Hugging Face's logo

Boffl
/
BullingerLM-llama3.1-70B-pretrain-Z

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
 Community
Boffl commited on
Commit
bfb792b
·
verified ·
1 Parent(s): a5fadd0

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": 0.7132964134216309,
14
+ "learning_rate": 3.6363636363636364e-05,
15
+ "loss": 2.8806,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.1864801864801865,
20
+ "grad_norm": 0.2468750923871994,
21
+ "learning_rate": 4.934692448193334e-05,
22
+ "loss": 2.6386,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.27972027972027974,
27
+ "grad_norm": 0.3147766888141632,
28
+ "learning_rate": 4.6230054538164474e-05,
29
+ "loss": 2.5088,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.372960372960373,
34
+ "grad_norm": 0.3248756229877472,
35
+ "learning_rate": 4.085983210409114e-05,
36
+ "loss": 2.4838,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.4662004662004662,
41
+ "grad_norm": 0.19801785051822662,
42
+ "learning_rate": 3.380625119803084e-05,
43
+ "loss": 2.4479,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.5594405594405595,
48
+ "grad_norm": 0.28579196333885193,
49
+ "learning_rate": 2.5817977070544407e-05,
50
+ "loss": 2.4131,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.6526806526806527,
55
+ "grad_norm": 0.3095599412918091,
56
+ "learning_rate": 1.7742883068638447e-05,
57
+ "loss": 2.3956,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.745920745920746,
62
+ "grad_norm": 0.22690406441688538,
63
+ "learning_rate": 1.043805757830495e-05,
64
+ "loss": 2.3636,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.8391608391608392,
69
+ "grad_norm": 0.30492693185806274,
70
+ "learning_rate": 4.678832885209622e-06,
71
+ "loss": 2.3307,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.9324009324009324,
76
+ "grad_norm": 0.18911170959472656,
77
+ "learning_rate": 1.0764916066947794e-06,
78
+ "loss": 2.3372,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.9976689976689976,
83
+ "step": 107,
84
+ "total_flos": 1.4643175261407805e+18,
85
+ "train_loss": 2.473550457820714,
86
+ "train_runtime": 8966.4187,
87
+ "train_samples_per_second": 0.382,
88
+ "train_steps_per_second": 0.012
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": 1.4643175261407805e+18,
109
+ "train_batch_size": 8,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }