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"__type": "AddedToken",
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"model_max_length": 512,
|
18 |
+
"name_or_path": "Jean-Baptiste/camembert-ner",
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"sp_model_kwargs": {},
|
22 |
+
"special_tokens_map_file": "/lrde/home2/stual/.cache/huggingface/hub/models--Jean-Baptiste--camembert-ner/snapshots/9f8b2203b6a2daba1ad279ac2adb822518caa167/special_tokens_map.json",
|
23 |
+
"tokenizer_class": "CamembertTokenizer",
|
24 |
+
"unk_token": "<unk>"
|
25 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9680589680589681,
|
3 |
+
"best_model_checkpoint": "/work/stual/res_ICDAR/method_2/tmp/211-camembert-ner-joint-labelling-io/checkpoint-600",
|
4 |
+
"epoch": 1.574803149606299,
|
5 |
+
"global_step": 600,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.26,
|
12 |
+
"eval_ACT": {
|
13 |
+
"f1": 0.9012229539040452,
|
14 |
+
"number": 519,
|
15 |
+
"precision": 0.8805147058823529,
|
16 |
+
"recall": 0.9229287090558767
|
17 |
+
},
|
18 |
+
"eval_ACT_L1": {
|
19 |
+
"f1": 0.9149952244508118,
|
20 |
+
"number": 503,
|
21 |
+
"precision": 0.8805147058823529,
|
22 |
+
"recall": 0.952286282306163
|
23 |
+
},
|
24 |
+
"eval_ACT_L2": {
|
25 |
+
"f1": 0.0,
|
26 |
+
"number": 16,
|
27 |
+
"precision": 0.0,
|
28 |
+
"recall": 0.0
|
29 |
+
},
|
30 |
+
"eval_CARDINAL": {
|
31 |
+
"f1": 0.9911764705882352,
|
32 |
+
"number": 678,
|
33 |
+
"precision": 0.9882697947214076,
|
34 |
+
"recall": 0.9941002949852508
|
35 |
+
},
|
36 |
+
"eval_DESC": {
|
37 |
+
"f1": 0.0,
|
38 |
+
"number": 30,
|
39 |
+
"precision": 0.0,
|
40 |
+
"recall": 0.0
|
41 |
+
},
|
42 |
+
"eval_FT": {
|
43 |
+
"f1": 0.0,
|
44 |
+
"number": 7,
|
45 |
+
"precision": 0.0,
|
46 |
+
"recall": 0.0
|
47 |
+
},
|
48 |
+
"eval_LOC": {
|
49 |
+
"f1": 0.9370179948586118,
|
50 |
+
"number": 761,
|
51 |
+
"precision": 0.9169811320754717,
|
52 |
+
"recall": 0.9579500657030223
|
53 |
+
},
|
54 |
+
"eval_PER": {
|
55 |
+
"f1": 0.9478324761204997,
|
56 |
+
"number": 676,
|
57 |
+
"precision": 0.9416058394160584,
|
58 |
+
"recall": 0.9541420118343196
|
59 |
+
},
|
60 |
+
"eval_SPAT": {
|
61 |
+
"f1": 0.9201680672268908,
|
62 |
+
"number": 694,
|
63 |
+
"precision": 0.8950953678474114,
|
64 |
+
"recall": 0.946685878962536
|
65 |
+
},
|
66 |
+
"eval_TITRE": {
|
67 |
+
"f1": 0.0,
|
68 |
+
"number": 2,
|
69 |
+
"precision": 0.0,
|
70 |
+
"recall": 0.0
|
71 |
+
},
|
72 |
+
"eval_TITREH": {
|
73 |
+
"f1": 0.0,
|
74 |
+
"number": 33,
|
75 |
+
