Hugging Face's logo

aixk
/
fs8

Safetensors
Model card Files
xet
 Community
fs8
File size: 2,424 Bytes
bbba145
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005289256198347108,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005289256198347108,
      "grad_norm": 2042.0159912109375,
      "learning_rate": 3.2e-07,
      "loss": 8.126,
      "step": 10
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 132.607666015625,
      "learning_rate": 1.12e-06,
      "loss": 8.0108,
      "step": 20
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 117.4473876953125,
      "learning_rate": 1.92e-06,
      "loss": 7.8388,
      "step": 30
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 58.00923538208008,
      "learning_rate": 2.72e-06,
      "loss": 7.7671,
      "step": 40
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 62.31724166870117,
      "learning_rate": 3.52e-06,
      "loss": 7.821,
      "step": 50
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 99.75863647460938,
      "learning_rate": 4.32e-06,
      "loss": 7.6772,
      "step": 60
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 337.9526672363281,
      "learning_rate": 5.12e-06,
      "loss": 7.8172,
      "step": 70
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 95.75334167480469,
      "learning_rate": 5.920000000000001e-06,
      "loss": 7.6801,
      "step": 80
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 589.1984252929688,
      "learning_rate": 6.72e-06,
      "loss": 7.7462,
      "step": 90
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 115.37745666503906,
      "learning_rate": 7.520000000000001e-06,
      "loss": 7.5665,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 529,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1740714979737600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}