Upload 11 files
Browse files- config.json +49 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +483 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5,
|
30 |
+
"LABEL_6": 6
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"model_type": "bert",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 0,
|
38 |
+
"pooler_fc_size": 768,
|
39 |
+
"pooler_num_attention_heads": 12,
|
40 |
+
"pooler_num_fc_layers": 3,
|
41 |
+
"pooler_size_per_head": 128,
|
42 |
+
"pooler_type": "first_token_transform",
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.38.1",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 119547
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3464507543bcd5a63144ad9e7c40083a605e6ae28e76daa26b9df5a09404d6c
|
3 |
+
size 709096284
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c4762c65f673b48b6e30a37ae48167d77dc5e9c0f1ef957bfd9c54a2b27f232
|
3 |
+
size 1418312250
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e173b028a7b49b7598e1d0be461b9d1381eae9728de0257e5a2a3230ba0a5ad5
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e9d47ac0c4a6583ddb94f81f2a71d6ba82f5603d2acd75906e08ceb02509c00
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9518328315919957,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 21500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04,
|
13 |
+
"grad_norm": 16.78230857849121,
|
14 |
+
"learning_rate": 1.987315680989377e-05,
|
15 |
+
"loss": 0.7008,
|
16 |
+
"step": 1000
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04,
|
20 |
+
"eval_LOC_f1": 0.7083043365359647,
|
21 |
+
"eval_ORG_f1": 0.5623498694516972,
|
22 |
+
"eval_PER_f1": 0.7100647964924535,
|
23 |
+
"eval_loss": 0.525841236114502,
|
24 |
+
"eval_overall_accuracy": 0.839431747364137,
|
25 |
+
"eval_overall_f1": 0.6684494885258021,
|
26 |
+
"eval_overall_precision": 0.6813296398891967,
|
27 |
+
"eval_overall_recall": 0.656047285763059,
|
28 |
+
"eval_runtime": 178.5538,
|
29 |
+
"eval_samples_per_second": 365.156,
|
30 |
+
"eval_steps_per_second": 22.822,
|
31 |
+
"step": 1000
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.09,
|
35 |
+
"grad_norm": 9.70958137512207,
|
36 |
+
"learning_rate": 1.974631361978754e-05,
|
37 |
+
"loss": 0.4865,
|
38 |
+
"step": 2000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.09,
|
42 |
+
"eval_LOC_f1": 0.7016948849995092,
|
43 |
+
"eval_ORG_f1": 0.590386287417712,
|
44 |
+
"eval_PER_f1": 0.744081694250214,
|
45 |
+
"eval_loss": 0.4681616723537445,
|
46 |
+
"eval_overall_accuracy": 0.8518320678647284,
|
47 |
+
"eval_overall_f1": 0.6854302821050324,
|
48 |
+
"eval_overall_precision": 0.6610573746663495,
|
49 |
+
"eval_overall_recall": 0.7116692272675543,
|
50 |
+
"eval_runtime": 178.958,
|
51 |
+
"eval_samples_per_second": 364.331,
|
52 |
+
"eval_steps_per_second": 22.771,
|
53 |
+
"step": 2000
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.13,
|
57 |
+
"grad_norm": 15.70914077758789,
|
58 |
+
"learning_rate": 1.961947042968131e-05,
|
59 |
+
"loss": 0.4382,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.13,
|
64 |
+