"precision": 0.0,
|
76 |
+
"recall": 0.0
|
77 |
+
},
|
78 |
+
"eval_TITREP": {
|
79 |
+
"f1": 0.0,
|
80 |
+
"number": 5,
|
81 |
+
"precision": 0.0,
|
82 |
+
"recall": 0.0
|
83 |
+
},
|
84 |
+
"eval_accuracy": 0.939051638530288,
|
85 |
+
"eval_accuracy-all": 0.9571747765640516,
|
86 |
+
"eval_accuracy-das": 0.9535749751737835,
|
87 |
+
"eval_accuracy-l1": 0.945506454816286,
|
88 |
+
"eval_accuracy-l2": 0.9688430983118173,
|
89 |
+
"eval_f1": 0.9351139497750036,
|
90 |
+
"eval_f1-all": 0.9303140978816655,
|
91 |
+
"eval_f1-das": 0.9332096474953618,
|
92 |
+
"eval_f1-l1": 0.920889348500517,
|
93 |
+
"eval_f1-l2": 0.9425596237823312,
|
94 |
+
"eval_loss": 0.34274226427078247,
|
95 |
+
"eval_precision": 0.9374272409778812,
|
96 |
+
"eval_precision-all": 0.9255813953488372,
|
97 |
+
"eval_precision-das": 0.9294161123429416,
|
98 |
+
"eval_precision-l1": 0.9072847682119205,
|
99 |
+
"eval_precision-l2": 0.949898442789438,
|
100 |
+
"eval_recall": 0.932812047494932,
|
101 |
+
"eval_recall-all": 0.9350954478707783,
|
102 |
+
"eval_recall-das": 0.9370342771982116,
|
103 |
+
"eval_recall-l1": 0.9349081364829396,
|
104 |
+
"eval_recall-l2": 0.9353333333333333,
|
105 |
+
"eval_runtime": 5.3519,
|
106 |
+
"eval_samples_per_second": 126.31,
|
107 |
+
"eval_steps_per_second": 8.034,
|
108 |
+
"step": 100
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.52,
|
112 |
+
"eval_ACT": {
|
113 |
+
"f1": 0.9210526315789475,
|
114 |
+
"number": 519,
|
115 |
+
"precision": 0.8990825688073395,
|
116 |
+
"recall": 0.9441233140655106
|
117 |
+
},
|
118 |
+
"eval_ACT_L1": {
|
119 |
+
"f1": 0.9351145038167938,
|
120 |
+
"number": 503,
|
121 |
+
"precision": 0.8990825688073395,
|
122 |
+
"recall": 0.974155069582505
|
123 |
+
},
|
124 |
+
"eval_ACT_L2": {
|
125 |
+
"f1": 0.0,
|
126 |
+
"number": 16,
|
127 |
+
"precision": 0.0,
|
128 |
+
"recall": 0.0
|
129 |
+
},
|
130 |
+
"eval_CARDINAL": {
|
131 |
+
"f1": 0.9911764705882352,
|
132 |
+
"number": 678,
|
133 |
+
"precision": 0.9882697947214076,
|
134 |
+
"recall": 0.9941002949852508
|
135 |
+
},
|
136 |
+
"eval_DESC": {
|
137 |
+
"f1": 0.0,
|
138 |
+
"number": 30,
|
139 |
+
"precision": 0.0,
|
140 |
+
"recall": 0.0
|
141 |
+
},
|
142 |
+
"eval_FT": {
|
143 |
+
"f1": 0.0,
|
144 |
+
"number": 7,
|
145 |
+
"precision": 0.0,
|
146 |
+
"recall": 0.0
|
147 |
+
},
|
148 |
+
"eval_LOC": {
|
149 |
+
"f1": 0.9466840052015604,
|
150 |
+
"number": 761,
|
151 |
+
"precision": 0.9369369369369369,
|
152 |
+
"recall": 0.9566360052562418
|
153 |
+
},
|
154 |
+
"eval_PER": {
|
