Hugging Face's logo

yueqis
/
Qwen3-14B-30K-sft-nopacking

Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
yueqis commited on
Commit
6294b01
·
verified ·
1 Parent(s): 483642a

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +204 -0
trainer_state.json ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9968186638388123,
6
+ "eval_steps": 500,
7
+ "global_step": 235,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.042417815482502653,
14
+ "grad_norm": 0.8155243915035402,
15
+ "learning_rate": 7.500000000000001e-06,
16
+ "loss": 0.6415,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.08483563096500531,
21
+ "grad_norm": 0.3724018495341306,
22
+ "learning_rate": 9.975707393083328e-06,
23
+ "loss": 0.4089,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.12725344644750794,
28
+ "grad_norm": 0.28463462503464637,
29
+ "learning_rate": 9.85729110226596e-06,
30
+ "loss": 0.3616,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.16967126193001061,
35
+ "grad_norm": 0.297538920144775,
36
+ "learning_rate": 9.642632564563576e-06,
37
+ "loss": 0.3331,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.21208907741251326,
42
+ "grad_norm": 0.2991153079080703,
43
+ "learning_rate": 9.33598501898256e-06,
44
+ "loss": 0.3282,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.2545068928950159,
49
+ "grad_norm": 0.2618563036667496,
50
+ "learning_rate": 8.943424372477455e-06,
51
+ "loss": 0.305,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.29692470837751855,
56
+ "grad_norm": 0.2945290407529977,
57
+ "learning_rate": 8.472728812079436e-06,
58
+ "loss": 0.3293,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.33934252386002123,
63
+ "grad_norm": 0.2686931795972466,
64
+ "learning_rate": 7.933224688089059e-06,
65
+ "loss": 0.3093,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.38176033934252385,
70
+ "grad_norm": 0.24826628745526108,
71
+ "learning_rate": 7.3356017219999236e-06,
72
+ "loss": 0.2981,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.4241781548250265,
77
+ "grad_norm": 0.2770179971302181,
78
+ "learning_rate": 6.691701200618925e-06,
79
+ "loss": 0.2925,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.46659597030752914,
84
+ "grad_norm": 0.2581961736174019,
85
+ "learning_rate": 6.014281353099601e-06,
86
+ "loss": 0.2999,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.5090137857900318,
91
+ "grad_norm": 0.2686100147543252,
92
+ "learning_rate": 5.3167645597022855e-06,
93
+ "loss": 0.3111,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.5514316012725344,
98
+ "grad_norm": 1.1286877967357856,
99
+ "learning_rate": 4.612971401080521e-06,
100
+ "loss": 0.2747,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.5938494167550371,
105
+ "grad_norm": 0.27687544341997167,
106
+ "learning_rate": 3.916846817634618e-06,
107
+ "loss": 0.2929,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.6362672322375398,
112
+ "grad_norm": 0.27713605473267083,
113
+ "learning_rate": 3.2421838048042516e-06,
114
+ "loss": 0.291,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.6786850477200425,
119
+ "grad_norm": 0.2658744274079011,
120
+ "learning_rate": 2.602350118994782e-06,
121
+ "loss": 0.2846,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.721102863202545,
126
+ "grad_norm": 0.2771317958447051,
127
+ "learning_rate": 2.0100234091793778e-06,
128
+ "loss": 0.2883,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.7635206786850477,
133
+ "grad_norm": 0.26274869656822974,
134
+ "learning_rate": 1.4769400222728974e-06,
135
+ "loss": 0.2904,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.8059384941675504,
140
+ "grad_norm": 0.25909723594124506,
141
+ "learning_rate": 1.0136624594416828e-06,
142
+ "loss": 0.2808,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.848356309650053,
147
+ "grad_norm": 0.2815262998286053,
148
+ "learning_rate": 6.29370090964262e-07,
149
+ "loss": 0.2844,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.8907741251325557,
154
+ "grad_norm": 0.27545396785421056,
155
+ "learning_rate": 3.3167727641356064e-07,
156
+ "loss": 0.273,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.9331919406150583,
161
+ "grad_norm": 0.27726375004859716,
162
+ "learning_rate": 1.2648249392289925e-07,
163
+ "loss": 0.2713,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.975609756097561,
168
+ "grad_norm": 0.26279284026638045,
169
+ "learning_rate": 1.785146788478298e-08,
170
+ "loss": 0.2891,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.9968186638388123,
175
+ "step": 235,
176
+ "total_flos": 412229836996608.0,
177
+ "train_loss": 0.3199658251823263,
178
+ "train_runtime": 20135.6606,
179
+ "train_samples_per_second": 1.498,
180
+ "train_steps_per_second": 0.012
181
+ }
182
+ ],
183
+ "logging_steps": 10,
184
+ "max_steps": 235,
185
+ "num_input_tokens_seen": 0,
186
+ "num_train_epochs": 1,
187
+ "save_steps": 500,
188
+ "stateful_callbacks": {
189
+ "TrainerControl": {
190
+ "args": {
191
+ "should_epoch_stop": false,
192
+ "should_evaluate": false,
193
+ "should_log": false,
194
+ "should_save": true,
195
+ "should_training_stop": true
196
+ },
197
+ "attributes": {}
198
+ }
199
+ },
200
+ "total_flos": 412229836996608.0,
201
+ "train_batch_size": 1,
202
+ "trial_name": null,
203
+ "trial_params": null
204
+ }