Hugging Face's logo

dimasik1987
/
5aa407fb-7336-4e21-87a7-80e987ee6437

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
5aa407fb-7336-4e21-87a7-80e987ee6437
File size: 3,177 Bytes 
6e2487e
 
 
3bc1007
6e2487e
3bc1007
6e2487e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3bc1007
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6e2487e
 
 
 
 
 
 
 
 
 
 
 
 
 
3bc1007
6e2487e
 
 
 
3bc1007
6e2487e
 
 
 
 
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": 0.023837902264600714,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023837902264600714,
      "grad_norm": 1.388173222541809,
      "learning_rate": 2e-05,
      "loss": 3.4581,
      "step": 1
    },
    {
      "epoch": 0.0023837902264600714,
      "eval_loss": 4.8837971687316895,
      "eval_runtime": 23.6073,
      "eval_samples_per_second": 7.498,
      "eval_steps_per_second": 3.77,
      "step": 1
    },
    {
      "epoch": 0.004767580452920143,
      "grad_norm": 1.1888856887817383,
      "learning_rate": 4e-05,
      "loss": 2.9179,
      "step": 2
    },
    {
      "epoch": 0.007151370679380214,
      "grad_norm": 1.1461793184280396,
      "learning_rate": 6e-05,
      "loss": 2.6894,
      "step": 3
    },
    {
      "epoch": 0.007151370679380214,
      "eval_loss": 4.878833293914795,
      "eval_runtime": 23.0772,
      "eval_samples_per_second": 7.67,
      "eval_steps_per_second": 3.857,
      "step": 3
    },
    {
      "epoch": 0.009535160905840286,
      "grad_norm": 1.5066274404525757,
      "learning_rate": 8e-05,
      "loss": 3.0156,
      "step": 4
    },
    {
      "epoch": 0.011918951132300357,
      "grad_norm": 1.1865642070770264,
      "learning_rate": 0.0001,
      "loss": 2.993,
      "step": 5
    },
    {
      "epoch": 0.014302741358760428,
      "grad_norm": 1.3507497310638428,
      "learning_rate": 0.00012,
      "loss": 2.5632,
      "step": 6
    },
    {
      "epoch": 0.014302741358760428,
      "eval_loss": 4.79640007019043,
      "eval_runtime": 23.1984,
      "eval_samples_per_second": 7.63,
      "eval_steps_per_second": 3.836,
      "step": 6
    },
    {
      "epoch": 0.0166865315852205,
      "grad_norm": 1.5210137367248535,
      "learning_rate": 0.00014,
      "loss": 3.0109,
      "step": 7
    },
    {
      "epoch": 0.01907032181168057,
      "grad_norm": 1.6760146617889404,
      "learning_rate": 0.00016,
      "loss": 2.6024,
      "step": 8
    },
    {
      "epoch": 0.021454112038140644,
      "grad_norm": 2.1592094898223877,
      "learning_rate": 0.00018,
      "loss": 2.3319,
      "step": 9
    },
    {
      "epoch": 0.021454112038140644,
      "eval_loss": 4.315332889556885,
      "eval_runtime": 23.146,
      "eval_samples_per_second": 7.647,
      "eval_steps_per_second": 3.845,
      "step": 9
    },
    {
      "epoch": 0.023837902264600714,
      "grad_norm": 1.8350367546081543,
      "learning_rate": 0.0002,
      "loss": 2.9011,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}