155 |
+
"f1": 0.9691176470588235,
|
156 |
+
"number": 676,
|
157 |
+
"precision": 0.9634502923976608,
|
158 |
+
"recall": 0.9748520710059172
|
159 |
+
},
|
160 |
+
"eval_SPAT": {
|
161 |
+
"f1": 0.9319971367215462,
|
162 |
+
"number": 694,
|
163 |
+
"precision": 0.9260312944523471,
|
164 |
+
"recall": 0.9380403458213257
|
165 |
+
},
|
166 |
+
"eval_TITRE": {
|
167 |
+
"f1": 0.0,
|
168 |
+
"number": 2,
|
169 |
+
"precision": 0.0,
|
170 |
+
"recall": 0.0
|
171 |
+
},
|
172 |
+
"eval_TITREH": {
|
173 |
+
"f1": 0.5454545454545454,
|
174 |
+
"number": 33,
|
175 |
+
"precision": 0.5454545454545454,
|
176 |
+
"recall": 0.5454545454545454
|
177 |
+
},
|
178 |
+
"eval_TITREP": {
|
179 |
+
"f1": 0.0,
|
180 |
+
"number": 5,
|
181 |
+
"precision": 0.0,
|
182 |
+
"recall": 0.0
|
183 |
+
},
|
184 |
+
"eval_accuracy": 0.9461271102284012,
|
185 |
+
"eval_accuracy-all": 0.9623882820258193,
|
186 |
+
"eval_accuracy-das": 0.9620158887785502,
|
187 |
+
"eval_accuracy-l1": 0.952085402184707,
|
188 |
+
"eval_accuracy-l2": 0.9726911618669315,
|
189 |
+
"eval_f1": 0.9448275862068966,
|
190 |
+
"eval_f1-all": 0.9415204678362573,
|
191 |
+
"eval_f1-das": 0.9487511563367254,
|
192 |
+
"eval_f1-l1": 0.9355509355509356,
|
193 |
+
"eval_f1-l2": 0.9491978609625668,
|
194 |
+
"eval_loss": 0.25068724155426025,
|
195 |
+
"eval_precision": 0.9375534644995723,
|
196 |
+
"eval_precision-all": 0.9374090247452693,
|
197 |
+
"eval_precision-das": 0.9423006247703051,
|
198 |
+
"eval_precision-l1": 0.9264024704065877,
|
199 |
+
"eval_precision-l2": 0.9517426273458445,
|
200 |
+
"eval_recall": 0.952215464813206,
|
201 |
+
"eval_recall-all": 0.9456681350954479,
|
202 |
+
"eval_recall-das": 0.9552906110283159,
|
203 |
+
"eval_recall-l1": 0.9448818897637795,
|
204 |
+
"eval_recall-l2": 0.9466666666666667,
|
205 |
+
"eval_runtime": 5.4759,
|
206 |
+
"eval_samples_per_second": 123.45,
|
207 |
+
"eval_steps_per_second": 7.853,
|
208 |
+
"step": 200
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.79,
|
212 |
+
"eval_ACT": {
|
213 |
+
"f1": 0.9352380952380951,
|
214 |
+
"number": 519,
|
215 |
+
"precision": 0.9246704331450094,
|
216 |
+
"recall": 0.9460500963391136
|
217 |
+
},
|
218 |
+
"eval_ACT_L1": {
|
219 |
+
"f1": 0.9497098646034816,
|
220 |
+
"number": 503,
|
221 |
+
"precision": 0.9246704331450094,
|
222 |
+
"recall": 0.9761431411530815
|
223 |
+
},
|
224 |
+
"eval_ACT_L2": {
|
225 |
+
"f1": 0.0,
|
226 |
+
"number": 16,
|
227 |
+
"precision": 0.0,
|
228 |
+
"recall": 0.0
|
229 |
+
},
|
230 |
+
"eval_CARDINAL": {
|
231 |
