Hugging Face's logo

vmpsergio
/
5a0f80a1-6b5f-4686-b04f-ee68a5fe5edd

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
5a0f80a1-6b5f-4686-b04f-ee68a5fe5edd
File size: 3,301 Bytes 
09d30f8
 
 
e57134f
09d30f8
e57134f
09d30f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b1130f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e57134f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
09d30f8
 
 
 
 
 
 
 
 
 
 
 
 
 
e57134f
09d30f8
 
 
 
e57134f
09d30f8
 
 
 
 
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": 0.006846970215679562,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022823234052265205,
      "eval_loss": 2.2855961322784424,
      "eval_runtime": 257.8182,
      "eval_samples_per_second": 7.156,
      "eval_steps_per_second": 3.58,
      "step": 1
    },
    {
      "epoch": 0.0006846970215679561,
      "grad_norm": 0.9269846081733704,
      "learning_rate": 6e-05,
      "loss": 2.2791,
      "step": 3
    },
    {
      "epoch": 0.0013693940431359123,
      "grad_norm": 0.9510827660560608,
      "learning_rate": 0.00012,
      "loss": 2.3717,
      "step": 6
    },
    {
      "epoch": 0.0018258587241812164,
      "eval_loss": 2.153048276901245,
      "eval_runtime": 258.3426,
      "eval_samples_per_second": 7.142,
      "eval_steps_per_second": 3.573,
      "step": 8
    },
    {
      "epoch": 0.0020540910647038686,
      "grad_norm": 0.6708703637123108,
      "learning_rate": 0.00018,
      "loss": 2.2041,
      "step": 9
    },
    {
      "epoch": 0.0027387880862718246,
      "grad_norm": 1.3607641458511353,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.2227,
      "step": 12
    },
    {
      "epoch": 0.003423485107839781,
      "grad_norm": 0.737883448600769,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.1457,
      "step": 15
    },
    {
      "epoch": 0.0036517174483624328,
      "eval_loss": 2.0498392581939697,
      "eval_runtime": 258.2323,
      "eval_samples_per_second": 7.145,
      "eval_steps_per_second": 3.574,
      "step": 16
    },
    {
      "epoch": 0.004108182129407737,
      "grad_norm": 0.6803624033927917,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.0524,
      "step": 18
    },
    {
      "epoch": 0.004792879150975694,
      "grad_norm": 0.5455082058906555,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.0345,
      "step": 21
    },
    {
      "epoch": 0.005477576172543649,
      "grad_norm": 1.0996414422988892,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.0625,
      "step": 24
    },
    {
      "epoch": 0.005477576172543649,
      "eval_loss": 2.0255534648895264,
      "eval_runtime": 258.4482,
      "eval_samples_per_second": 7.139,
      "eval_steps_per_second": 3.571,
      "step": 24
    },
    {
      "epoch": 0.0061622731941116055,
      "grad_norm": 0.6625553965568542,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.0498,
      "step": 27
    },
    {
      "epoch": 0.006846970215679562,
      "grad_norm": 0.5361489057540894,
      "learning_rate": 0.0,
      "loss": 2.124,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2148404268302336e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}