Hugging Face's logo

Best000
/
a319b4fe-b08e-4310-9c71-c615fcbce748

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
a319b4fe-b08e-4310-9c71-c615fcbce748
File size: 3,175 Bytes 
cff05c4
 
 
298011f
cff05c4
298011f
cff05c4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa32139
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25f8d72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298011f
 
 
 
 
 
 
cff05c4
 
 
 
 
 
 
 
 
 
 
 
 
 
298011f
cff05c4
 
 
 
298011f
cff05c4
 
 
 
 
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": 0.0006826404532732609,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.82640453273261e-05,
      "grad_norm": 1.0312207450624555e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 6.82640453273261e-05,
      "eval_loss": 11.5,
      "eval_runtime": 219.9365,
      "eval_samples_per_second": 28.044,
      "eval_steps_per_second": 14.022,
      "step": 1
    },
    {
      "epoch": 0.0001365280906546522,
      "grad_norm": 1.0248472790408414e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.00020479213598197828,
      "grad_norm": 1.0351810487918556e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00020479213598197828,
      "eval_loss": 11.5,
      "eval_runtime": 234.4844,
      "eval_samples_per_second": 26.305,
      "eval_steps_per_second": 13.152,
      "step": 3
    },
    {
      "epoch": 0.0002730561813093044,
      "grad_norm": 8.629100193502381e-06,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.00034132022663663046,
      "grad_norm": 1.4386303519131616e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.00040958427196395656,
      "grad_norm": 1.0215183465334121e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.00040958427196395656,
      "eval_loss": 11.5,
      "eval_runtime": 233.8134,
      "eval_samples_per_second": 26.38,
      "eval_steps_per_second": 13.19,
      "step": 6
    },
    {
      "epoch": 0.00047784831729128267,
      "grad_norm": 7.424625891871983e-06,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0005461123626186088,
      "grad_norm": 1.8153745259041898e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0006143764079459349,
      "grad_norm": 1.0418201782158576e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0006143764079459349,
      "eval_loss": 11.5,
      "eval_runtime": 235.0273,
      "eval_samples_per_second": 26.244,
      "eval_steps_per_second": 13.122,
      "step": 9
    },
    {
      "epoch": 0.0006826404532732609,
      "grad_norm": 1.5078968317538965e-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": 254016700416.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}