+
"f1": 0.9926470588235294,
|
232 |
+
"number": 678,
|
233 |
+
"precision": 0.9897360703812317,
|
234 |
+
"recall": 0.995575221238938
|
235 |
+
},
|
236 |
+
"eval_DESC": {
|
237 |
+
"f1": 0.28571428571428575,
|
238 |
+
"number": 30,
|
239 |
+
"precision": 0.25,
|
240 |
+
"recall": 0.3333333333333333
|
241 |
+
},
|
242 |
+
"eval_FT": {
|
243 |
+
"f1": 0.0,
|
244 |
+
"number": 7,
|
245 |
+
"precision": 0.0,
|
246 |
+
"recall": 0.0
|
247 |
+
},
|
248 |
+
"eval_LOC": {
|
249 |
+
"f1": 0.9646133682830931,
|
250 |
+
"number": 761,
|
251 |
+
"precision": 0.9620915032679739,
|
252 |
+
"recall": 0.9671484888304862
|
253 |
+
},
|
254 |
+
"eval_PER": {
|
255 |
+
"f1": 0.980825958702065,
|
256 |
+
"number": 676,
|
257 |
+
"precision": 0.9779411764705882,
|
258 |
+
"recall": 0.9837278106508875
|
259 |
+
},
|
260 |
+
"eval_SPAT": {
|
261 |
+
"f1": 0.9634931997136722,
|
262 |
+
"number": 694,
|
263 |
+
"precision": 0.957325746799431,
|
264 |
+
"recall": 0.9697406340057637
|
265 |
+
},
|
266 |
+
"eval_TITRE": {
|
267 |
+
"f1": 0.0,
|
268 |
+
"number": 2,
|
269 |
+
"precision": 0.0,
|
270 |
+
"recall": 0.0
|
271 |
+
},
|
272 |
+
"eval_TITREH": {
|
273 |
+
"f1": 0.927536231884058,
|
274 |
+
"number": 33,
|
275 |
+
"precision": 0.8888888888888888,
|
276 |
+
"recall": 0.9696969696969697
|
277 |
+
},
|
278 |
+
"eval_TITREP": {
|
279 |
+
"f1": 0.0,
|
280 |
+
"number": 5,
|
281 |
+
"precision": 0.0,
|
282 |
+
"recall": 0.0
|
283 |
+
},
|
284 |
+
"eval_accuracy": 0.961519364448858,
|
285 |
+
"eval_accuracy-all": 0.972877358490566,
|
286 |
+
"eval_accuracy-das": 0.9733118172790467,
|
287 |
+
"eval_accuracy-l1": 0.9668570009930486,
|
288 |
+
"eval_accuracy-l2": 0.9788977159880834,
|
289 |
+
"eval_f1": 0.9649198787353834,
|
290 |
+
"eval_f1-all": 0.9593686056708564,
|
291 |
+
"eval_f1-das": 0.9698884758364312,
|
292 |
+
"eval_f1-l1": 0.9530966571650686,
|
293 |
+
"eval_f1-l2": 0.9674824002681863,
|
294 |
+
"eval_loss": 0.16728797554969788,
|
295 |
+
"eval_precision": 0.9620034542314335,
|
296 |
+
"eval_precision-all": 0.9549025312772766,
|
297 |
+
"eval_precision-das": 0.9677299703264095,
|
298 |
+
"eval_precision-l1": 0.9411463664278403,
|
299 |
+
"eval_precision-l2": 0.9730276466621712,
|
300 |
+
"eval_recall": 0.9678540399652477,
|
301 |
+
"eval_recall-all": 0.9638766519823788,
|
302 |
+
"eval_recall-das": 0.9720566318926974,
|
303 |
+
"eval_recall-l1": 0.9653543307086614,
|
304 |
+
"eval_recall-l2": 0.962,
|
305 |
+
"eval_runtime": 5.9254,
|
306 |
+
"eval_samples_per_second": 114.086,
|
307 |
+