"eval_LOC_f1": 0.7578888199720886,
|
65 |
+
"eval_ORG_f1": 0.6413910093299406,
|
66 |
+
"eval_PER_f1": 0.7750323494978126,
|
67 |
+
"eval_loss": 0.4217945635318756,
|
68 |
+
"eval_overall_accuracy": 0.8756332018861953,
|
69 |
+
"eval_overall_f1": 0.7298225286836603,
|
70 |
+
"eval_overall_precision": 0.7249466651695486,
|
71 |
+
"eval_overall_recall": 0.7347644247183339,
|
72 |
+
"eval_runtime": 177.7042,
|
73 |
+
"eval_samples_per_second": 366.902,
|
74 |
+
"eval_steps_per_second": 22.931,
|
75 |
+
"step": 3000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.18,
|
79 |
+
"grad_norm": 0.9930562376976013,
|
80 |
+
"learning_rate": 1.9492627239575078e-05,
|
81 |
+
"loss": 0.3973,
|
82 |
+
"step": 4000
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.18,
|
86 |
+
"eval_LOC_f1": 0.7571125548125672,
|
87 |
+
"eval_ORG_f1": 0.648735892760337,
|
88 |
+
"eval_PER_f1": 0.7869654790165547,
|
89 |
+
"eval_loss": 0.37678804993629456,
|
90 |
+
"eval_overall_accuracy": 0.8835828734179773,
|
91 |
+
"eval_overall_f1": 0.7360367198972751,
|
92 |
+
"eval_overall_precision": 0.7341253555609017,
|
93 |
+
"eval_overall_recall": 0.7379580630476841,
|
94 |
+
"eval_runtime": 176.7693,
|
95 |
+
"eval_samples_per_second": 368.842,
|
96 |
+
"eval_steps_per_second": 23.053,
|
97 |
+
"step": 4000
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.22,
|
101 |
+
"grad_norm": 10.682718276977539,
|
102 |
+
"learning_rate": 1.9365784049468845e-05,
|
103 |
+
"loss": 0.3937,
|
104 |
+
"step": 5000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.22,
|
108 |
+
"eval_LOC_f1": 0.7778496267121274,
|
109 |
+
"eval_ORG_f1": 0.6430323934146428,
|
110 |
+
"eval_PER_f1": 0.7986373262130558,
|
111 |
+
"eval_loss": 0.4208361804485321,
|
112 |
+
"eval_overall_accuracy": 0.8810407141986101,
|
113 |
+
"eval_overall_f1": 0.7449750865636349,
|
114 |
+
"eval_overall_precision": 0.7371928798261742,
|
115 |
+
"eval_overall_recall": 0.7529233526800956,
|
116 |
+
"eval_runtime": 175.2138,
|
117 |
+
"eval_samples_per_second": 372.117,
|
118 |
+
"eval_steps_per_second": 23.257,
|
119 |
+
"step": 5000
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.27,
|
123 |
+
"grad_norm": 9.084446907043457,
|
124 |
+
"learning_rate": 1.924106352298313e-05,
|
125 |
+
"loss": 0.3536,
|
126 |
+
"step": 6000
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 0.27,
|
130 |
+
"eval_LOC_f1": 0.7828708236001125,
|
131 |
+
"eval_ORG_f1": 0.6829649863421904,
|
132 |
+
"eval_PER_f1": 0.799357419856545,
|
133 |
+
"eval_loss": 0.36626189947128296,
|
134 |
+
"eval_overall_accuracy": 0.8907383203725096,
|
135 |
+
"eval_overall_f1": 0.760005685048323,
|
136 |
+
"eval_overall_precision": 0.7663556759390631,
|
137 |
+
"eval_overall_recall": 0.7537600608939571,
|
138 |
+
"eval_runtime": 1096.1574,
|
139 |
+
"eval_samples_per_second": 59.937,
|
140 |
+
"eval_steps_per_second": 0.118,
|
141 |
+
"step": 6000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.31,
|
145 |
+
"grad_norm": 17.549041748046875,
|
146 |
+
"learning_rate": 1.9114574110146982e-05,
|
147 |
+
"loss": 0.3432,
