Hugging Face's logo

mrferr3t
/
2dbcea98-4ffd-4b9e-8968-0b8902129e95

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
2dbcea98-4ffd-4b9e-8968-0b8902129e95
File size: 3,162 Bytes 
a22a308
 
 
c4cc267
a22a308
c4cc267
a22a308
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7bfca0c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1809c82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c4cc267
 
 
 
 
 
 
a22a308
 
 
 
 
 
 
 
 
 
 
 
 
 
c4cc267
a22a308
 
 
 
c4cc267
a22a308
 
 
 
 
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": 0.003604902667627974,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003604902667627974,
      "grad_norm": 2.7337660867488012e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0003604902667627974,
      "eval_loss": 11.5,
      "eval_runtime": 7.5615,
      "eval_samples_per_second": 154.598,
      "eval_steps_per_second": 77.365,
      "step": 1
    },
    {
      "epoch": 0.0007209805335255948,
      "grad_norm": 1.7489677702542394e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0010814708002883922,
      "grad_norm": 2.5130821086349897e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0010814708002883922,
      "eval_loss": 11.5,
      "eval_runtime": 7.5323,
      "eval_samples_per_second": 155.198,
      "eval_steps_per_second": 77.665,
      "step": 3
    },
    {
      "epoch": 0.0014419610670511895,
      "grad_norm": 1.059984333551256e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.001802451333813987,
      "grad_norm": 1.5773546692798845e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0021629416005767843,
      "grad_norm": 1.64099383255234e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0021629416005767843,
      "eval_loss": 11.5,
      "eval_runtime": 7.6482,
      "eval_samples_per_second": 152.847,
      "eval_steps_per_second": 76.489,
      "step": 6
    },
    {
      "epoch": 0.0025234318673395817,
      "grad_norm": 2.0088316887267865e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002883922134102379,
      "grad_norm": 3.462352105998434e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0032444124008651765,
      "grad_norm": 1.6997619241010398e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0032444124008651765,
      "eval_loss": 11.5,
      "eval_runtime": 7.6752,
      "eval_samples_per_second": 152.309,
      "eval_steps_per_second": 76.22,
      "step": 9
    },
    {
      "epoch": 0.003604902667627974,
      "grad_norm": 4.1601579141570255e-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": 373553971200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}