"eval_steps_per_second": 7.257,
|
308 |
+
"step": 300
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.05,
|
312 |
+
"eval_ACT": {
|
313 |
+
"f1": 0.9230769230769231,
|
314 |
+
"number": 519,
|
315 |
+
"precision": 0.9101123595505618,
|
316 |
+
"recall": 0.9364161849710982
|
317 |
+
},
|
318 |
+
"eval_ACT_L1": {
|
319 |
+
"f1": 0.9373191899710704,
|
320 |
+
"number": 503,
|
321 |
+
"precision": 0.9101123595505618,
|
322 |
+
"recall": 0.9662027833001988
|
323 |
+
},
|
324 |
+
"eval_ACT_L2": {
|
325 |
+
"f1": 0.0,
|
326 |
+
"number": 16,
|
327 |
+
"precision": 0.0,
|
328 |
+
"recall": 0.0
|
329 |
+
},
|
330 |
+
"eval_CARDINAL": {
|
331 |
+
"f1": 0.9933774834437086,
|
332 |
+
"number": 678,
|
333 |
+
"precision": 0.9911894273127754,
|
334 |
+
"recall": 0.995575221238938
|
335 |
+
},
|
336 |
+
"eval_DESC": {
|
337 |
+
"f1": 0.17142857142857143,
|
338 |
+
"number": 30,
|
339 |
+
"precision": 0.15,
|
340 |
+
"recall": 0.2
|
341 |
+
},
|
342 |
+
"eval_FT": {
|
343 |
+
"f1": 0.0,
|
344 |
+
"number": 7,
|
345 |
+
"precision": 0.0,
|
346 |
+
"recall": 0.0
|
347 |
+
},
|
348 |
+
"eval_LOC": {
|
349 |
+
"f1": 0.9620418848167539,
|
350 |
+
"number": 761,
|
351 |
+
"precision": 0.9582790091264668,
|
352 |
+
"recall": 0.9658344283837057
|
353 |
+
},
|
354 |
+
"eval_PER": {
|
355 |
+
"f1": 0.9779086892488954,
|
356 |
+
"number": 676,
|
357 |
+
"precision": 0.9736070381231672,
|
358 |
+
"recall": 0.9822485207100592
|
359 |
+
},
|
360 |
+
"eval_SPAT": {
|
361 |
+
"f1": 0.9557142857142857,
|
362 |
+
"number": 694,
|
363 |
+
"precision": 0.9475920679886686,
|
364 |
+
"recall": 0.9639769452449568
|
365 |
+
},
|
366 |
+
"eval_TITRE": {
|
367 |
+
"f1": 0.0,
|
368 |
+
"number": 2,
|
369 |
+
"precision": 0.0,
|
370 |
+
"recall": 0.0
|
371 |
+
},
|
372 |
+
"eval_TITREH": {
|
373 |
+
"f1": 0.8732394366197183,
|
374 |
+
"number": 33,
|
375 |
+
"precision": 0.8157894736842105,
|
376 |
+
"recall": 0.9393939393939394
|
377 |
+
},
|
378 |
+
"eval_TITREP": {
|
379 |
+
"f1": 0.0,
|
380 |
+
"number": 5,
|
381 |
+
"precision": 0.0,
|
382 |
+
"recall": 0.0
|
383 |
+
},
|
384 |
+
"eval_accuracy": 0.9606504468718967,
|
385 |
+
"eval_accuracy-all": 0.9717601787487586,
|
386 |
+
"eval_accuracy-das": 0.9735600794438928,
|
387 |
+
"eval_accuracy-l1": 0.9641261171797418,
|
388 |
+
"eval_accuracy-l2": 0.9793942403177756,
|
389 |
+
"eval_f1": 0.9591571655361523,
|
390 |
+
"eval_f1-all": 0.9531592003502116,
|
391 |
+
"eval_f1-das": 0.9647364513734225,
|
392 |
+
"eval_f1-l1": 0.9438841479182829,
|
393 |
+
"eval_f1-l2": 0.9651707970529135,
