Hugging Face's logo

yueqis
/
unified-agent-code-mix-sample

Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
yueqis commited on
Commit
6306c98
·
verified ·
1 Parent(s): c57646c

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +113 -0
trainer_state.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9947704822777454,
6
+ "eval_steps": 1000,
7
+ "global_step": 107,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.09296920395119117,
14
+ "grad_norm": 0.7048821800444566,
15
+ "learning_rate": 9.978246739845095e-06,
16
+ "loss": 0.8236,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.18593840790238234,
21
+ "grad_norm": 0.4150380996837911,
22
+ "learning_rate": 9.596765194911182e-06,
23
+ "loss": 0.5002,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.2789076118535735,
28
+ "grad_norm": 0.3590804657677201,
29
+ "learning_rate": 8.774114695766286e-06,
30
+ "loss": 0.4698,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.37187681580476467,
35
+ "grad_norm": 0.3203064886912417,
36
+ "learning_rate": 7.589248124491627e-06,
37
+ "loss": 0.4408,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.46484601975595585,
42
+ "grad_norm": 0.319927362444108,
43
+ "learning_rate": 6.15588161057485e-06,
44
+ "loss": 0.4316,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.557815223707147,
49
+ "grad_norm": 0.3063736106799291,
50
+ "learning_rate": 4.611580763554969e-06,
51
+ "loss": 0.439,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.6507844276583382,
56
+ "grad_norm": 0.3055856222140526,
57
+ "learning_rate": 3.104557980798104e-06,
58
+ "loss": 0.4321,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.7437536316095293,
63
+ "grad_norm": 0.3197809936930162,
64
+ "learning_rate": 1.7794479427480115e-06,
65
+ "loss": 0.4268,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.8367228355607205,
70
+ "grad_norm": 0.3159717120836253,
71
+ "learning_rate": 7.634264752111131e-07,
72
+ "loss": 0.421,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.9296920395119117,
77
+ "grad_norm": 0.3098749060038542,
78
+ "learning_rate": 1.540050040016694e-07,
79
+ "loss": 0.435,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.9947704822777454,
84
+ "step": 107,
85
+ "total_flos": 145069794394112.0,
86
+ "train_loss": 0.4802975632319941,
87
+ "train_runtime": 3035.4853,
88
+ "train_samples_per_second": 4.534,
89
+ "train_steps_per_second": 0.035
90
+ }
91
+ ],
92
+ "logging_steps": 10,
93
+ "max_steps": 107,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 1,
96
+ "save_steps": 100,
97
+ "stateful_callbacks": {
98
+ "TrainerControl": {
99
+ "args": {
100
+ "should_epoch_stop": false,
101
+ "should_evaluate": false,
102
+ "should_log": false,
103
+ "should_save": true,
104
+ "should_training_stop": true
105
+ },
106
+ "attributes": {}
107
+ }
108
+ },
109
+ "total_flos": 145069794394112.0,
110
+ "train_batch_size": 1,
111
+ "trial_name": null,
112
+ "trial_params": null
113
+ }