Hugging Face's logo

WinF
/
stackorderflow-filter-v1

Text Classification
Transformers
Safetensors
electra
Model card Files
xet
Community
SangwonYoon commited on
Commit
51350e7
·
1 Parent(s): 0733adc

initial commit

Browse files
Files changed (7) hide show
  1. config.json +31 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +114 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "monologg/koelectra-small-v3-discriminator",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 128,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1024,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "electra",
17
+ "num_attention_heads": 4,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "summary_activation": "gelu",
23
+ "summary_last_dropout": 0.1,
24
+ "summary_type": "first",
25
+ "summary_use_proj": true,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.38.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 35000
31
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1bcadb5056932995c6779e8af4f4a2944fcdc34752162edcf11ed99a983dc6
3
+ size 56513936
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb973e2b81451eb8d309faccf46312bf7985c3c00d2701cc96d0d864a844dfc
3
+ size 113144122
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58ea6db84f06f71f3413d338e868805fc6ce439156fbbb3d6e1268a63844332
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0078bef835dc8db8abd05b0bbc25ef4d33915b6fc26849ab969bb6f803a57f4c
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4978097081184387,
3
+ "best_model_checkpoint": "output_dir/checkpoint-168",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 168,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_f1": 0.7504690431519699,
14
+ "eval_loss": 0.6844255328178406,
15
+ "eval_runtime": 31.6654,
16
+ "eval_samples_per_second": 10.516,
17
+ "eval_steps_per_second": 0.189,
18
+ "step": 21
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.7504690431519699,
23
+ "eval_loss": 0.6841882467269897,
24
+ "eval_runtime": 29.3795,
25
+ "eval_samples_per_second": 11.334,
26
+ "eval_steps_per_second": 0.204,
27
+ "step": 42
28
+ },
29
+ {
30
+ "epoch": 2.38,
31
+ "grad_norm": 1.0868926048278809,
32
+ "learning_rate": 7.61904761904762e-06,
33
+ "loss": 0.6614,
34
+ "step": 50
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_f1": 0.9393939393939394,
39
+ "eval_loss": 0.6861188411712646,
40
+ "eval_runtime": 29.5784,
41
+ "eval_samples_per_second": 11.258,
42
+ "eval_steps_per_second": 0.203,
43
+ "step": 63
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_f1": 0.15668202764976957,
48
+ "eval_loss": 0.6874817609786987,
49
+ "eval_runtime": 30.604,
50
+ "eval_samples_per_second": 10.881,
51
+ "eval_steps_per_second": 0.196,
52
+ "step": 84
53
+ },
54
+ {
55
+ "epoch": 4.76,
56
+ "grad_norm": 1.4174736738204956,
57
+ "learning_rate": 5.2380952380952384e-06,
58
+ "loss": 0.5543,
59
+ "step": 100
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_f1": 0.2608695652173913,
64
+ "eval_loss": 0.682039737701416,
65
+ "eval_runtime": 31.2133,
66
+ "eval_samples_per_second": 10.669,
67
+ "eval_steps_per_second": 0.192,
68
+ "step": 105
69
+ },
70
+ {
71
+ "epoch": 6.0,
72
+ "eval_f1": 0.8636363636363636,
73
+ "eval_loss": 0.5800318717956543,
74
+ "eval_runtime": 29.3466,
75
+ "eval_samples_per_second": 11.347,
76
+ "eval_steps_per_second": 0.204,
77
+ "step": 126
78
+ },
79
+ {
80
+ "epoch": 7.0,
81
+ "eval_f1": 0.8235294117647058,
82
+ "eval_loss": 0.5767043232917786,
83
+ "eval_runtime": 29.766,
84
+ "eval_samples_per_second": 11.187,
85
+ "eval_steps_per_second": 0.202,
86
+ "step": 147
87
+ },
88
+ {
89
+ "epoch": 7.14,
90
+ "grad_norm": 2.605710506439209,
91
+ "learning_rate": 2.8571428571428573e-06,
92
+ "loss": 0.4746,
93
+ "step": 150
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_f1": 0.9159891598915989,
98
+ "eval_loss": 0.4978097081184387,
99
+ "eval_runtime": 29.603,
100
+ "eval_samples_per_second": 11.249,
101
+ "eval_steps_per_second": 0.203,
102
+ "step": 168
103
+ }
104
+ ],
105
+ "logging_steps": 50,
106
+ "max_steps": 210,
107
+ "num_input_tokens_seen": 0,
108
+ "num_train_epochs": 10,
109
+ "save_steps": 500,
110
+ "total_flos": 156512489226240.0,
111
+ "train_batch_size": 64,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b67b4975b33e7a1340dc2536d534d0b084792e962d48b8cc1fef2ae6509ac4
3
+ size 4856