|
394 |
+
"eval_loss": 0.15428000688552856,
|
395 |
+
"eval_precision": 0.9559838895281934,
|
396 |
+
"eval_precision-all": 0.947215777262181,
|
397 |
+
"eval_precision-das": 0.9611686390532544,
|
398 |
+
"eval_precision-l1": 0.9301732925586137,
|
399 |
+
"eval_precision-l2": 0.9697173620457604,
|
400 |
+
"eval_recall": 0.9623515783376774,
|
401 |
+
"eval_recall-all": 0.9591776798825257,
|
402 |
+
"eval_recall-das": 0.9683308494783904,
|
403 |
+
"eval_recall-l1": 0.958005249343832,
|
404 |
+
"eval_recall-l2": 0.9606666666666667,
|
405 |
+
"eval_runtime": 6.235,
|
406 |
+
"eval_samples_per_second": 108.42,
|
407 |
+
"eval_steps_per_second": 6.897,
|
408 |
+
"step": 400
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.31,
|
412 |
+
"learning_rate": 9e-05,
|
413 |
+
"loss": 0.3421,
|
414 |
+
"step": 500
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 1.31,
|
418 |
+
"eval_ACT": {
|
419 |
+
"f1": 0.9407265774378585,
|
420 |
+
"number": 519,
|
421 |
+
"precision": 0.9335863377609108,
|
422 |
+
"recall": 0.9479768786127167
|
423 |
+
},
|
424 |
+
"eval_ACT_L1": {
|
425 |
+
"f1": 0.9590643274853801,
|
426 |
+
"number": 503,
|
427 |
+
"precision": 0.9407265774378585,
|
428 |
+
"recall": 0.9781312127236581
|
429 |
+
},
|
430 |
+
"eval_ACT_L2": {
|
431 |
+
"f1": 0.0,
|
432 |
+
"number": 16,
|
433 |
+
"precision": 0.0,
|
434 |
+
"recall": 0.0
|
435 |
+
},
|
436 |
+
"eval_CARDINAL": {
|
437 |
+
"f1": 0.9933774834437086,
|
438 |
+
"number": 678,
|
439 |
+
"precision": 0.9911894273127754,
|
440 |
+
"recall": 0.995575221238938
|
441 |
+
},
|
442 |
+
"eval_DESC": {
|
443 |
+
"f1": 0.3555555555555555,
|
444 |
+
"number": 30,
|
445 |
+
"precision": 0.5333333333333333,
|
446 |
+
"recall": 0.26666666666666666
|
447 |
+
},
|
448 |
+
"eval_FT": {
|
449 |
+
"f1": 0.0,
|
450 |
+
"number": 7,
|
451 |
+
"precision": 0.0,
|
452 |
+
"recall": 0.0
|
453 |
+
},
|
454 |
+
"eval_LOC": {
|
455 |
+
"f1": 0.9546044098573281,
|
456 |
+
"number": 761,
|
457 |
+
"precision": 0.942381562099872,
|
458 |
+
"recall": 0.9671484888304862
|
459 |
+
},
|
460 |
+
"eval_PER": {
|
461 |
+
"f1": 0.9786921381337252,
|
462 |
+
"number": 676,
|
463 |
+
"precision": 0.9722627737226277,
|
464 |
+
"recall": 0.985207100591716
|
465 |
+
},
|
466 |
+
"eval_SPAT": {
|
467 |
+
"f1": 0.9524485450674237,
|
468 |
+
"number": 694,
|
469 |
+
"precision": 0.9384615384615385,
|
470 |
+
"recall": 0.9668587896253602
|
471 |
+
},
|
472 |
+
"eval_TITRE": {
|
473 |
+
"f1": 0.0,
|
474 |
+
"number": 2,
|
475 |
+
"precision": 0.0,
|
