Hugging Face's logo

C10X
/
DGGs

Safetensors
qwen3_moe
Model card Files Community
C10X commited on
Commit
a9c1ce7
·
verified ·
1 Parent(s): 66cee2f

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +181 -0
trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9966329966329966,
6
+ "eval_steps": 500,
7
+ "global_step": 148,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04713804713804714,
14
+ "grad_norm": NaN,
15
+ "learning_rate": 2.1428571428571428e-05,
16
+ "loss": 0.0,
17
+ "step": 7
18
+ },
19
+ {
20
+ "epoch": 0.09427609427609428,
21
+ "grad_norm": NaN,
22
+ "learning_rate": 4.642857142857143e-05,
23
+ "loss": 0.0,
24
+ "step": 14
25
+ },
26
+ {
27
+ "epoch": 0.1414141414141414,
28
+ "grad_norm": NaN,
29
+ "learning_rate": 4.975670171853926e-05,
30
+ "loss": 0.0,
31
+ "step": 21
32
+ },
33
+ {
34
+ "epoch": 0.18855218855218855,
35
+ "grad_norm": NaN,
36
+ "learning_rate": 4.88646908061933e-05,
37
+ "loss": 0.0,
38
+ "step": 28
39
+ },
40
+ {
41
+ "epoch": 0.2356902356902357,
42
+ "grad_norm": NaN,
43
+ "learning_rate": 4.734081600808531e-05,
44
+ "loss": 0.0,
45
+ "step": 35
46
+ },
47
+ {
48
+ "epoch": 0.2828282828282828,
49
+ "grad_norm": NaN,
50
+ "learning_rate": 4.522542485937369e-05,
51
+ "loss": 0.0,
52
+ "step": 42
53
+ },
54
+ {
55
+ "epoch": 0.32996632996632996,
56
+ "grad_norm": NaN,
57
+ "learning_rate": 4.257452643564155e-05,
58
+ "loss": 0.0,
59
+ "step": 49
60
+ },
61
+ {
62
+ "epoch": 0.3771043771043771,
63
+ "grad_norm": NaN,
64
+ "learning_rate": 3.945830840419966e-05,
65
+ "loss": 0.0,
66
+ "step": 56
67
+ },
68
+ {
69
+ "epoch": 0.42424242424242425,
70
+ "grad_norm": NaN,
71
+ "learning_rate": 3.5959278669726935e-05,
72
+ "loss": 0.0,
73
+ "step": 63
74
+ },
75
+ {
76
+ "epoch": 0.4713804713804714,
77
+ "grad_norm": NaN,
78
+ "learning_rate": 3.217008081777726e-05,
79
+ "loss": 0.0,
80
+ "step": 70
81
+ },
82
+ {
83
+ "epoch": 0.5185185185185185,
84
+ "grad_norm": NaN,
85
+ "learning_rate": 2.8191041196514873e-05,
86
+ "loss": 0.0,
87
+ "step": 77
88
+ },
89
+ {
90
+ "epoch": 0.5656565656565656,
91
+ "grad_norm": NaN,
92
+ "learning_rate": 2.4127512582437485e-05,
93
+ "loss": 0.0,
94
+ "step": 84
95
+ },
96
+ {
97
+ "epoch": 0.6127946127946128,
98
+ "grad_norm": NaN,
99
+ "learning_rate": 2.0087084761679245e-05,
100
+ "loss": 0.0,
101
+ "step": 91
102
+ },
103
+ {
104
+ "epoch": 0.6599326599326599,
105
+ "grad_norm": NaN,
106
+ "learning_rate": 1.617673588215328e-05,
107
+ "loss": 0.0,
108
+ "step": 98
109
+ },
110
+ {
111
+ "epoch": 0.7070707070707071,
112
+ "grad_norm": NaN,
113
+ "learning_rate": 1.2500000000000006e-05,
114
+ "loss": 0.0,
115
+ "step": 105
116
+ },
117
+ {
118
+ "epoch": 0.7542087542087542,
119
+ "grad_norm": NaN,
120
+ "learning_rate": 9.154225815032242e-06,
121
+ "loss": 0.0,
122
+ "step": 112
123
+ },
124
+ {
125
+ "epoch": 0.8013468013468014,
126
+ "grad_norm": NaN,
127
+ "learning_rate": 6.22799917546252e-06,
128
+ "loss": 0.0,
129
+ "step": 119
130
+ },
131
+ {
132
+ "epoch": 0.8484848484848485,
133
+ "grad_norm": NaN,
134
+ "learning_rate": 3.798797596089351e-06,
135
+ "loss": 0.0,
136
+ "step": 126
137
+ },
138
+ {
139
+ "epoch": 0.8956228956228957,
140
+ "grad_norm": NaN,
141
+ "learning_rate": 1.9309388911139426e-06,
142
+ "loss": 0.0,
143
+ "step": 133
144
+ },
145
+ {
146
+ "epoch": 0.9427609427609428,
147
+ "grad_norm": NaN,
148
+ "learning_rate": 6.738782355044049e-07,
149
+ "loss": 0.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "epoch": 0.98989898989899,
154
+ "grad_norm": NaN,
155
+ "learning_rate": 6.089874350439506e-08,
156
+ "loss": 0.0,
157
+ "step": 147
158
+ }
159
+ ],
160
+ "logging_steps": 7,
161
+ "max_steps": 148,
162
+ "num_input_tokens_seen": 0,
163
+ "num_train_epochs": 1,
164
+ "save_steps": 74,
165
+ "stateful_callbacks": {
166
+ "TrainerControl": {
167
+ "args": {
168
+ "should_epoch_stop": false,
169
+ "should_evaluate": false,
170
+ "should_log": false,
171
+ "should_save": true,
172
+ "should_training_stop": true
173
+ },
174
+ "attributes": {}
175
+ }
176
+ },
177
+ "total_flos": 1296015690362880.0,
178
+ "train_batch_size": 32,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }