Hugging Face's logo

trenden
/
1b81159e-9daf-47ba-856b-7957cf3ad522

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
1b81159e-9daf-47ba-856b-7957cf3ad522
File size: 3,160 Bytes 
09e25b7
 
 
d80fe4f
09e25b7
d80fe4f
09e25b7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c884211
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b6adea9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d80fe4f
 
 
 
 
 
 
09e25b7
 
 
 
 
 
 
 
 
 
 
 
 
 
d80fe4f
09e25b7
 
 
 
d80fe4f
09e25b7
 
 
 
 
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": 2.8397016649250872e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0003604902667627974,
      "eval_loss": 11.5,
      "eval_runtime": 7.9948,
      "eval_samples_per_second": 146.221,
      "eval_steps_per_second": 73.173,
      "step": 1
    },
    {
      "epoch": 0.0007209805335255948,
      "grad_norm": 1.8306640413356945e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0010814708002883922,
      "grad_norm": 3.550108158378862e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0010814708002883922,
      "eval_loss": 11.5,
      "eval_runtime": 8.0033,
      "eval_samples_per_second": 146.065,
      "eval_steps_per_second": 73.095,
      "step": 3
    },
    {
      "epoch": 0.0014419610670511895,
      "grad_norm": 1.1271844414295629e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.001802451333813987,
      "grad_norm": 2.229763958894182e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0021629416005767843,
      "grad_norm": 1.8139169696951285e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0021629416005767843,
      "eval_loss": 11.5,
      "eval_runtime": 8.0679,
      "eval_samples_per_second": 144.895,
      "eval_steps_per_second": 72.51,
      "step": 6
    },
    {
      "epoch": 0.0025234318673395817,
      "grad_norm": 2.1264735551085323e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002883922134102379,
      "grad_norm": 3.568589090718888e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0032444124008651765,
      "grad_norm": 1.6866040823515505e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0032444124008651765,
      "eval_loss": 11.5,
      "eval_runtime": 8.0468,
      "eval_samples_per_second": 145.275,
      "eval_steps_per_second": 72.7,
      "step": 9
    },
    {
      "epoch": 0.003604902667627974,
      "grad_norm": 3.739544627023861e-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
}