Hugging Face's logo

sigridjineth
/
ko-embedding-v1-preview-241130

Safetensors
xlm-roberta
Model card Files Community
sigridjineth commited on
Commit
2760714
·
verified ·
1 Parent(s): 4ac3d36

Upload checkpoint-14/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-14/trainer_state.json +131 -0
checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14285714285714285,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0,
15
+ "loss": 3.1568,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.2857142857142857,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 0,
22
+ "loss": 2.0929,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.42857142857142855,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0,
29
+ "loss": 1.8548,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.5714285714285714,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 0,
36
+ "loss": 1.9561,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.7142857142857143,
41
+ "grad_norm": 31.57492020476853,
42
+ "learning_rate": 0.0,
43
+ "loss": 2.158,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.8571428571428571,
48
+ "grad_norm": 31.153859925878365,
49
+ "learning_rate": 1e-05,
50
+ "loss": 2.1095,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "grad_norm": 27.11565016529603,
56
+ "learning_rate": 1e-05,
57
+ "loss": 1.9969,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.1428571428571428,
62
+ "grad_norm": 13.454490530290899,
63
+ "learning_rate": 9.166666666666666e-06,
64
+ "loss": 1.9251,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.2857142857142856,
69
+ "grad_norm": 11.618148917850199,
70
+ "learning_rate": 8.333333333333334e-06,
71
+ "loss": 2.3126,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.4285714285714286,
76
+ "grad_norm": 15.134253327445556,
77
+ "learning_rate": 7.500000000000001e-06,
78
+ "loss": 1.937,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.5714285714285714,
83
+ "grad_norm": 15.062018295753115,
84
+ "learning_rate": 6.666666666666667e-06,
85
+ "loss": 1.8163,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.7142857142857144,
90
+ "grad_norm": 14.2866003252187,
91
+ "learning_rate": 5.833333333333334e-06,
92
+ "loss": 1.98,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.8571428571428572,
97
+ "grad_norm": 13.311110732967121,
98
+ "learning_rate": 5e-06,
99
+ "loss": 1.9709,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 2.0,
104
+ "grad_norm": 13.689697089288877,
105
+ "learning_rate": 4.166666666666667e-06,
106
+ "loss": 1.9649,
107
+ "step": 14
108
+ }
109
+ ],
110
+ "logging_steps": 1.0,
111
+ "max_steps": 14,
112
+ "num_input_tokens_seen": 0,
113
+ "num_train_epochs": 2,
114
+ "save_steps": 1000,
115
+ "stateful_callbacks": {
116
+ "TrainerControl": {
117
+ "args": {
118
+ "should_epoch_stop": false,
119
+ "should_evaluate": false,
120
+ "should_log": false,
121
+ "should_save": true,
122
+ "should_training_stop": true
123
+ },
124
+ "attributes": {}
125
+ }
126
+ },
127
+ "total_flos": 0.0,
128
+ "train_batch_size": 1,
129
+ "trial_name": null,
130
+ "trial_params": null
131
+ }