|
148 |
+
"step": 7000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 0.31,
|
152 |
+
"eval_LOC_f1": 0.7952019006963426,
|
153 |
+
"eval_ORG_f1": 0.6895359096523734,
|
154 |
+
"eval_PER_f1": 0.8176749430952034,
|
155 |
+
"eval_loss": 0.3385719060897827,
|
156 |
+
"eval_overall_accuracy": 0.8962171463957795,
|
157 |
+
"eval_overall_f1": 0.771180360157569,
|
158 |
+
"eval_overall_precision": 0.7696968420461406,
|
159 |
+
"eval_overall_recall": 0.772669607995151,
|
160 |
+
"eval_runtime": 858.9522,
|
161 |
+
"eval_samples_per_second": 76.489,
|
162 |
+
"eval_steps_per_second": 0.15,
|
163 |
+
"step": 7000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.35,
|
167 |
+
"grad_norm": 24.70513916015625,
|
168 |
+
"learning_rate": 1.8988084697310836e-05,
|
169 |
+
"loss": 0.3278,
|
170 |
+
"step": 8000
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.35,
|
174 |
+
"eval_LOC_f1": 0.8013627254509018,
|
175 |
+
"eval_ORG_f1": 0.6951269959460578,
|
176 |
+
"eval_PER_f1": 0.8197644808913556,
|
177 |
+
"eval_loss": 0.34438127279281616,
|
178 |
+
"eval_overall_accuracy": 0.898079396458301,
|
179 |
+
"eval_overall_f1": 0.7756412540713129,
|
180 |
+
"eval_overall_precision": 0.7844467189482182,
|
181 |
+
"eval_overall_recall": 0.7670312786321413,
|
182 |
+
"eval_runtime": 858.3259,
|
183 |
+
"eval_samples_per_second": 76.544,
|
184 |
+
"eval_steps_per_second": 0.15,
|
185 |
+
"step": 8000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.4,
|
189 |
+
"grad_norm": 9.711076736450195,
|
190 |
+
"learning_rate": 1.8861595284474693e-05,
|
191 |
+
"loss": 0.3262,
|
192 |
+
"step": 9000
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.4,
|
196 |
+
"eval_LOC_f1": 0.813213095471476,
|
197 |
+
"eval_ORG_f1": 0.7107696972759894,
|
198 |
+
"eval_PER_f1": 0.8219371637919723,
|
199 |
+
"eval_loss": 0.3584470748901367,
|
200 |
+
"eval_overall_accuracy": 0.898605619797311,
|
201 |
+
"eval_overall_f1": 0.7873656115410829,
|
202 |
+
"eval_overall_precision": 0.7973837314349728,
|
203 |
+
"eval_overall_recall": 0.7775960982760808,
|
204 |
+
"eval_runtime": 870.9363,
|
205 |
+
"eval_samples_per_second": 75.436,
|
206 |
+
"eval_steps_per_second": 0.148,
|
207 |
+
"step": 9000
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.44,
|
211 |
+
"grad_norm": 1.0706424713134766,
|
212 |
+
"learning_rate": 1.8735105871638546e-05,
|
213 |
+
"loss": 0.3224,
|
214 |
+
"step": 10000
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.44,
|
218 |
+
"eval_LOC_f1": 0.8127321363277717,
|
219 |
+
"eval_ORG_f1": 0.7053217033370902,
|
220 |
+
"eval_PER_f1": 0.8284614520690605,
|
221 |
+
"eval_loss": 0.3149181008338928,
|
222 |
+
"eval_overall_accuracy": 0.9003740874825833,
|
223 |
+
"eval_overall_f1": 0.78723937113973,
|
224 |
+
"eval_overall_precision": 0.7880037567703074,
|
225 |
+
"eval_overall_recall": 0.7864764670228211,
|
226 |
+
"eval_runtime": 905.7017,
|
227 |
+
"eval_samples_per_second": 72.54,
|
228 |
+
"eval_steps_per_second": 0.142,
|
229 |
+
"step": 10000
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.49,
|
233 |
+
