Hugging Face's logo

yueqis
/
web-long-sample

Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
yueqis commited on
Commit
6a99dd7
·
verified ·
1 Parent(s): d5f4dce

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +162 -0
trainer_state.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9957081545064378,
6
+ "eval_steps": 1000,
7
+ "global_step": 174,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05722460658082976,
14
+ "grad_norm": 2.8843040386286187,
15
+ "learning_rate": 1e-05,
16
+ "loss": 1.2427,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.11444921316165951,
21
+ "grad_norm": 0.9017664305111632,
22
+ "learning_rate": 9.909643486313533e-06,
23
+ "loss": 0.5328,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.17167381974248927,
28
+ "grad_norm": 0.797068637259448,
29
+ "learning_rate": 9.641839665080363e-06,
30
+ "loss": 0.4447,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.22889842632331903,
35
+ "grad_norm": 0.6941745476559829,
36
+ "learning_rate": 9.206267664155906e-06,
37
+ "loss": 0.4017,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.2861230329041488,
42
+ "grad_norm": 0.6250591769825486,
43
+ "learning_rate": 8.61867019052535e-06,
44
+ "loss": 0.3776,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.34334763948497854,
49
+ "grad_norm": 0.6177949791797019,
50
+ "learning_rate": 7.900284547855992e-06,
51
+ "loss": 0.3662,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.4005722460658083,
56
+ "grad_norm": 0.6776944915753278,
57
+ "learning_rate": 7.0770750650094335e-06,
58
+ "loss": 0.3658,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.45779685264663805,
63
+ "grad_norm": 0.7027875485112575,
64
+ "learning_rate": 6.178794677547138e-06,
65
+ "loss": 0.3553,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.5150214592274678,
70
+ "grad_norm": 0.6301404025031555,
71
+ "learning_rate": 5.237909579118713e-06,
72
+ "loss": 0.3317,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.5722460658082976,
77
+ "grad_norm": 0.6840316408079424,
78
+ "learning_rate": 4.2884258086335755e-06,
79
+ "loss": 0.3428,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.6294706723891274,
84
+ "grad_norm": 0.6028809547153681,
85
+ "learning_rate": 3.3646601834128924e-06,
86
+ "loss": 0.331,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.6866952789699571,
91
+ "grad_norm": 0.6463003155720976,
92
+ "learning_rate": 2.5000000000000015e-06,
93
+ "loss": 0.3252,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.7439198855507868,
98
+ "grad_norm": 0.5511586120399353,
99
+ "learning_rate": 1.7256963302735752e-06,
100
+ "loss": 0.3167,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.8011444921316166,
105
+ "grad_norm": 0.6770595845177203,
106
+ "learning_rate": 1.0697345262860638e-06,
107
+ "loss": 0.326,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.8583690987124464,
112
+ "grad_norm": 0.5474842641924246,
113
+ "learning_rate": 5.558227567253832e-07,
114
+ "loss": 0.3133,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.9155937052932761,
119
+ "grad_norm": 0.5872523545390601,
120
+ "learning_rate": 2.0253513192751374e-07,
121
+ "loss": 0.3195,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.9728183118741058,
126
+ "grad_norm": 0.5924289357218945,
127
+ "learning_rate": 2.264038713457706e-08,
128
+ "loss": 0.3216,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.9957081545064378,
133
+ "step": 174,
134
+ "total_flos": 599683779002368.0,
135
+ "train_loss": 0.40995535357245083,
136
+ "train_runtime": 10019.3178,
137
+ "train_samples_per_second": 2.232,
138
+ "train_steps_per_second": 0.017
139
+ }
140
+ ],
141
+ "logging_steps": 10,
142
+ "max_steps": 174,
143
+ "num_input_tokens_seen": 0,
144
+ "num_train_epochs": 1,
145
+ "save_steps": 1000,
146
+ "stateful_callbacks": {
147
+ "TrainerControl": {
148
+ "args": {
149
+ "should_epoch_stop": false,
150
+ "should_evaluate": false,
151
+ "should_log": false,
152
+ "should_save": true,
153
+ "should_training_stop": true
154
+ },
155
+ "attributes": {}
156
+ }
157
+ },
158
+ "total_flos": 599683779002368.0,
159
+ "train_batch_size": 1,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }