HF中国镜像站's logo

moogician
/
DSR1-Qwen-32B-131fad2c

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
moogician commited on
Commit
fd37ee6
·
verified ·
1 Parent(s): 44c4325

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +238 -0
trainer_state.json ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.5161290322580645,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12903225806451613,
13
+ "grad_norm": 2.0922131538391113,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 0.6097,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.25806451612903225,
20
+ "grad_norm": 2.037680149078369,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.5815,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.3870967741935484,
27
+ "grad_norm": 1.9914177656173706,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.5731,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.5161290322580645,
34
+ "grad_norm": 1.7522591352462769,
35
+ "learning_rate": 9.960573506572391e-06,
36
+ "loss": 0.5499,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.6451612903225806,
41
+ "grad_norm": 1.2676565647125244,
42
+ "learning_rate": 9.842915805643156e-06,
43
+ "loss": 0.5117,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.7741935483870968,
48
+ "grad_norm": 0.952801525592804,
49
+ "learning_rate": 9.648882429441258e-06,
50
+ "loss": 0.4997,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.9032258064516129,
55
+ "grad_norm": 1.187522053718567,
56
+ "learning_rate": 9.381533400219319e-06,
57
+ "loss": 0.5062,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.0,
62
+ "grad_norm": 1.187522053718567,
63
+ "learning_rate": 9.045084971874738e-06,
64
+ "loss": 0.4698,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.129032258064516,
69
+ "grad_norm": 1.5576032400131226,
70
+ "learning_rate": 8.644843137107058e-06,
71
+ "loss": 0.4722,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.2580645161290323,
76
+ "grad_norm": 1.07254958152771,
77
+ "learning_rate": 8.18711994874345e-06,
78
+ "loss": 0.4426,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.3870967741935485,
83
+ "grad_norm": 0.8922549486160278,
84
+ "learning_rate": 7.679133974894984e-06,
85
+ "loss": 0.4364,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.5161290322580645,
90
+ "grad_norm": 0.7638566493988037,
91
+ "learning_rate": 7.128896457825364e-06,
92
+ "loss": 0.417,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.6451612903225805,
97
+ "grad_norm": 0.6911720633506775,
98
+ "learning_rate": 6.545084971874738e-06,
99
+ "loss": 0.4195,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.7741935483870968,
104
+ "grad_norm": 0.6178150177001953,
105
+ "learning_rate": 5.936906572928625e-06,
106
+ "loss": 0.4147,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.903225806451613,
111
+ "grad_norm": 0.46914201974868774,
112
+ "learning_rate": 5.3139525976465675e-06,
113
+ "loss": 0.4204,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 2.0,
118
+ "grad_norm": 0.37992069125175476,
119
+ "learning_rate": 4.686047402353433e-06,
120
+ "loss": 0.3935,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 2.129032258064516,
125
+ "grad_norm": 0.4508312940597534,
126
+ "learning_rate": 4.063093427071376e-06,
127
+ "loss": 0.3939,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 2.258064516129032,
132
+ "grad_norm": 0.3774235248565674,
133
+ "learning_rate": 3.4549150281252635e-06,
134
+ "loss": 0.3945,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 2.3870967741935485,
139
+ "grad_norm": 0.3686850368976593,
140
+ "learning_rate": 2.871103542174637e-06,
141
+ "loss": 0.3761,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 2.5161290322580645,
146
+ "grad_norm": 0.3773055672645569,
147
+ "learning_rate": 2.320866025105016e-06,
148
+ "loss": 0.3804,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.6451612903225805,
153
+ "grad_norm": 0.33530160784721375,
154
+ "learning_rate": 1.8128800512565514e-06,
155
+ "loss": 0.3861,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.774193548387097,
160
+ "grad_norm": 0.3947732448577881,
161
+ "learning_rate": 1.3551568628929434e-06,
162
+ "loss": 0.3731,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.903225806451613,
167
+ "grad_norm": 0.34654495120048523,
168
+ "learning_rate": 9.549150281252633e-07,
169
+ "loss": 0.378,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 3.0,
174
+ "grad_norm": 0.3812512755393982,
175
+ "learning_rate": 6.184665997806832e-07,
176
+ "loss": 0.372,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 3.129032258064516,
181
+ "grad_norm": 0.366245836019516,
182
+ "learning_rate": 3.511175705587433e-07,
183
+ "loss": 0.3714,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 3.258064516129032,
188
+ "grad_norm": 0.3321492671966553,
189
+ "learning_rate": 1.5708419435684463e-07,
190
+ "loss": 0.3653,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 3.3870967741935485,
195
+ "grad_norm": 0.28523552417755127,
196
+ "learning_rate": 3.9426493427611177e-08,
197
+ "loss": 0.3678,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 3.5161290322580645,
202
+ "grad_norm": 0.3045349717140198,
203
+ "learning_rate": 0.0,
204
+ "loss": 0.3741,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 3.5161290322580645,
209
+ "step": 28,
210
+ "total_flos": 74554711998464.0,
211
+ "train_loss": 0.43752551823854446,
212
+ "train_runtime": 3591.335,
213
+ "train_samples_per_second": 0.538,
214
+ "train_steps_per_second": 0.008
215
+ }
216
+ ],
217
+ "logging_steps": 1,
218
+ "max_steps": 28,
219
+ "num_input_tokens_seen": 0,
220
+ "num_train_epochs": 4,
221
+ "save_steps": 8,
222
+ "stateful_callbacks": {
223
+ "TrainerControl": {
224
+ "args": {
225
+ "should_epoch_stop": false,
226
+ "should_evaluate": false,
227
+ "should_log": false,
228
+ "should_save": true,
229
+ "should_training_stop": true
230
+ },
231
+ "attributes": {}
232
+ }
233
+ },
234
+ "total_flos": 74554711998464.0,
235
+ "train_batch_size": 2,
236
+ "trial_name": null,
237
+ "trial_params": null
238
+ }