"grad_norm": 5.779551982879639,
|
234 |
+
"learning_rate": 1.86086164588024e-05,
|
235 |
+
"loss": 0.323,
|
236 |
+
"step": 11000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.49,
|
240 |
+
"eval_LOC_f1": 0.8184425456746753,
|
241 |
+
"eval_ORG_f1": 0.7099403917116094,
|
242 |
+
"eval_PER_f1": 0.8274642760571583,
|
243 |
+
"eval_loss": 0.32969576120376587,
|
244 |
+
"eval_overall_accuracy": 0.8986934477379095,
|
245 |
+
"eval_overall_f1": 0.787954918665525,
|
246 |
+
"eval_overall_precision": 0.7845852840472364,
|
247 |
+
"eval_overall_recall": 0.7913536219218246,
|
248 |
+
"eval_runtime": 904.0471,
|
249 |
+
"eval_samples_per_second": 72.673,
|
250 |
+
"eval_steps_per_second": 0.143,
|
251 |
+
"step": 11000
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.53,
|
255 |
+
"grad_norm": 0.5029723048210144,
|
256 |
+
"learning_rate": 1.8482127045966253e-05,
|
257 |
+
"loss": 0.307,
|
258 |
+
"step": 12000
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 0.53,
|
262 |
+
"eval_LOC_f1": 0.8216145583120352,
|
263 |
+
"eval_ORG_f1": 0.7225526656894693,
|
264 |
+
"eval_PER_f1": 0.8273035359038698,
|
265 |
+
"eval_loss": 0.3300624191761017,
|
266 |
+
"eval_overall_accuracy": 0.9015344583248979,
|
267 |
+
"eval_overall_f1": 0.7950728742961997,
|
268 |
+
"eval_overall_precision": 0.7871480673058326,
|
269 |
+
"eval_overall_recall": 0.8031588740256262,
|
270 |
+
"eval_runtime": 864.0266,
|
271 |
+
"eval_samples_per_second": 76.039,
|
272 |
+
"eval_steps_per_second": 0.149,
|
273 |
+
"step": 12000
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.58,
|
277 |
+
"grad_norm": 3.1533098220825195,
|
278 |
+
"learning_rate": 1.8355637633130106e-05,
|
279 |
+
"loss": 0.3176,
|
280 |
+
"step": 13000
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 0.58,
|
284 |
+
"eval_LOC_f1": 0.8250715828125148,
|
285 |
+
"eval_ORG_f1": 0.7192632496804788,
|
286 |
+
"eval_PER_f1": 0.8411864068909802,
|
287 |
+
"eval_loss": 0.32228201627731323,
|
288 |
+
"eval_overall_accuracy": 0.9048257731835991,
|
289 |
+
"eval_overall_f1": 0.7993031971987119,
|
290 |
+
"eval_overall_precision": 0.7982273018015168,
|
291 |
+
"eval_overall_recall": 0.8003819968143439,
|
292 |
+
"eval_runtime": 861.5394,
|
293 |
+
"eval_samples_per_second": 76.259,
|
294 |
+
"eval_steps_per_second": 0.15,
|
295 |
+
"step": 13000
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.62,
|
299 |
+
"grad_norm": 27.121158599853516,
|
300 |
+
"learning_rate": 1.8229148220293963e-05,
|
301 |
+
"loss": 0.3026,
|
302 |
+
"step": 14000
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.62,
|
306 |
+
"eval_LOC_f1": 0.813366057700572,
|
307 |
+
"eval_ORG_f1": 0.7255497858288067,
|
308 |
+
"eval_PER_f1": 0.8334248928753359,
|
309 |
+
"eval_loss": 0.31955230236053467,
|
310 |
+
"eval_overall_accuracy": 0.9049277429112431,
|
311 |
+
"eval_overall_f1": 0.7948808632215472,
|
312 |
+
"eval_overall_precision": 0.7823057288325302,
|
313 |
+
"eval_overall_recall": 0.8078668790437393,
|
314 |
+
"eval_runtime": 870.9305,
|
315 |
+
"eval_samples_per_second": 75.437,
|
316 |
+
