Hugging Face's logo

yueqis
/
non_web_sweagent-qwen-coder-7b-3epochs-30k-5e-5

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
yueqis commited on
Commit
4d33b16
·
verified ·
1 Parent(s): 13df151

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +190 -0
trainer_state.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.9888412017167383,
6
+ "eval_steps": 500,
7
+ "global_step": 216,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13733905579399142,
14
+ "grad_norm": 0.34648972749710083,
15
+ "learning_rate": 4.0909090909090915e-05,
16
+ "loss": 0.3874,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.27467811158798283,
21
+ "grad_norm": 0.15221631526947021,
22
+ "learning_rate": 4.9812354578598874e-05,
23
+ "loss": 0.2859,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.41201716738197425,
28
+ "grad_norm": 0.11299337446689606,
29
+ "learning_rate": 4.905487021607461e-05,
30
+ "loss": 0.2596,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.5493562231759657,
35
+ "grad_norm": 0.11068418622016907,
36
+ "learning_rate": 4.773356008364812e-05,
37
+ "loss": 0.2314,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.6866952789699571,
42
+ "grad_norm": 0.10527141392230988,
43
+ "learning_rate": 4.587939457093295e-05,
44
+ "loss": 0.2216,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.8240343347639485,
49
+ "grad_norm": 0.09902259707450867,
50
+ "learning_rate": 4.353583374602933e-05,
51
+ "loss": 0.2118,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.9613733905579399,
56
+ "grad_norm": 0.1092037484049797,
57
+ "learning_rate": 4.0757808688362954e-05,
58
+ "loss": 0.2063,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.109871244635193,
63
+ "grad_norm": 0.12466109544038773,
64
+ "learning_rate": 3.7610433950740665e-05,
65
+ "loss": 0.2005,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.2472103004291846,
70
+ "grad_norm": 0.1254044771194458,
71
+ "learning_rate": 3.4167481329421206e-05,
72
+ "loss": 0.1585,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.384549356223176,
77
+ "grad_norm": 0.10462108254432678,
78
+ "learning_rate": 3.0509650715736976e-05,
79
+ "loss": 0.1595,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 1.5218884120171674,
84
+ "grad_norm": 0.11514872312545776,
85
+ "learning_rate": 2.6722678559039272e-05,
86
+ "loss": 0.1506,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 1.6592274678111587,
91
+ "grad_norm": 0.10760746151208878,
92
+ "learning_rate": 2.2895328276992324e-05,
93
+ "loss": 0.1479,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 1.7965665236051502,
98
+ "grad_norm": 0.10493598878383636,
99
+ "learning_rate": 1.911730971629566e-05,
100
+ "loss": 0.1424,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 1.9339055793991418,
105
+ "grad_norm": 0.10689274221658707,
106
+ "learning_rate": 1.5477176429911934e-05,
107
+ "loss": 0.1374,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 2.082403433476395,
112
+ "grad_norm": 0.11674414575099945,
113
+ "learning_rate": 1.2060250056840089e-05,
114
+ "loss": 0.1328,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 2.219742489270386,
119
+ "grad_norm": 0.10049585998058319,
120
+ "learning_rate": 8.946620455212438e-06,
121
+ "loss": 0.1013,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 2.3570815450643776,
126
+ "grad_norm": 0.10471402108669281,
127
+ "learning_rate": 6.209268463901047e-06,
128
+ "loss": 0.0987,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 2.494420600858369,
133
+ "grad_norm": 0.10078439116477966,
134
+ "learning_rate": 3.912355293510298e-06,
135
+ "loss": 0.0995,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 2.6317596566523607,
140
+ "grad_norm": 0.09874217212200165,
141
+ "learning_rate": 2.109718641980815e-06,
142
+ "loss": 0.0968,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 2.769098712446352,
147
+ "grad_norm": 0.09445998817682266,
148
+ "learning_rate": 8.436107845804842e-07,
149
+ "loss": 0.0999,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 2.9064377682403433,
154
+ "grad_norm": 0.09762085974216461,
155
+ "learning_rate": 1.437082163835035e-07,
156
+ "loss": 0.0974,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 2.9888412017167383,
161
+ "step": 216,
162
+ "total_flos": 2672474621739008.0,
163
+ "train_loss": 0.17009929595170198,
164
+ "train_runtime": 32614.5981,
165
+ "train_samples_per_second": 3.428,
166
+ "train_steps_per_second": 0.007
167
+ }
168
+ ],
169
+ "logging_steps": 10,
170
+ "max_steps": 216,
171
+ "num_input_tokens_seen": 0,
172
+ "num_train_epochs": 3,
173
+ "save_steps": 500,
174
+ "stateful_callbacks": {
175
+ "TrainerControl": {
176
+ "args": {
177
+ "should_epoch_stop": false,
178
+ "should_evaluate": false,
179
+ "should_log": false,
180
+ "should_save": true,
181
+ "should_training_stop": true
182
+ },
183
+ "attributes": {}
184
+ }
185
+ },
186
+ "total_flos": 2672474621739008.0,
187
+ "train_batch_size": 1,
188
+ "trial_name": null,
189
+ "trial_params": null
190
+ }