476 |
+
"recall": 0.0
|
477 |
+
},
|
478 |
+
"eval_TITREH": {
|
479 |
+
"f1": 0.8888888888888888,
|
480 |
+
"number": 33,
|
481 |
+
"precision": 0.8205128205128205,
|
482 |
+
"recall": 0.9696969696969697
|
483 |
+
},
|
484 |
+
"eval_TITREP": {
|
485 |
+
"f1": 0.0,
|
486 |
+
"number": 5,
|
487 |
+
"precision": 0.0,
|
488 |
+
"recall": 0.0
|
489 |
+
},
|
490 |
+
"eval_accuracy": 0.9608987090367428,
|
491 |
+
"eval_accuracy-all": 0.9716981132075472,
|
492 |
+
"eval_accuracy-das": 0.9724428997020854,
|
493 |
+
"eval_accuracy-l1": 0.9652432969215492,
|
494 |
+
"eval_accuracy-l2": 0.9781529294935452,
|
495 |
+
"eval_f1": 0.9627705627705628,
|
496 |
+
"eval_f1-all": 0.9579439252336449,
|
497 |
+
"eval_f1-das": 0.9659259259259259,
|
498 |
+
"eval_f1-l1": 0.9560239396304969,
|
499 |
+
"eval_f1-l2": 0.9603993344425957,
|
500 |
+
"eval_loss": 0.16323766112327576,
|
501 |
+
"eval_precision": 0.9594477998274374,
|
502 |
+
"eval_precision-all": 0.9526575660760964,
|
503 |
+
"eval_precision-das": 0.9602356406480118,
|
504 |
+
"eval_precision-l1": 0.9478844169246646,
|
505 |
+
"eval_precision-l2": 0.9588039867109635,
|
506 |
+
"eval_recall": 0.9661164205039097,
|
507 |
+
"eval_recall-all": 0.9632892804698973,
|
508 |
+
"eval_recall-das": 0.9716840536512668,
|
509 |
+
"eval_recall-l1": 0.9643044619422572,
|
510 |
+
"eval_recall-l2": 0.962,
|
511 |
+
"eval_runtime": 6.0867,
|
512 |
+
"eval_samples_per_second": 111.062,
|
513 |
+
"eval_steps_per_second": 7.065,
|
514 |
+
"step": 500
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.57,
|
518 |
+
"eval_ACT": {
|
519 |
+
"f1": 0.9512893982808023,
|
520 |
+
"number": 519,
|
521 |
+
"precision": 0.9431818181818182,
|
522 |
+
"recall": 0.9595375722543352
|
523 |
+
},
|
524 |
+
"eval_ACT_L1": {
|
525 |
+
"f1": 0.9669260700389105,
|
526 |
+
"number": 503,
|
527 |
+
"precision": 0.9466666666666667,
|
528 |
+
"recall": 0.9880715705765407
|
529 |
+
},
|
530 |
+
"eval_ACT_L2": {
|
531 |
+
"f1": 0.10526315789473684,
|
532 |
+
"number": 16,
|
533 |
+
"precision": 0.3333333333333333,
|
534 |
+
"recall": 0.0625
|
535 |
+
},
|
536 |
+
"eval_CARDINAL": {
|
537 |
+
"f1": 0.9926470588235294,
|
538 |
+
"number": 678,
|
539 |
+
"precision": 0.9897360703812317,
|
540 |
+
"recall": 0.995575221238938
|
541 |
+
},
|
542 |
+
"eval_DESC": {
|
543 |
+
"f1": 0.3928571428571428,
|
544 |
+
"number": 30,
|
545 |
+
"precision": 0.4230769230769231,
|
546 |
+
"recall": 0.36666666666666664
|
547 |
+
},
|
548 |
+
"eval_FT": {
|
549 |
+
"f1": 0.0,
|
550 |
+
"number": 7,
|
551 |
+