"eval_steps_per_second": 0.148,
|
317 |
+
"step": 14000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.66,
|
321 |
+
"grad_norm": 2.3121883869171143,
|
322 |
+
"learning_rate": 1.8102658807457817e-05,
|
323 |
+
"loss": 0.3148,
|
324 |
+
"step": 15000
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.66,
|
328 |
+
"eval_LOC_f1": 0.8302503673286692,
|
329 |
+
"eval_ORG_f1": 0.7304969576437721,
|
330 |
+
"eval_PER_f1": 0.8389894805913836,
|
331 |
+
"eval_loss": 0.3013811409473419,
|
332 |
+
"eval_overall_accuracy": 0.9075328089459457,
|
333 |
+
"eval_overall_f1": 0.8036533849292605,
|
334 |
+
"eval_overall_precision": 0.8008272039526633,
|
335 |
+
"eval_overall_recall": 0.8064995841732094,
|
336 |
+
"eval_runtime": 915.5251,
|
337 |
+
"eval_samples_per_second": 71.762,
|
338 |
+
"eval_steps_per_second": 0.141,
|
339 |
+
"step": 15000
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.71,
|
343 |
+
"grad_norm": 9.053048133850098,
|
344 |
+
"learning_rate": 1.7976169394621674e-05,
|
345 |
+
"loss": 0.2919,
|
346 |
+
"step": 16000
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.71,
|
350 |
+
"eval_LOC_f1": 0.8302478759061501,
|
351 |
+
"eval_ORG_f1": 0.731782075129564,
|
352 |
+
"eval_PER_f1": 0.8492362049256988,
|
353 |
+
"eval_loss": 0.29880577325820923,
|
354 |
+
"eval_overall_accuracy": 0.9072484845958724,
|
355 |
+
"eval_overall_f1": 0.8070731973229327,
|
356 |
+
"eval_overall_precision": 0.8054613737671545,
|
357 |
+
"eval_overall_recall": 0.8086914847130795,
|
358 |
+
"eval_runtime": 868.8985,
|
359 |
+
"eval_samples_per_second": 75.613,
|
360 |
+
"eval_steps_per_second": 0.148,
|
361 |
+
"step": 16000
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.75,
|
365 |
+
"grad_norm": 10.181853294372559,
|
366 |
+
"learning_rate": 1.7849679981785527e-05,
|
367 |
+
"loss": 0.284,
|
368 |
+
"step": 17000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.75,
|
372 |
+
"eval_LOC_f1": 0.8266632184651193,
|
373 |
+
"eval_ORG_f1": 0.7243731835870154,
|
374 |
+
"eval_PER_f1": 0.8473984474857374,
|
375 |
+
"eval_loss": 0.32140275835990906,
|
376 |
+
"eval_overall_accuracy": 0.9021306462945541,
|
377 |
+
"eval_overall_f1": 0.8045739646627278,
|
378 |
+
"eval_overall_precision": 0.7991697840325968,
|
379 |
+
"eval_overall_recall": 0.8100517316719056,
|
380 |
+
"eval_runtime": 858.2577,
|
381 |
+
"eval_samples_per_second": 76.55,
|
382 |
+
"eval_steps_per_second": 0.15,
|
383 |
+
"step": 17000
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.8,
|
387 |
+
"grad_norm": 5.25670862197876,
|
388 |
+
"learning_rate": 1.772319056894938e-05,
|
389 |
+
"loss": 0.3011,
|
390 |
+
"step": 18000
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.8,
|
394 |
+
"eval_LOC_f1": 0.8265056399966245,
|
395 |
+
"eval_ORG_f1": 0.7394759212033855,
|
396 |
+
"eval_PER_f1": 0.8559909523111401,
|
397 |
+
"eval_loss": 0.30769339203834534,
|
398 |
+
"eval_overall_accuracy": 0.9103075764251944,
|
399 |
+
"eval_overall_f1": 0.8115094912358725,
|
400 |
+
"eval_overall_precision": 0.8128234861554996,
|
401 |
+
