Hugging Face's logo

kk-aivio
/
5112e16c-8a4d-4c73-905f-43b385fd3d96

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
5112e16c-8a4d-4c73-905f-43b385fd3d96
File size: 3,161 Bytes 
cebaefe
 
 
8bb5b49
cebaefe
8bb5b49
cebaefe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4b76171
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58dd7c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bb5b49
 
 
 
 
 
 
cebaefe
 
 
 
 
 
 
 
 
 
 
 
 
 
8bb5b49
cebaefe
 
 
 
8bb5b49
cebaefe
 
 
 
 
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": 0.004730928444707274,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004730928444707274,
      "grad_norm": 1.4858208487567026e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0004730928444707274,
      "eval_loss": 11.5,
      "eval_runtime": 4.9213,
      "eval_samples_per_second": 180.846,
      "eval_steps_per_second": 90.423,
      "step": 1
    },
    {
      "epoch": 0.0009461856889414548,
      "grad_norm": 2.9847333280486055e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0014192785334121822,
      "grad_norm": 1.8405144146527164e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0014192785334121822,
      "eval_loss": 11.5,
      "eval_runtime": 4.895,
      "eval_samples_per_second": 181.819,
      "eval_steps_per_second": 90.91,
      "step": 3
    },
    {
      "epoch": 0.0018923713778829095,
      "grad_norm": 1.1168894161528442e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.002365464222353637,
      "grad_norm": 1.6932426660787314e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0028385570668243644,
      "grad_norm": 1.2790730579581577e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0028385570668243644,
      "eval_loss": 11.5,
      "eval_runtime": 4.9485,
      "eval_samples_per_second": 179.852,
      "eval_steps_per_second": 89.926,
      "step": 6
    },
    {
      "epoch": 0.0033116499112950917,
      "grad_norm": 2.107107502524741e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.003784742755765819,
      "grad_norm": 1.4111342352407519e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.004257835600236547,
      "grad_norm": 2.7559131922316737e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.004257835600236547,
      "eval_loss": 11.5,
      "eval_runtime": 4.9088,
      "eval_samples_per_second": 181.306,
      "eval_steps_per_second": 90.653,
      "step": 9
    },
    {
      "epoch": 0.004730928444707274,
      "grad_norm": 2.406312523817178e-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": 199228784640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}