End of training
Browse files- .gitignore +1 -0
- all_results.json +26 -0
- config.json +46 -0
- eval_results.json +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- test_results.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +9 -0
- trainer_state.json +121 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
all_results.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.979997105690534,
|
4 |
+
"eval_f1": 0.9379482534942355,
|
5 |
+
"eval_loss": 0.1315528005361557,
|
6 |
+
"eval_precision": 0.9340386115444618,
|
7 |
+
"eval_recall": 0.9418907624993855,
|
8 |
+
"eval_runtime": 22.5786,
|
9 |
+
"eval_samples": 10000,
|
10 |
+
"eval_samples_per_second": 442.898,
|
11 |
+
"eval_steps_per_second": 36.938,
|
12 |
+
"test_accuracy": 0.9792432006306662,
|
13 |
+
"test_f1": 0.9409973905479849,
|
14 |
+
"test_loss": 0.13579198718070984,
|
15 |
+
"test_precision": 0.9374187647426948,
|
16 |
+
"test_recall": 0.9446034440941062,
|
17 |
+
"test_runtime": 24.1205,
|
18 |
+
"test_samples_per_second": 414.585,
|
19 |
+
"test_steps_per_second": 34.576,
|
20 |
+
"total_flos": 1404947975153976.0,
|
21 |
+
"train_loss": 0.054277180967462514,
|
22 |
+
"train_runtime": 938.8043,
|
23 |
+
"train_samples": 20000,
|
24 |
+
"train_samples_per_second": 106.518,
|
25 |
+
"train_steps_per_second": 8.878
|
26 |
+
}
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "KB/bert-base-swedish-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "ner",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-PER",
|
16 |
+
"2": "I-PER",
|
17 |
+
"3": "B-ORG",
|
18 |
+
"4": "I-ORG",
|
19 |
+
"5": "B-LOC",
|
20 |
+
"6": "I-LOC"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 3072,
|
24 |
+
"label2id": {
|
25 |
+
"B-LOC": "5",
|
26 |
+
"B-ORG": "3",
|
27 |
+
"B-PER": "1",
|
28 |
+
"I-LOC": "6",
|
29 |
+
"I-ORG": "4",
|
30 |
+
"I-PER": "2",
|
31 |
+
"O": "0"
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "bert",
|
36 |
+
"num_attention_heads": 12,
|
37 |
+
"num_hidden_layers": 12,
|
38 |
+
"output_past": true,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"position_embedding_type": "absolute",
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.22.1",
|
43 |
+
"type_vocab_size": 2,
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50325
|
46 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.979997105690534,
|
4 |
+
"eval_f1": 0.9379482534942355,
|
5 |
+
"eval_loss": 0.1315528005361557,
|
6 |
+
"eval_precision": 0.9340386115444618,
|
7 |
+
"eval_recall": 0.9418907624993855,
|
8 |
+
"eval_runtime": 22.5786,
|
9 |
+
"eval_samples": 10000,
|
10 |
+
"eval_samples_per_second": 442.898,
|
11 |
+
"eval_steps_per_second": 36.938
|
12 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2c35d035c2c2fa167092628fad3a9753ecf2324fb6c58d73e25644f9acf6a6f
|
3 |
+
size 496493361
|
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 |
+
}
|
test_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"test_accuracy": 0.9792432006306662,
|
3 |
+
"test_f1": 0.9409973905479849,
|
4 |
+
"test_loss": 0.13579198718070984,
|
5 |
+
"test_precision": 0.9374187647426948,
|
6 |
+
"test_recall": 0.9446034440941062,
|
7 |
+
"test_runtime": 24.1205,
|
8 |
+
"test_samples_per_second": 414.585,
|
9 |
+
"test_steps_per_second": 34.576
|
10 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"name_or_path": "KB/bert-base-swedish-cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--KB--bert-base-swedish-cased/snapshots/81c7baa04742a30cb6732c181e678721868cb42e/special_tokens_map.json",
|
12 |
+
"strip_accents": false,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 1404947975153976.0,
|
4 |
+
"train_loss": 0.054277180967462514,
|
5 |
+
"train_runtime": 938.8043,
|
6 |
+
"train_samples": 20000,
|
7 |
+
"train_samples_per_second": 106.518,
|
8 |
+
"train_steps_per_second": 8.878
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 8335,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.3,
|
12 |
+
"learning_rate": 4.7000599880024e-05,
|
13 |
+
"loss": 0.2124,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.6,
|
18 |
+
"learning_rate": 4.4001199760047995e-05,
|
19 |
+
"loss": 0.1387,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.9,
|
24 |
+
"learning_rate": 4.100179964007199e-05,
|
25 |
+
"loss": 0.1202,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.2,
|
30 |
+
"learning_rate": 3.800239952009598e-05,
|
31 |
+
"loss": 0.0785,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.5,
|
36 |
+
"learning_rate": 3.500299940011998e-05,
|
37 |
+
"loss": 0.0632,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.8,
|
42 |
+
"learning_rate": 3.2003599280143974e-05,
|
43 |
+
"loss": 0.0647,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.1,
|
48 |
+
"learning_rate": 2.9004199160167967e-05,
|
49 |
+
"loss": 0.0554,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.4,
|
54 |
+
"learning_rate": 2.6004799040191963e-05,
|
55 |
+
"loss": 0.0355,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.7,
|
60 |
+
"learning_rate": 2.300539892021596e-05,
|
61 |
+
"loss": 0.0335,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.0,
|
66 |
+
"learning_rate": 2.0005998800239953e-05,
|
67 |
+
"loss": 0.0318,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 3.3,
|
72 |
+
"learning_rate": 1.700659868026395e-05,
|
73 |
+
"loss": 0.0136,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 3.6,
|
78 |
+
"learning_rate": 1.4007198560287942e-05,
|
79 |
+
"loss": 0.0193,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.9,
|
84 |
+
"learning_rate": 1.1007798440311939e-05,
|
85 |
+
"loss": 0.0145,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 4.2,
|
90 |
+
"learning_rate": 8.008398320335933e-06,
|
91 |
+
"loss": 0.0086,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 4.5,
|
96 |
+
"learning_rate": 5.008998200359928e-06,
|
97 |
+
"loss": 0.0059,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 4.8,
|
102 |
+
"learning_rate": 2.009598080383923e-06,
|
103 |
+
"loss": 0.0052,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 5.0,
|
108 |
+
"step": 8335,
|
109 |
+
"total_flos": 1404947975153976.0,
|
110 |
+
"train_loss": 0.054277180967462514,
|
111 |
+
"train_runtime": 938.8043,
|
112 |
+
"train_samples_per_second": 106.518,
|
113 |
+
"train_steps_per_second": 8.878
|
114 |
+
}
|
115 |
+
],
|
116 |
+
"max_steps": 8335,
|
117 |
+
"num_train_epochs": 5,
|
118 |
+
"total_flos": 1404947975153976.0,
|
119 |
+
"trial_name": null,
|
120 |
+
"trial_params": null
|
121 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94c863290560ba4ff42f221a93c20f50077f12bfe86bc3437aa50ece107f4c82
|
3 |
+
size 3311
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|