Hugging Face's logo

Boffl
/
BullingerLM-llama3.1-8B-pretrain-Z

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
Boffl commited on
Commit
a03819e
·
verified ·
1 Parent(s): b8341c2

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +112 -0
trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9976689976689976,
5
+ "eval_steps": 500,
6
+ "global_step": 107,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09324009324009325,
13
+ "grad_norm": 0.34649500250816345,
14
+ "learning_rate": 4.545454545454546e-05,
15
+ "loss": 3.2724,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.1864801864801865,
20
+ "grad_norm": NaN,
21
+ "learning_rate": 4.914814565722671e-05,
22
+ "loss": 3.0626,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.27972027972027974,
27
+ "grad_norm": 0.25361865758895874,
28
+ "learning_rate": 4.5786740307563636e-05,
29
+ "loss": 2.9196,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.372960372960373,
34
+ "grad_norm": 0.2663494646549225,
35
+ "learning_rate": 4.021903572521802e-05,
36
+ "loss": 2.8823,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.4662004662004662,
41
+ "grad_norm": 0.41050922870635986,
42
+ "learning_rate": 3.303598663257904e-05,
43
+ "loss": 2.828,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.5594405594405595,
48
+ "grad_norm": 0.2641640305519104,
49
+ "learning_rate": 2.5e-05,
50
+ "loss": 2.7899,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.6526806526806527,
55
+ "grad_norm": 0.2726258635520935,
56
+ "learning_rate": 1.6964013367420966e-05,
57
+ "loss": 2.7625,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.745920745920746,
62
+ "grad_norm": 0.25895363092422485,
63
+ "learning_rate": 9.780964274781984e-06,
64
+ "loss": 2.7318,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.8391608391608392,
69
+ "grad_norm": 0.2540779709815979,
70
+ "learning_rate": 4.213259692436367e-06,
71
+ "loss": 2.7024,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.9324009324009324,
76
+ "grad_norm": 0.26027920842170715,
77
+ "learning_rate": 8.51854342773295e-07,
78
+ "loss": 2.7023,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.9976689976689976,
83
+ "step": 107,
84
+ "total_flos": 1.5832269964129075e+17,
85
+ "train_loss": 2.857464264486438,
86
+ "train_runtime": 1269.0499,
87
+ "train_samples_per_second": 2.7,
88
+ "train_steps_per_second": 0.084
89
+ }
90
+ ],
91
+ "logging_steps": 10,
92
+ "max_steps": 107,
93
+ "num_input_tokens_seen": 0,
94
+ "num_train_epochs": 1,
95
+ "save_steps": 100,
96
+ "stateful_callbacks": {
97
+ "TrainerControl": {
98
+ "args": {
99
+ "should_epoch_stop": false,
100
+ "should_evaluate": false,
101
+ "should_log": false,
102
+ "should_save": true,
103
+ "should_training_stop": true
104
+ },
105
+ "attributes": {}
106
+ }
107
+ },
108
+ "total_flos": 1.5832269964129075e+17,
109
+ "train_batch_size": 8,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }