Hugging Face's logo

great0001
/
c99590c6-74d7-4fe1-bea4-156afd00dcd8

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
c99590c6-74d7-4fe1-bea4-156afd00dcd8
File size: 3,014 Bytes 
2bfa28e
 
 
218148b
2bfa28e
218148b
2bfa28e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4fc779f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
218148b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2bfa28e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
218148b
2bfa28e
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006143764079459349,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.82640453273261e-05,
      "grad_norm": 1.1533392353157979e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 6.82640453273261e-05,
      "eval_loss": 11.5,
      "eval_runtime": 234.2617,
      "eval_samples_per_second": 26.33,
      "eval_steps_per_second": 13.165,
      "step": 1
    },
    {
      "epoch": 0.0001365280906546522,
      "grad_norm": 1.1955745321756694e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.00020479213598197828,
      "grad_norm": 1.3316417607711628e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00020479213598197828,
      "eval_loss": 11.5,
      "eval_runtime": 235.5688,
      "eval_samples_per_second": 26.183,
      "eval_steps_per_second": 13.092,
      "step": 3
    },
    {
      "epoch": 0.0002730561813093044,
      "grad_norm": 9.974223758035805e-06,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.00034132022663663046,
      "grad_norm": 1.7771051716408692e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.00040958427196395656,
      "grad_norm": 1.1142774383188225e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.00040958427196395656,
      "eval_loss": 11.5,
      "eval_runtime": 227.6494,
      "eval_samples_per_second": 27.094,
      "eval_steps_per_second": 13.547,
      "step": 6
    },
    {
      "epoch": 0.00047784831729128267,
      "grad_norm": 1.0504824786039535e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0005461123626186088,
      "grad_norm": 2.366983608226292e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0006143764079459349,
      "grad_norm": 1.3963933270133566e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0006143764079459349,
      "eval_loss": 11.5,
      "eval_runtime": 233.8368,
      "eval_samples_per_second": 26.377,
      "eval_steps_per_second": 13.189,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 219151663104.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}