Hugging Face's logo

heitorrosa
/
logun-base

Fill-Mask
PEFT
Safetensors
Transformers
modernbert
lora
dapt
sft
Model card Files
xet
 Community
1
heitorrosa commited on
Commit
0e32412
·
verified ·
1 Parent(s): 162b04a

Delete heitorrosa/logun-base/sft/checkpoint-150/trainer_state.json

Browse files
Files changed (1) hide show
  1. sft/checkpoint-150/trainer_state.json +0 -114
sft/checkpoint-150/trainer_state.json DELETED
@@ -1,114 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.1701162461015027,
6
- "eval_steps": 150,
7
- "global_step": 150,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.01701162461015027,
14
- "grad_norm": 116.99359893798828,
15
- "learning_rate": 4.666666666666667e-06,
16
- "loss": 39.077762858072916,
17
- "step": 15
18
- },
19
- {
20
- "epoch": 0.03402324922030054,
21
- "grad_norm": 114.67162322998047,
22
- "learning_rate": 9.666666666666667e-06,
23
- "loss": 37.629154459635416,
24
- "step": 30
25
- },
26
- {
27
- "epoch": 0.05103487383045081,
28
- "grad_norm": 78.71202850341797,
29
- "learning_rate": 1.4666666666666668e-05,
30
- "loss": 36.40402018229167,
31
- "step": 45
32
- },
33
- {
34
- "epoch": 0.06804649844060108,
35
- "grad_norm": 77.94384002685547,
36
- "learning_rate": 1.9666666666666666e-05,
37
- "loss": 35.03992513020833,
38
- "step": 60
39
- },
40
- {
41
- "epoch": 0.08505812305075135,
42
- "grad_norm": 69.6011734008789,
43
- "learning_rate": 2.466666666666667e-05,
44
- "loss": 34.81482747395833,
45
- "step": 75
46
- },
47
- {
48
- "epoch": 0.10206974766090161,
49
- "grad_norm": 74.6609878540039,
50
- "learning_rate": 2.9666666666666672e-05,
51
- "loss": 33.83201497395833,
52
- "step": 90
53
- },
54
- {
55
- "epoch": 0.11908137227105188,
56
- "grad_norm": 73.47967529296875,
57
- "learning_rate": 3.466666666666667e-05,
58
- "loss": 34.1611328125,
59
- "step": 105
60
- },
61
- {
62
- "epoch": 0.13609299688120216,
63
- "grad_norm": 57.3227424621582,
64
- "learning_rate": 3.966666666666667e-05,
65
- "loss": 33.17495524088542,
66
- "step": 120
67
- },
68
- {
69
- "epoch": 0.15310462149135243,
70
- "grad_norm": 41.92803955078125,
71
- "learning_rate": 4.466666666666667e-05,
72
- "loss": 33.14850056966146,
73
- "step": 135
74
- },
75
- {
76
- "epoch": 0.1701162461015027,
77
- "grad_norm": 57.70565414428711,
78
- "learning_rate": 4.966666666666667e-05,
79
- "loss": 33.152496337890625,
80
- "step": 150
81
- },
82
- {
83
- "epoch": 0.1701162461015027,
84
- "eval_accuracy": 0.519298245614035,
85
- "eval_loss": 1.9665578603744507,
86
- "eval_macro_f1": 0.43657905964809113,
87
- "eval_runtime": 7.6538,
88
- "eval_samples_per_second": 74.472,
89
- "eval_steps_per_second": 9.407,
90
- "step": 150
91
- }
92
- ],
93
- "logging_steps": 15,
94
- "max_steps": 1323,
95
- "num_input_tokens_seen": 0,
96
- "num_train_epochs": 2,
97
- "save_steps": 150,
98
- "stateful_callbacks": {
99
- "TrainerControl": {
100
- "args": {
101
- "should_epoch_stop": false,
102
- "should_evaluate": false,
103
- "should_log": false,
104
- "should_save": true,
105
- "should_training_stop": false
106
- },
107
- "attributes": {}
108
- }
109
- },
110
- "total_flos": 361691504181248.0,
111
- "train_batch_size": 2,
112
- "trial_name": null,
113
- "trial_params": null
114
- }