Hugging Face's logo

ugaoo
/
xp180

Safetensors
llama
4-bit precision
bitsandbytes
Model card Files Community
xp180
File size: 2,783 Bytes 
b2ba87f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7894736842105263,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 29.249841690063477,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.3522,
      "step": 1
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 28.9044246673584,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.3252,
      "step": 2
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 29.364099502563477,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.3516,
      "step": 3
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 29.600059509277344,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.3531,
      "step": 4
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 28.67375373840332,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.2996,
      "step": 5
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 28.520565032958984,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.261,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 28.520565032958984,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.4103,
      "step": 7
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 50.07780075073242,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.3406,
      "step": 8
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 27.654495239257812,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.2567,
      "step": 9
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 29.456050872802734,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.2952,
      "step": 10
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 29.20940399169922,
      "learning_rate": 5.5e-07,
      "loss": 2.2942,
      "step": 11
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 29.31597328186035,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.1754,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.290941060677632e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}