Hugging Face's logo

leixa
/
c4eea9fc-2882-45d0-92bb-29040f1c2fed

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
c4eea9fc-2882-45d0-92bb-29040f1c2fed
File size: 3,402 Bytes 
a308b31
 
 
341e7a3
a308b31
341e7a3
a308b31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e3feb53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
faf7498
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f56dc0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
341e7a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a308b31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
341e7a3
a308b31
 
 
 
 
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
137
138
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005862351975612616,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023449407902450463,
      "eval_loss": 1.0330525636672974,
      "eval_runtime": 1094.0868,
      "eval_samples_per_second": 6.564,
      "eval_steps_per_second": 0.821,
      "step": 1
    },
    {
      "epoch": 0.0007034822370735139,
      "grad_norm": 3.4436771869659424,
      "learning_rate": 3e-05,
      "loss": 4.3657,
      "step": 3
    },
    {
      "epoch": 0.0011724703951225231,
      "eval_loss": 0.9120507836341858,
      "eval_runtime": 1097.6215,
      "eval_samples_per_second": 6.543,
      "eval_steps_per_second": 0.818,
      "step": 5
    },
    {
      "epoch": 0.0014069644741470278,
      "grad_norm": 3.4235165119171143,
      "learning_rate": 6e-05,
      "loss": 3.8288,
      "step": 6
    },
    {
      "epoch": 0.002110446711220542,
      "grad_norm": 2.5789833068847656,
      "learning_rate": 9e-05,
      "loss": 2.9521,
      "step": 9
    },
    {
      "epoch": 0.0023449407902450463,
      "eval_loss": 0.611504077911377,
      "eval_runtime": 1097.4338,
      "eval_samples_per_second": 6.544,
      "eval_steps_per_second": 0.818,
      "step": 10
    },
    {
      "epoch": 0.0028139289482940555,
      "grad_norm": 1.891883134841919,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.4376,
      "step": 12
    },
    {
      "epoch": 0.0035174111853675696,
      "grad_norm": 1.4731217622756958,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1727,
      "step": 15
    },
    {
      "epoch": 0.0035174111853675696,
      "eval_loss": 0.5438524484634399,
      "eval_runtime": 1097.8515,
      "eval_samples_per_second": 6.542,
      "eval_steps_per_second": 0.818,
      "step": 15
    },
    {
      "epoch": 0.004220893422441084,
      "grad_norm": 1.4727015495300293,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.0787,
      "step": 18
    },
    {
      "epoch": 0.0046898815804900925,
      "eval_loss": 0.5278410911560059,
      "eval_runtime": 1097.7064,
      "eval_samples_per_second": 6.543,
      "eval_steps_per_second": 0.818,
      "step": 20
    },
    {
      "epoch": 0.004924375659514597,
      "grad_norm": 1.5371854305267334,
      "learning_rate": 8.247240241650918e-05,
      "loss": 2.1324,
      "step": 21
    },
    {
      "epoch": 0.005627857896588111,
      "grad_norm": 1.4840267896652222,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.9502,
      "step": 24
    },
    {
      "epoch": 0.005862351975612616,
      "eval_loss": 0.5124460458755493,
      "eval_runtime": 1097.1769,
      "eval_samples_per_second": 6.546,
      "eval_steps_per_second": 0.818,
      "step": 25
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.4401180721152e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}