Hugging Face's logo

Dnsx077
/
db622137-ef49-4004-b62b-bc7305501c41

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
db622137-ef49-4004-b62b-bc7305501c41
File size: 3,195 Bytes 
22cfd2d
 
 
877bcb4
22cfd2d
877bcb4
22cfd2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fbb973d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d2f3b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
877bcb4
 
 
 
 
 
 
22cfd2d
 
 
 
 
 
 
 
 
 
 
 
 
 
877bcb4
22cfd2d
 
 
 
877bcb4
22cfd2d
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004231460911879826,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004231460911879826,
      "grad_norm": 2.2086119651794434,
      "learning_rate": 2e-05,
      "loss": 2.5751,
      "step": 1
    },
    {
      "epoch": 0.0004231460911879826,
      "eval_loss": 2.844357967376709,
      "eval_runtime": 392.816,
      "eval_samples_per_second": 2.533,
      "eval_steps_per_second": 1.268,
      "step": 1
    },
    {
      "epoch": 0.0008462921823759652,
      "grad_norm": 2.279730796813965,
      "learning_rate": 4e-05,
      "loss": 2.8377,
      "step": 2
    },
    {
      "epoch": 0.0012694382735639479,
      "grad_norm": 2.6086931228637695,
      "learning_rate": 6e-05,
      "loss": 2.8085,
      "step": 3
    },
    {
      "epoch": 0.0012694382735639479,
      "eval_loss": 2.829608201980591,
      "eval_runtime": 396.4002,
      "eval_samples_per_second": 2.51,
      "eval_steps_per_second": 1.256,
      "step": 3
    },
    {
      "epoch": 0.0016925843647519305,
      "grad_norm": 2.4624593257904053,
      "learning_rate": 8e-05,
      "loss": 2.6401,
      "step": 4
    },
    {
      "epoch": 0.002115730455939913,
      "grad_norm": 1.834259033203125,
      "learning_rate": 0.0001,
      "loss": 2.195,
      "step": 5
    },
    {
      "epoch": 0.0025388765471278957,
      "grad_norm": 2.621457099914551,
      "learning_rate": 0.00012,
      "loss": 2.7121,
      "step": 6
    },
    {
      "epoch": 0.0025388765471278957,
      "eval_loss": 2.5834829807281494,
      "eval_runtime": 396.4072,
      "eval_samples_per_second": 2.51,
      "eval_steps_per_second": 1.256,
      "step": 6
    },
    {
      "epoch": 0.0029620226383158784,
      "grad_norm": 3.0319173336029053,
      "learning_rate": 0.00014,
      "loss": 2.7119,
      "step": 7
    },
    {
      "epoch": 0.003385168729503861,
      "grad_norm": 2.3886566162109375,
      "learning_rate": 0.00016,
      "loss": 2.4817,
      "step": 8
    },
    {
      "epoch": 0.003808314820691844,
      "grad_norm": 2.3795809745788574,
      "learning_rate": 0.00018,
      "loss": 1.9891,
      "step": 9
    },
    {
      "epoch": 0.003808314820691844,
      "eval_loss": 1.9471328258514404,
      "eval_runtime": 396.3083,
      "eval_samples_per_second": 2.511,
      "eval_steps_per_second": 1.257,
      "step": 9
    },
    {
      "epoch": 0.004231460911879826,
      "grad_norm": 2.5473413467407227,
      "learning_rate": 0.0002,
      "loss": 1.8588,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.318461275897856e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}