Hugging Face's logo

omarmomen
/
sf_babylm_1

Fill-Mask
Transformers
PyTorch
English
structformer
custom_code
Model card Files Community
sf_babylm_1
File size: 2,847 Bytes 
efff561
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
{
  "best_metric": 0.7005434567019715,
  "best_model_checkpoint": "omarmomen/sf_babylm_1/finetune/main_verb_relative_token_position/checkpoint-600",
  "epoch": 10.0,
  "global_step": 1280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.56,
      "eval_accuracy": 0.6927323937416077,
      "eval_f1": 0.6946446118571896,
      "eval_loss": 2.4948320388793945,
      "eval_mcc": 0.3856146503540029,
      "eval_runtime": 40.5572,
      "eval_samples_per_second": 598.464,
      "eval_steps_per_second": 74.808,
      "step": 200
    },
    {
      "epoch": 3.12,
      "eval_accuracy": 0.6875411868095398,
      "eval_f1": 0.6927066450567261,
      "eval_loss": 2.764369010925293,
      "eval_mcc": 0.3755569894922736,
      "eval_runtime": 40.7514,
      "eval_samples_per_second": 595.612,
      "eval_steps_per_second": 74.451,
      "step": 400
    },
    {
      "epoch": 3.91,
      "learning_rate": 3.0468750000000002e-05,
      "loss": 0.0306,
      "step": 500
    },
    {
      "epoch": 4.69,
      "eval_accuracy": 0.6889832019805908,
      "eval_f1": 0.7005434567019715,
      "eval_loss": 2.911891222000122,
      "eval_mcc": 0.3796604961737416,
      "eval_runtime": 40.6436,
      "eval_samples_per_second": 597.191,
      "eval_steps_per_second": 74.649,
      "step": 600
    },
    {
      "epoch": 6.25,
      "eval_accuracy": 0.6878708004951477,
      "eval_f1": 0.6976855546687949,
      "eval_loss": 3.003314256668091,
      "eval_mcc": 0.37701315620571924,
      "eval_runtime": 40.7458,
      "eval_samples_per_second": 595.693,
      "eval_steps_per_second": 74.462,
      "step": 800
    },
    {
      "epoch": 7.81,
      "learning_rate": 1.09375e-05,
      "loss": 0.0004,
      "step": 1000
    },
    {
      "epoch": 7.81,
      "eval_accuracy": 0.6849868297576904,
      "eval_f1": 0.688045695634435,
      "eval_loss": 3.07293963432312,
      "eval_mcc": 0.3702111809587659,
      "eval_runtime": 40.7129,
      "eval_samples_per_second": 596.175,
      "eval_steps_per_second": 74.522,
      "step": 1000
    },
    {
      "epoch": 9.38,
      "eval_accuracy": 0.6858519911766052,
      "eval_f1": 0.6903804767125513,
      "eval_loss": 3.0911686420440674,
      "eval_mcc": 0.37209524754667683,
      "eval_runtime": 40.494,
      "eval_samples_per_second": 599.398,
      "eval_steps_per_second": 74.925,
      "step": 1200
    },
    {
      "epoch": 10.0,
      "step": 1280,
      "total_flos": 2095477363799040.0,
      "train_loss": 0.012110003488487564,
      "train_runtime": 513.4847,
      "train_samples_per_second": 159.245,
      "train_steps_per_second": 2.493
    }
  ],
  "max_steps": 1280,
  "num_train_epochs": 10,
  "total_flos": 2095477363799040.0,
  "trial_name": null,
  "trial_params": null
}