Hugging Face's logo

daniel40
/
167f13ce-ede0-48ca-927c-00b322468a98

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
167f13ce-ede0-48ca-927c-00b322468a98
File size: 3,177 Bytes 
73616c6
 
 
e801f27
73616c6
e801f27
73616c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fead5c3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1ae556
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e801f27
 
 
 
 
 
 
73616c6
 
 
 
 
 
 
 
 
 
 
 
 
 
e801f27
73616c6
 
 
 
e801f27
73616c6
 
 
 
 
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": 0.00026468155500413565,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.6468155500413566e-05,
      "grad_norm": 2.9249105864437297e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 2.6468155500413566e-05,
      "eval_loss": 11.5,
      "eval_runtime": 88.4186,
      "eval_samples_per_second": 179.917,
      "eval_steps_per_second": 89.958,
      "step": 1
    },
    {
      "epoch": 5.293631100082713e-05,
      "grad_norm": 1.881800744740758e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 7.94044665012407e-05,
      "grad_norm": 9.297357792092953e-06,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 7.94044665012407e-05,
      "eval_loss": 11.5,
      "eval_runtime": 87.5708,
      "eval_samples_per_second": 181.659,
      "eval_steps_per_second": 90.829,
      "step": 3
    },
    {
      "epoch": 0.00010587262200165426,
      "grad_norm": 1.1598300261539407e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.00013234077750206782,
      "grad_norm": 7.736736006336287e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0001588089330024814,
      "grad_norm": 4.066749170306139e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0001588089330024814,
      "eval_loss": 11.5,
      "eval_runtime": 87.6866,
      "eval_samples_per_second": 181.419,
      "eval_steps_per_second": 90.709,
      "step": 6
    },
    {
      "epoch": 0.00018527708850289495,
      "grad_norm": 5.161886656424031e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.00021174524400330852,
      "grad_norm": 2.6241363229928538e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.00023821339950372207,
      "grad_norm": 1.9505538148223422e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.00023821339950372207,
      "eval_loss": 11.5,
      "eval_runtime": 88.1528,
      "eval_samples_per_second": 180.459,
      "eval_steps_per_second": 90.23,
      "step": 9
    },
    {
      "epoch": 0.00026468155500413565,
      "grad_norm": 1.4031124919711147e-05,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "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": 249035980800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}