Hugging Face's logo

abocide
/
Qwen2.5-7B-Instruct-R1-forfinance

Text Generation
Transformers
Safetensors
qwen2
finance
chinese
sft
reasoning
financial-ai
conversational
text-generation-inference
Model card Files
xet
Community
abocide commited on
Commit
6983629
·
verified ·
1 Parent(s): 93ac056

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +260 -0
trainer_state.json ADDED
@@ -0,0 +1,260 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 312,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06433453960595094,
14
+ "grad_norm": 3.45802150331781,
15
+ "learning_rate": 9e-06,
16
+ "loss": 1.2375,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.12866907921190188,
21
+ "grad_norm": 1.1539024437598726,
22
+ "learning_rate": 9.701986754966888e-06,
23
+ "loss": 0.9458,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.19300361881785283,
28
+ "grad_norm": 0.9061861869896987,
29
+ "learning_rate": 9.370860927152319e-06,
30
+ "loss": 0.8553,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.25733815842380375,
35
+ "grad_norm": 0.9981148139996454,
36
+ "learning_rate": 9.039735099337749e-06,
37
+ "loss": 0.8223,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.32167269802975473,
42
+ "grad_norm": 0.8365225486736688,
43
+ "learning_rate": 8.70860927152318e-06,
44
+ "loss": 0.7753,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.38600723763570566,
49
+ "grad_norm": 0.8456361592054138,
50
+ "learning_rate": 8.37748344370861e-06,
51
+ "loss": 0.7945,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.45034177724165664,
56
+ "grad_norm": 0.8510899654200162,
57
+ "learning_rate": 8.04635761589404e-06,
58
+ "loss": 0.7906,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.5146763168476075,
63
+ "grad_norm": 0.8094078169285094,
64
+ "learning_rate": 7.715231788079471e-06,
65
+ "loss": 0.7744,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.5790108564535585,
70
+ "grad_norm": 0.7429293470064048,
71
+ "learning_rate": 7.384105960264901e-06,
72
+ "loss": 0.7717,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.6433453960595095,
77
+ "grad_norm": 0.7512159253738925,
78
+ "learning_rate": 7.052980132450332e-06,
79
+ "loss": 0.7744,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.7076799356654604,
84
+ "grad_norm": 0.826044235136776,
85
+ "learning_rate": 6.721854304635762e-06,
86
+ "loss": 0.7491,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.7720144752714113,
91
+ "grad_norm": 0.8503335376772373,
92
+ "learning_rate": 6.390728476821193e-06,
93
+ "loss": 0.7593,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.8363490148773622,
98
+ "grad_norm": 0.7306086642250036,
99
+ "learning_rate": 6.059602649006623e-06,
100
+ "loss": 0.7555,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.9006835544833133,
105
+ "grad_norm": 0.745854567446407,
106
+ "learning_rate": 5.728476821192054e-06,
107
+ "loss": 0.7434,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.9650180940892642,
112
+ "grad_norm": 0.7574425315504884,
113
+ "learning_rate": 5.397350993377483e-06,
114
+ "loss": 0.7764,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 1.0257338158423803,
119
+ "grad_norm": 0.7250372088806204,
120
+ "learning_rate": 5.066225165562915e-06,
121
+ "loss": 0.709,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 1.0900683554483312,
126
+ "grad_norm": 0.75139008443435,
127
+ "learning_rate": 4.7350993377483445e-06,
128
+ "loss": 0.6574,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 1.1544028950542822,
133
+ "grad_norm": 0.7181949393746255,
134
+ "learning_rate": 4.403973509933775e-06,
135
+ "loss": 0.6573,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 1.218737434660233,
140
+ "grad_norm": 0.7970783454719403,
141
+ "learning_rate": 4.072847682119206e-06,
142
+ "loss": 0.6617,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 1.2830719742661842,
147
+ "grad_norm": 0.741621225992888,
148
+ "learning_rate": 3.7417218543046362e-06,
149
+ "loss": 0.6625,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 1.3474065138721352,
154
+ "grad_norm": 0.7244825073568412,
155
+ "learning_rate": 3.4105960264900668e-06,
156
+ "loss": 0.6516,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 1.411741053478086,
161
+ "grad_norm": 0.6328326617408025,
162
+ "learning_rate": 3.079470198675497e-06,
163
+ "loss": 0.6478,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 1.476075593084037,
168
+ "grad_norm": 0.7325603487325139,
169
+ "learning_rate": 2.7483443708609275e-06,
170
+ "loss": 0.6512,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 1.540410132689988,
175
+ "grad_norm": 0.6447452871518153,
176
+ "learning_rate": 2.417218543046358e-06,
177
+ "loss": 0.6454,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 1.6047446722959389,
182
+ "grad_norm": 0.7076398532029401,
183
+ "learning_rate": 2.086092715231788e-06,
184
+ "loss": 0.6539,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 1.6690792119018898,
189
+ "grad_norm": 0.6775962757094781,
190
+ "learning_rate": 1.7549668874172188e-06,
191
+ "loss": 0.6499,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 1.7334137515078407,
196
+ "grad_norm": 0.6345994881996349,
197
+ "learning_rate": 1.4238410596026491e-06,
198
+ "loss": 0.6456,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 1.7977482911137916,
203
+ "grad_norm": 0.6759310052346794,
204
+ "learning_rate": 1.0927152317880797e-06,
205
+ "loss": 0.6499,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 1.8620828307197428,
210
+ "grad_norm": 0.686752021394961,
211
+ "learning_rate": 7.6158940397351e-07,
212
+ "loss": 0.6526,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.9264173703256935,
217
+ "grad_norm": 0.6535588837970772,
218
+ "learning_rate": 4.304635761589404e-07,
219
+ "loss": 0.6394,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 1.9907519099316446,
224
+ "grad_norm": 0.7094514579767396,
225
+ "learning_rate": 9.933774834437088e-08,
226
+ "loss": 0.643,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 2.0,
231
+ "step": 312,
232
+ "total_flos": 119307564613632.0,
233
+ "train_loss": 0.7332022241674937,
234
+ "train_runtime": 6450.9735,
235
+ "train_samples_per_second": 6.168,
236
+ "train_steps_per_second": 0.048
237
+ }
238
+ ],
239
+ "logging_steps": 10,
240
+ "max_steps": 312,
241
+ "num_input_tokens_seen": 0,
242
+ "num_train_epochs": 2,
243
+ "save_steps": 500,
244
+ "stateful_callbacks": {
245
+ "TrainerControl": {
246
+ "args": {
247
+ "should_epoch_stop": false,
248
+ "should_evaluate": false,
249
+ "should_log": false,
250
+ "should_save": true,
251
+ "should_training_stop": true
252
+ },
253
+ "attributes": {}
254
+ }
255
+ },
256
+ "total_flos": 119307564613632.0,
257
+ "train_batch_size": 1,
258
+ "trial_name": null,
259
+ "trial_params": null
260
+ }