Hugging Face's logo

yueqis
/
web-qwen-coder-32b-2epochs-30k-5e-5

Safetensors
qwen2
Model card Files
xet
Community
yueqis commited on
Commit
dbab00b
·
verified ·
1 Parent(s): ca9ffe1

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +244 -0
trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0992419021364577,
6
+ "eval_steps": 500,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.036756260050539856,
14
+ "grad_norm": 1.0688965320587158,
15
+ "learning_rate": 1.0975609756097562e-05,
16
+ "loss": 1.1745,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.07351252010107971,
21
+ "grad_norm": 0.6050378084182739,
22
+ "learning_rate": 2.3170731707317075e-05,
23
+ "loss": 0.9615,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.11026878015161957,
28
+ "grad_norm": 0.5260648727416992,
29
+ "learning_rate": 3.5365853658536584e-05,
30
+ "loss": 0.9305,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.14702504020215942,
35
+ "grad_norm": 0.4684043824672699,
36
+ "learning_rate": 4.75609756097561e-05,
37
+ "loss": 0.8995,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1837813002526993,
42
+ "grad_norm": 0.4516962468624115,
43
+ "learning_rate": 4.998685537302135e-05,
44
+ "loss": 0.8836,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.22053756030323915,
49
+ "grad_norm": 0.4993128776550293,
50
+ "learning_rate": 4.9933479014963055e-05,
51
+ "loss": 0.8635,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.257293820353779,
56
+ "grad_norm": 0.4929085373878479,
57
+ "learning_rate": 4.9839137016353147e-05,
58
+ "loss": 0.8769,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.29405008040431885,
63
+ "grad_norm": 0.4800896644592285,
64
+ "learning_rate": 4.970398438084758e-05,
65
+ "loss": 0.9013,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.33080634045485874,
70
+ "grad_norm": 0.42861899733543396,
71
+ "learning_rate": 4.952824316387163e-05,
72
+ "loss": 0.8876,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.3675626005053986,
77
+ "grad_norm": 0.45206961035728455,
78
+ "learning_rate": 4.931220210778332e-05,
79
+ "loss": 0.8549,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.4043188605559384,
84
+ "grad_norm": 0.7127406597137451,
85
+ "learning_rate": 4.905621616747054e-05,
86
+ "loss": 0.8494,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.4410751206064783,
91
+ "grad_norm": 0.40425172448158264,
92
+ "learning_rate": 4.876070592716105e-05,
93
+ "loss": 0.8437,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.47783138065701813,
98
+ "grad_norm": 0.4734930992126465,
99
+ "learning_rate": 4.842615690940373e-05,
100
+ "loss": 0.8411,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.514587640707558,
105
+ "grad_norm": 0.4126618802547455,
106
+ "learning_rate": 4.80531187773563e-05,
107
+ "loss": 0.8658,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.5513439007580979,
112
+ "grad_norm": 0.4084201157093048,
113
+ "learning_rate": 4.7642204431690206e-05,
114
+ "loss": 0.8467,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5881001608086377,
119
+ "grad_norm": 0.38719961047172546,
120
+ "learning_rate": 4.71940890035964e-05,
121
+ "loss": 0.8834,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.6248564208591776,
126
+ "grad_norm": 0.37913328409194946,
127
+ "learning_rate": 4.6709508745546575e-05,
128
+ "loss": 0.8286,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.6616126809097175,
133
+ "grad_norm": 0.35573574900627136,
134
+ "learning_rate": 4.618925982163232e-05,
135
+ "loss": 0.8447,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6983689409602573,
140
+ "grad_norm": 0.3563328683376312,
141
+ "learning_rate": 4.563419699946956e-05,
142
+ "loss": 0.855,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.7351252010107971,
147
+ "grad_norm": 0.3638900816440582,
148
+ "learning_rate": 4.504523224581762e-05,
149
+ "loss": 0.864,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.771881461061337,
154
+ "grad_norm": 0.38919857144355774,
155
+ "learning_rate": 4.442333322822028e-05,
156
+ "loss": 0.8375,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.8086377211118768,
161
+ "grad_norm": 0.3908405303955078,
162
+ "learning_rate": 4.376952172513046e-05,
163
+ "loss": 0.8642,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.8453939811624167,
168
+ "grad_norm": 0.37455061078071594,
169
+ "learning_rate": 4.308487194713097e-05,
170
+ "loss": 0.8775,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.8821502412129566,
175
+ "grad_norm": 0.3894438147544861,
176
+ "learning_rate": 4.2370508772009334e-05,
177
+ "loss": 0.8454,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.9189065012634965,
182
+ "grad_norm": 0.40810340642929077,
183
+ "learning_rate": 4.162760589658649e-05,
184
+ "loss": 0.8399,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.9556627613140363,
189
+ "grad_norm": 0.36629530787467957,
190
+ "learning_rate": 4.0857383908336076e-05,
191
+ "loss": 0.8519,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.9924190213645762,
196
+ "grad_norm": 0.37508270144462585,
197
+ "learning_rate": 4.0061108279962336e-05,
198
+ "loss": 0.8629,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 1.025729382035378,
203
+ "grad_norm": 0.5247800350189209,
204
+ "learning_rate": 3.924008729023185e-05,
205
+ "loss": 0.7402,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 1.0624856420859177,
210
+ "grad_norm": 0.39590781927108765,
211
+ "learning_rate": 3.8395669874474915e-05,
212
+ "loss": 0.7421,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.0992419021364577,
217
+ "grad_norm": 0.3770304322242737,
218
+ "learning_rate": 3.752924340828837e-05,
219
+ "loss": 0.6945,
220
+ "step": 300
221
+ }
222
+ ],
223
+ "logging_steps": 10,
224
+ "max_steps": 816,
225
+ "num_input_tokens_seen": 0,
226
+ "num_train_epochs": 3,
227
+ "save_steps": 50,
228
+ "stateful_callbacks": {
229
+ "TrainerControl": {
230
+ "args": {
231
+ "should_epoch_stop": false,
232
+ "should_evaluate": false,
233
+ "should_log": false,
234
+ "should_save": true,
235
+ "should_training_stop": false
236
+ },
237
+ "attributes": {}
238
+ }
239
+ },
240
+ "total_flos": 9973542502268928.0,
241
+ "train_batch_size": 1,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }