xingxm commited on
Commit
f4b22d1
·
verified ·
1 Parent(s): 23799ae

Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/trainer_state.json

Browse files
designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.6756756756756757,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06756756756756757,
14
+ "grad_norm": 3.5905625890982313,
15
+ "learning_rate": 3e-06,
16
+ "loss": 1.327353572845459,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.13513513513513514,
21
+ "grad_norm": 1.2623528349877715,
22
+ "learning_rate": 6.333333333333333e-06,
23
+ "loss": 0.9504005432128906,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.20270270270270271,
28
+ "grad_norm": 0.5826406357300133,
29
+ "learning_rate": 9.666666666666667e-06,
30
+ "loss": 0.7079431533813476,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.2702702702702703,
35
+ "grad_norm": 0.5175673714866398,
36
+ "learning_rate": 9.971780289496585e-06,
37
+ "loss": 0.6138272285461426,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.33783783783783783,
42
+ "grad_norm": 0.4314173287603003,
43
+ "learning_rate": 9.874639560909118e-06,
44
+ "loss": 0.567446231842041,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.40540540540540543,
49
+ "grad_norm": 0.43902172959797603,
50
+ "learning_rate": 9.70958251970347e-06,
51
+ "loss": 0.539431095123291,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.47297297297297297,
56
+ "grad_norm": 0.4756357822639688,
57
+ "learning_rate": 9.478908836546629e-06,
58
+ "loss": 0.5228753566741944,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.5405405405405406,
63
+ "grad_norm": 0.5308781274621973,
64
+ "learning_rate": 9.185832391312644e-06,
65
+ "loss": 0.5104542732238769,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.6081081081081081,
70
+ "grad_norm": 0.5705458844047502,
71
+ "learning_rate": 8.834436495439588e-06,
72
+ "loss": 0.5040336608886719,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.6756756756756757,
77
+ "grad_norm": 0.5934341387838614,
78
+ "learning_rate": 8.429617000860441e-06,
79
+ "loss": 0.49561896324157717,
80
+ "step": 100
81
+ }
82
+ ],
83
+ "logging_steps": 10,
84
+ "max_steps": 296,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 2,
87
+ "save_steps": 50,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 4.465728839137362e+17,
101
+ "train_batch_size": 2,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }