Hugging Face's logo

yueqis
/
web-sample

Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
yueqis commited on
Commit
f07c735
·
verified ·
1 Parent(s): a777201

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +211 -0
trainer_state.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9964841788046208,
6
+ "eval_steps": 1000,
7
+ "global_step": 248,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04018081366147665,
14
+ "grad_norm": 3.9855914370792176,
15
+ "learning_rate": 6.923076923076923e-06,
16
+ "loss": 1.528,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0803616273229533,
21
+ "grad_norm": 1.1009387233386336,
22
+ "learning_rate": 9.983924160137627e-06,
23
+ "loss": 0.7997,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.12054244098442994,
28
+ "grad_norm": 0.8531122977437774,
29
+ "learning_rate": 9.886057021922984e-06,
30
+ "loss": 0.6384,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.1607232546459066,
35
+ "grad_norm": 0.8536491315382806,
36
+ "learning_rate": 9.700998080399287e-06,
37
+ "loss": 0.626,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.20090406830738322,
42
+ "grad_norm": 0.8012093869333087,
43
+ "learning_rate": 9.432049716762151e-06,
44
+ "loss": 0.5725,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.24108488196885988,
49
+ "grad_norm": 0.7591296330983313,
50
+ "learning_rate": 9.08401132093219e-06,
51
+ "loss": 0.5478,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.2812656956303365,
56
+ "grad_norm": 0.7482379362816577,
57
+ "learning_rate": 8.663093646328166e-06,
58
+ "loss": 0.547,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.3214465092918132,
63
+ "grad_norm": 0.739024551349721,
64
+ "learning_rate": 8.17680797882512e-06,
65
+ "loss": 0.5588,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.3616273229532898,
70
+ "grad_norm": 0.7393951361302983,
71
+ "learning_rate": 7.633832097679959e-06,
72
+ "loss": 0.508,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.40180813661476644,
77
+ "grad_norm": 0.7515531494396616,
78
+ "learning_rate": 7.04385542035506e-06,
79
+ "loss": 0.5226,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.4419889502762431,
84
+ "grad_norm": 0.7192941297373309,
85
+ "learning_rate": 6.41740609463409e-06,
86
+ "loss": 0.5259,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.48216976393771976,
91
+ "grad_norm": 0.7491496835437959,
92
+ "learning_rate": 5.765663123575401e-06,
93
+ "loss": 0.5236,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.5223505775991963,
98
+ "grad_norm": 0.6913958034624077,
99
+ "learning_rate": 5.1002568759376134e-06,
100
+ "loss": 0.4932,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.562531391260673,
105
+ "grad_norm": 0.7500711845802256,
106
+ "learning_rate": 4.433061541973591e-06,
107
+ "loss": 0.4862,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.6027122049221497,
112
+ "grad_norm": 0.6913808839000353,
113
+ "learning_rate": 3.77598323822407e-06,
114
+ "loss": 0.5015,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.6428930185836264,
119
+ "grad_norm": 0.6642782125575131,
120
+ "learning_rate": 3.1407475425859348e-06,
121
+ "loss": 0.5478,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.683073832245103,
126
+ "grad_norm": 0.6488024479264766,
127
+ "learning_rate": 2.5386902510968627e-06,
128
+ "loss": 0.4814,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.7232546459065796,
133
+ "grad_norm": 0.7186636113633829,
134
+ "learning_rate": 1.9805550903864775e-06,
135
+ "loss": 0.5066,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.7634354595680563,
140
+ "grad_norm": 0.6368854640125701,
141
+ "learning_rate": 1.4763019956201252e-06,
142
+ "loss": 0.4917,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.8036162732295329,
147
+ "grad_norm": 0.8130162452154214,
148
+ "learning_rate": 1.0349293752198842e-06,
149
+ "loss": 0.4796,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.8437970868910095,
154
+ "grad_norm": 0.7305985326066481,
155
+ "learning_rate": 6.643135340531137e-07,
156
+ "loss": 0.5084,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.8839779005524862,
161
+ "grad_norm": 0.7027540145976225,
162
+ "learning_rate": 3.710681205854838e-07,
163
+ "loss": 0.4863,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.9241587142139628,
168
+ "grad_norm": 0.6411791844623818,
169
+ "learning_rate": 1.6042610616743782e-07,
170
+ "loss": 0.4763,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.9643395278754395,
175
+ "grad_norm": 0.6768334011228406,
176
+ "learning_rate": 3.6146402536468285e-08,
177
+ "loss": 0.4711,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.9964841788046208,
182
+ "step": 248,
183
+ "total_flos": 790927692005376.0,
184
+ "train_loss": 0.5734609403917866,
185
+ "train_runtime": 14466.4063,
186
+ "train_samples_per_second": 2.202,
187
+ "train_steps_per_second": 0.017
188
+ }
189
+ ],
190
+ "logging_steps": 10,
191
+ "max_steps": 248,
192
+ "num_input_tokens_seen": 0,
193
+ "num_train_epochs": 1,
194
+ "save_steps": 100,
195
+ "stateful_callbacks": {
196
+ "TrainerControl": {
197
+ "args": {
198
+ "should_epoch_stop": false,
199
+ "should_evaluate": false,
200
+ "should_log": false,
201
+ "should_save": true,
202
+ "should_training_stop": true
203
+ },
204
+ "attributes": {}
205
+ }
206
+ },
207
+ "total_flos": 790927692005376.0,
208
+ "train_batch_size": 1,
209
+ "trial_name": null,
210
+ "trial_params": null
211
+ }