"eval_overall_recall": 0.8101997378176846,
|
402 |
+
"eval_runtime": 857.6527,
|
403 |
+
"eval_samples_per_second": 76.604,
|
404 |
+
"eval_steps_per_second": 0.15,
|
405 |
+
"step": 18000
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.84,
|
409 |
+
"grad_norm": 3.439514398574829,
|
410 |
+
"learning_rate": 1.7596701156113234e-05,
|
411 |
+
"loss": 0.2913,
|
412 |
+
"step": 19000
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 0.84,
|
416 |
+
"eval_LOC_f1": 0.827463843173361,
|
417 |
+
"eval_ORG_f1": 0.7474629390110435,
|
418 |
+
"eval_PER_f1": 0.8510804051006602,
|
419 |
+
"eval_loss": 0.3055616617202759,
|
420 |
+
"eval_overall_accuracy": 0.9091010586988365,
|
421 |
+
"eval_overall_f1": 0.8128348309192438,
|
422 |
+
"eval_overall_precision": 0.817294400980434,
|
423 |
+
"eval_overall_recall": 0.8084236640683365,
|
424 |
+
"eval_runtime": 881.3321,
|
425 |
+
"eval_samples_per_second": 74.546,
|
426 |
+
"eval_steps_per_second": 0.146,
|
427 |
+
"step": 19000
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.89,
|
431 |
+
"grad_norm": 4.887170791625977,
|
432 |
+
"learning_rate": 1.747021174327709e-05,
|
433 |
+
"loss": 0.2927,
|
434 |
+
"step": 20000
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.89,
|
438 |
+
"eval_LOC_f1": 0.8435358479700547,
|
439 |
+
"eval_ORG_f1": 0.7490680162942847,
|
440 |
+
"eval_PER_f1": 0.859867877786953,
|
441 |
+
"eval_loss": 0.28957998752593994,
|
442 |
+
"eval_overall_accuracy": 0.9142888616308011,
|
443 |
+
"eval_overall_f1": 0.8220150311968236,
|
444 |
+
"eval_overall_precision": 0.8269754768392371,
|
445 |
+
"eval_overall_recall": 0.8171137391990753,
|
446 |
+
"eval_runtime": 908.0817,
|
447 |
+
"eval_samples_per_second": 72.35,
|
448 |
+
"eval_steps_per_second": 0.142,
|
449 |
+
"step": 20000
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.93,
|
453 |
+
"grad_norm": 24.44190216064453,
|
454 |
+
"learning_rate": 1.7343722330440944e-05,
|
455 |
+
"loss": 0.2833,
|
456 |
+
"step": 21000
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 0.93,
|
460 |
+
"eval_LOC_f1": 0.8368153269843636,
|
461 |
+
"eval_ORG_f1": 0.7463167531278608,
|
462 |
+
"eval_PER_f1": 0.8518246438142143,
|
463 |
+
"eval_loss": 0.3060026466846466,
|
464 |
+
"eval_overall_accuracy": 0.9097895404365793,
|
465 |
+
"eval_overall_f1": 0.8159558988135214,
|
466 |
+
"eval_overall_precision": 0.8099609727642672,
|
467 |
+
"eval_overall_recall": 0.8220402294800051,
|
468 |
+
"eval_runtime": 860.9742,
|
469 |
+
"eval_samples_per_second": 76.309,
|
470 |
+
"eval_steps_per_second": 0.15,
|
471 |
+
"step": 21000
|
472 |
+
}
|
473 |
+
],
|
474 |
+
"logging_steps": 1000,
|
475 |
+
"max_steps": 158116,
|
476 |
+
"num_input_tokens_seen": 0,
|
477 |
+
"num_train_epochs": 7,
|
478 |
+
"save_steps": 500,
|
479 |
+
"total_flos": 5913608888301312.0,
|
480 |
+
"train_batch_size": 8,
|
481 |
+
"trial_name": null,
|
482 |
+
"trial_params": null
|
483 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0f7a60270f3ee223660c001ddc4e29051fd77c829918010af9f92d6bd976d2e
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|