Hugging Face's logo

ugaoo
/
xp183

Safetensors
llama
4-bit precision
bitsandbytes
Model card Files
xet
 Community
xp183
File size: 3,772 Bytes
b13cb12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6315789473684212,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 31.074975967407227,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.6413,
      "step": 1
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 31.317493438720703,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.6669,
      "step": 2
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 30.651592254638672,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.6365,
      "step": 3
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 31.409021377563477,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.6506,
      "step": 4
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 31.246355056762695,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.6921,
      "step": 5
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 31.102157592773438,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.6521,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 31.102157592773438,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.6507,
      "step": 7
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 51.65867233276367,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.609,
      "step": 8
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 31.440189361572266,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.6483,
      "step": 9
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 31.163721084594727,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.5929,
      "step": 10
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 31.317119598388672,
      "learning_rate": 5.5e-07,
      "loss": 2.622,
      "step": 11
    },
    {
      "epoch": 1.7894736842105263,
      "grad_norm": 30.929079055786133,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.5431,
      "step": 12
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 31.02151107788086,
      "learning_rate": 6.5e-07,
      "loss": 2.4984,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 31.02151107788086,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.4068,
      "step": 14
    },
    {
      "epoch": 2.1578947368421053,
      "grad_norm": 49.92241287231445,
      "learning_rate": 7.5e-07,
      "loss": 2.4271,
      "step": 15
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 30.406696319580078,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.3558,
      "step": 16
    },
    {
      "epoch": 2.473684210526316,
      "grad_norm": 29.96433448791504,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.2551,
      "step": 17
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 29.700254440307617,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.1759,
      "step": 18
    }
  ],
  "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": 1.0721972163214049e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}