Hugging Face's logo

xiaomama2002
/
s1.1-direct-32B

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
xiaomama2002 commited on
Commit
8fd435a
·
verified ·
1 Parent(s): cac95e7

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +252 -0
trainer_state.json ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.896,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.096,
13
+ "grad_norm": 3.609203815460205,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 0.4792,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.192,
20
+ "grad_norm": 3.4065887928009033,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.4425,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.288,
27
+ "grad_norm": 3.396181583404541,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.4887,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.384,
34
+ "grad_norm": 1.740384578704834,
35
+ "learning_rate": 9.966191788709716e-06,
36
+ "loss": 0.3527,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.48,
41
+ "grad_norm": 1.299846887588501,
42
+ "learning_rate": 9.86522435289912e-06,
43
+ "loss": 0.3075,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.576,
48
+ "grad_norm": 1.0410711765289307,
49
+ "learning_rate": 9.698463103929542e-06,
50
+ "loss": 0.3255,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.672,
55
+ "grad_norm": 0.9354220628738403,
56
+ "learning_rate": 9.468163201617063e-06,
57
+ "loss": 0.2772,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.768,
62
+ "grad_norm": 0.684252917766571,
63
+ "learning_rate": 9.177439057064684e-06,
64
+ "loss": 0.2475,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.864,
69
+ "grad_norm": 0.548189640045166,
70
+ "learning_rate": 8.83022221559489e-06,
71
+ "loss": 0.2523,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.96,
76
+ "grad_norm": 0.5903598070144653,
77
+ "learning_rate": 8.43120818934367e-06,
78
+ "loss": 0.2553,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.064,
83
+ "grad_norm": 1.125814437866211,
84
+ "learning_rate": 7.985792958513932e-06,
85
+ "loss": 0.4129,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.16,
90
+ "grad_norm": 0.6294312477111816,
91
+ "learning_rate": 7.500000000000001e-06,
92
+ "loss": 0.2131,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.256,
97
+ "grad_norm": 0.6567461490631104,
98
+ "learning_rate": 6.980398830195785e-06,
99
+ "loss": 0.2005,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.3519999999999999,
104
+ "grad_norm": 0.5858513712882996,
105
+ "learning_rate": 6.434016163555452e-06,
106
+ "loss": 0.2022,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.448,
111
+ "grad_norm": 0.6008303761482239,
112
+ "learning_rate": 5.8682408883346535e-06,
113
+ "loss": 0.1983,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.544,
118
+ "grad_norm": 0.6003760099411011,
119
+ "learning_rate": 5.290724144552379e-06,
120
+ "loss": 0.1655,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 1.6400000000000001,
125
+ "grad_norm": 0.5758850574493408,
126
+ "learning_rate": 4.7092758554476215e-06,
127
+ "loss": 0.1897,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 1.736,
132
+ "grad_norm": 0.5658831000328064,
133
+ "learning_rate": 4.131759111665349e-06,
134
+ "loss": 0.1846,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 1.8319999999999999,
139
+ "grad_norm": 0.4785068929195404,
140
+ "learning_rate": 3.5659838364445505e-06,
141
+ "loss": 0.1496,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 1.928,
146
+ "grad_norm": 0.5116356015205383,
147
+ "learning_rate": 3.019601169804216e-06,
148
+ "loss": 0.1628,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.032,
153
+ "grad_norm": 0.9877704381942749,
154
+ "learning_rate": 2.5000000000000015e-06,
155
+ "loss": 0.2728,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.128,
160
+ "grad_norm": 0.51435786485672,
161
+ "learning_rate": 2.0142070414860704e-06,
162
+ "loss": 0.1391,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 2.224,
167
+ "grad_norm": 0.4802136719226837,
168
+ "learning_rate": 1.5687918106563326e-06,
169
+ "loss": 0.1173,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 2.32,
174
+ "grad_norm": 0.45264706015586853,
175
+ "learning_rate": 1.1697777844051105e-06,
176
+ "loss": 0.1175,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 2.416,
181
+ "grad_norm": 0.506596565246582,
182
+ "learning_rate": 8.225609429353187e-07,
183
+ "loss": 0.139,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 2.512,
188
+ "grad_norm": 0.5231615304946899,
189
+ "learning_rate": 5.318367983829393e-07,
190
+ "loss": 0.1215,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 2.608,
195
+ "grad_norm": 0.4291784167289734,
196
+ "learning_rate": 3.015368960704584e-07,
197
+ "loss": 0.1056,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 2.7039999999999997,
202
+ "grad_norm": 0.4940212666988373,
203
+ "learning_rate": 1.3477564710088097e-07,
204
+ "loss": 0.1158,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 2.8,
209
+ "grad_norm": 0.4577478766441345,
210
+ "learning_rate": 3.3808211290284886e-08,
211
+ "loss": 0.1173,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 2.896,
216
+ "grad_norm": 0.48457086086273193,
217
+ "learning_rate": 0.0,
218
+ "loss": 0.1155,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 2.896,
223
+ "step": 30,
224
+ "total_flos": 14576698425344.0,
225
+ "train_loss": 0.2289695508778095,
226
+ "train_runtime": 1925.3202,
227
+ "train_samples_per_second": 1.558,
228
+ "train_steps_per_second": 0.016
229
+ }
230
+ ],
231
+ "logging_steps": 1,
232
+ "max_steps": 30,
233
+ "num_input_tokens_seen": 0,
234
+ "num_train_epochs": 3,
235
+ "save_steps": 100,
236
+ "stateful_callbacks": {
237
+ "TrainerControl": {
238
+ "args": {
239
+ "should_epoch_stop": false,
240
+ "should_evaluate": false,
241
+ "should_log": false,
242
+ "should_save": true,
243
+ "should_training_stop": true
244
+ },
245
+ "attributes": {}
246
+ }
247
+ },
248
+ "total_flos": 14576698425344.0,
249
+ "train_batch_size": 1,
250
+ "trial_name": null,
251
+ "trial_params": null
252
+ }