"precision": 0.0,
|
552 |
+
"recall": 0.0
|
553 |
+
},
|
554 |
+
"eval_LOC": {
|
555 |
+
"f1": 0.9647058823529412,
|
556 |
+
"number": 761,
|
557 |
+
"precision": 0.9596879063719116,
|
558 |
+
"recall": 0.9697766097240473
|
559 |
+
},
|
560 |
+
"eval_PER": {
|
561 |
+
"f1": 0.9852289512555391,
|
562 |
+
"number": 676,
|
563 |
+
"precision": 0.9837758112094396,
|
564 |
+
"recall": 0.9866863905325444
|
565 |
+
},
|
566 |
+
"eval_SPAT": {
|
567 |
+
"f1": 0.9590811198851399,
|
568 |
+
"number": 694,
|
569 |
+
"precision": 0.9556509298998569,
|
570 |
+
"recall": 0.962536023054755
|
571 |
+
},
|
572 |
+
"eval_TITRE": {
|
573 |
+
"f1": 0.0,
|
574 |
+
"number": 2,
|
575 |
+
"precision": 0.0,
|
576 |
+
"recall": 0.0
|
577 |
+
},
|
578 |
+
"eval_TITREH": {
|
579 |
+
"f1": 0.8985507246376813,
|
580 |
+
"number": 33,
|
581 |
+
"precision": 0.8611111111111112,
|
582 |
+
"recall": 0.9393939393939394
|
583 |
+
},
|
584 |
+
"eval_TITREP": {
|
585 |
+
"f1": 0.0,
|
586 |
+
"number": 5,
|
587 |
+
"precision": 0.0,
|
588 |
+
"recall": 0.0
|
589 |
+
},
|
590 |
+
"eval_accuracy": 0.9640019860973188,
|
591 |
+
"eval_accuracy-all": 0.9731256206554121,
|
592 |
+
"eval_accuracy-das": 0.9754220456802384,
|
593 |
+
"eval_accuracy-l1": 0.9687189672293942,
|
594 |
+
"eval_accuracy-l2": 0.97753227408143,
|
595 |
+
"eval_f1": 0.9680589680589681,
|
596 |
+
"eval_f1-all": 0.9637989154330939,
|
597 |
+
"eval_f1-das": 0.9730332899386276,
|
598 |
+
"eval_f1-l1": 0.9616488390294807,
|
599 |
+
"eval_f1-l2": 0.9665551839464883,
|
600 |
+
"eval_loss": 0.15035659074783325,
|
601 |
+
"eval_precision": 0.9662435083669937,
|
602 |
+
"eval_precision-all": 0.9619660620245758,
|
603 |
+
"eval_precision-das": 0.9714073523950985,
|
604 |
+
"eval_precision-l1": 0.9559128630705395,
|
605 |
+
"eval_precision-l2": 0.9697986577181208,
|
606 |
+
"eval_recall": 0.9698812626701419,
|
607 |
+
"eval_recall-all": 0.9656387665198238,
|
608 |
+
"eval_recall-das": 0.9746646795827124,
|
609 |
+
"eval_recall-l1": 0.9674540682414698,
|
610 |
+
"eval_recall-l2": 0.9633333333333334,
|
611 |
+
"eval_runtime": 6.3141,
|
612 |
+
"eval_samples_per_second": 107.061,
|
613 |
+
"eval_steps_per_second": 6.81,
|
614 |
+
"step": 600
|
615 |
+
}
|
616 |
+
],
|
617 |
+
"max_steps": 5000,
|
618 |
+
"num_train_epochs": 14,
|
619 |
+
"total_flos": 241578442301760.0,
|
620 |
+
"trial_name": null,
|
621 |
+
"trial_params": null
|
622 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:271a333013ff332e5d8df54e250ed02dd9655d95de9224ea38967fae72caf587
|
3 |
+
size 3503
|