Hugging Face's logo

Charlie81
/
LoRE

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
LoRE
File size: 2,755 Bytes
11fe5f0
 
 
 
e59833b
11fe5f0
e59833b
11fe5f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
295afd0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e59833b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11fe5f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e59833b
11fe5f0
 
 
 
 
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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0058867896760426055,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004905658063368838,
      "grad_norm": 55.75,
      "learning_rate": 1.471550032701112e-07,
      "loss": 106.74,
      "step": 10
    },
    {
      "epoch": 0.0009811316126737675,
      "grad_norm": 53.5,
      "learning_rate": 3.106605624591236e-07,
      "loss": 106.5866,
      "step": 20
    },
    {
      "epoch": 0.0014716974190106514,
      "grad_norm": 52.75,
      "learning_rate": 4.7416612164813603e-07,
      "loss": 107.8943,
      "step": 30
    },
    {
      "epoch": 0.001962263225347535,
      "grad_norm": 68.5,
      "learning_rate": 6.376716808371485e-07,
      "loss": 109.0438,
      "step": 40
    },
    {
      "epoch": 0.002452829031684419,
      "grad_norm": 53.75,
      "learning_rate": 8.011772400261609e-07,
      "loss": 106.0855,
      "step": 50
    },
    {
      "epoch": 0.0029433948380213027,
      "grad_norm": 63.25,
      "learning_rate": 9.646827992151733e-07,
      "loss": 106.0407,
      "step": 60
    },
    {
      "epoch": 0.003433960644358187,
      "grad_norm": 54.0,
      "learning_rate": 1.1281883584041859e-06,
      "loss": 104.9819,
      "step": 70
    },
    {
      "epoch": 0.00392452645069507,
      "grad_norm": 51.25,
      "learning_rate": 1.2916939175931983e-06,
      "loss": 108.4838,
      "step": 80
    },
    {
      "epoch": 0.0044150922570319545,
      "grad_norm": 59.75,
      "learning_rate": 1.4551994767822106e-06,
      "loss": 104.6467,
      "step": 90
    },
    {
      "epoch": 0.004905658063368838,
      "grad_norm": 53.25,
      "learning_rate": 1.618705035971223e-06,
      "loss": 105.9295,
      "step": 100
    },
    {
      "epoch": 0.005396223869705722,
      "grad_norm": 55.0,
      "learning_rate": 1.7822105951602354e-06,
      "loss": 105.9408,
      "step": 110
    },
    {
      "epoch": 0.0058867896760426055,
      "grad_norm": 44.0,
      "learning_rate": 1.945716154349248e-06,
      "loss": 106.3008,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 61155,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.2647464829845504e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}