Hugging Face's logo

yueqis
/
non_web-qwen-coder-32b-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
44bde75
·
verified ·
1 Parent(s): b696c2f

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +155 -0
trainer_state.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.9592760180995477,
6
+ "eval_steps": 500,
7
+ "global_step": 165,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.18099547511312217,
14
+ "grad_norm": 0.22652482986450195,
15
+ "learning_rate": 5e-05,
16
+ "loss": 0.4309,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.36199095022624433,
21
+ "grad_norm": 0.14215262234210968,
22
+ "learning_rate": 4.949476630105669e-05,
23
+ "loss": 0.3174,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.5429864253393665,
28
+ "grad_norm": 0.11477602273225784,
29
+ "learning_rate": 4.799948609147061e-05,
30
+ "loss": 0.2812,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.7239819004524887,
35
+ "grad_norm": 0.10571786016225815,
36
+ "learning_rate": 4.557459664734141e-05,
37
+ "loss": 0.2675,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.9049773755656109,
42
+ "grad_norm": 0.10327080637216568,
43
+ "learning_rate": 4.231810883773999e-05,
44
+ "loss": 0.2594,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.0723981900452488,
49
+ "grad_norm": 0.11652153730392456,
50
+ "learning_rate": 3.8361645653195026e-05,
51
+ "loss": 0.2349,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 1.253393665158371,
56
+ "grad_norm": 0.09489592164754868,
57
+ "learning_rate": 3.386512217606339e-05,
58
+ "loss": 0.1941,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.4343891402714932,
63
+ "grad_norm": 0.12396658211946487,
64
+ "learning_rate": 2.9010282021444008e-05,
65
+ "loss": 0.1889,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.6153846153846154,
70
+ "grad_norm": 0.09647022187709808,
71
+ "learning_rate": 2.399335149726463e-05,
72
+ "loss": 0.185,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.7963800904977374,
77
+ "grad_norm": 0.09202118217945099,
78
+ "learning_rate": 1.9017108392811065e-05,
79
+ "loss": 0.1791,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 1.9773755656108598,
84
+ "grad_norm": 0.08454926311969757,
85
+ "learning_rate": 1.4282685964923642e-05,
86
+ "loss": 0.1738,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 2.1447963800904977,
91
+ "grad_norm": 0.1310415267944336,
92
+ "learning_rate": 9.981443394050525e-06,
93
+ "loss": 0.1368,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 2.32579185520362,
98
+ "grad_norm": 0.09298953413963318,
99
+ "learning_rate": 6.28723129572247e-06,
100
+ "loss": 0.1216,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 2.506787330316742,
105
+ "grad_norm": 0.08098515123128891,
106
+ "learning_rate": 3.3493649053890326e-06,
107
+ "loss": 0.1258,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 2.6877828054298645,
112
+ "grad_norm": 0.08589061349630356,
113
+ "learning_rate": 1.286588951321363e-06,
114
+ "loss": 0.1204,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 2.8687782805429864,
119
+ "grad_norm": 0.08980952948331833,
120
+ "learning_rate": 1.8227814754865068e-07,
121
+ "loss": 0.1194,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 2.9592760180995477,
126
+ "step": 165,
127
+ "total_flos": 6047450284425216.0,
128
+ "train_loss": 0.20585341887040573,
129
+ "train_runtime": 94606.623,
130
+ "train_samples_per_second": 0.896,
131
+ "train_steps_per_second": 0.002
132
+ }
133
+ ],
134
+ "logging_steps": 10,
135
+ "max_steps": 165,
136
+ "num_input_tokens_seen": 0,
137
+ "num_train_epochs": 3,
138
+ "save_steps": 500,
139
+ "stateful_callbacks": {
140
+ "TrainerControl": {
141
+ "args": {
142
+ "should_epoch_stop": false,
143
+ "should_evaluate": false,
144
+ "should_log": false,
145
+ "should_save": true,
146
+ "should_training_stop": true
147
+ },
148
+ "attributes": {}
149
+ }
150
+ },
151
+ "total_flos": 6047450284425216.0,
152
+ "train_batch_size": 1,
153
+ "trial_name": null,
154
+ "trial_params": null
155
+ }