Hugging Face's logo

AlanFeder
/
lora-out

PEFT
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files
xet
Community
lora-out
File size: 2,899 Bytes
56c1032
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.975609756097561,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.13416488468647003,
      "learning_rate": 2e-05,
      "loss": 1.1198,
      "step": 1
    },
    {
      "epoch": 0.0975609756097561,
      "eval_loss": 1.0946272611618042,
      "eval_runtime": 105.1442,
      "eval_samples_per_second": 0.951,
      "eval_steps_per_second": 0.476,
      "step": 1
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.14614562690258026,
      "learning_rate": 4e-05,
      "loss": 1.1433,
      "step": 2
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.12903447449207306,
      "learning_rate": 6e-05,
      "loss": 1.0338,
      "step": 3
    },
    {
      "epoch": 0.2926829268292683,
      "eval_loss": 1.0899513959884644,
      "eval_runtime": 105.534,
      "eval_samples_per_second": 0.948,
      "eval_steps_per_second": 0.474,
      "step": 3
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.12645691633224487,
      "learning_rate": 8e-05,
      "loss": 1.0196,
      "step": 4
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.15484200417995453,
      "learning_rate": 0.0001,
      "loss": 1.0868,
      "step": 5
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.13987194001674652,
      "learning_rate": 0.00012,
      "loss": 1.0658,
      "step": 6
    },
    {
      "epoch": 0.5853658536585366,
      "eval_loss": 1.0339258909225464,
      "eval_runtime": 105.5831,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.474,
      "step": 6
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.10199978202581406,
      "learning_rate": 0.00014,
      "loss": 1.0156,
      "step": 7
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.12288854271173477,
      "learning_rate": 0.00016,
      "loss": 1.0503,
      "step": 8
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.12781274318695068,
      "learning_rate": 0.00018,
      "loss": 1.0521,
      "step": 9
    },
    {
      "epoch": 0.8780487804878049,
      "eval_loss": 0.9954264163970947,
      "eval_runtime": 105.5993,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.473,
      "step": 9
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.11168772727251053,
      "learning_rate": 0.0002,
      "loss": 1.0098,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 10,
  "total_flos": 1.492020904329216e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}