Hugging Face's logo

filipesantoscv11
/
b2a11ae9-e5da-4dc9-aa72-79c71315a215

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b2a11ae9-e5da-4dc9-aa72-79c71315a215
File size: 3,073 Bytes 
14802d0
 
 
a6f394e
14802d0
a6f394e
14802d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a9e63cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a6f394e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14802d0
 
 
 
 
 
 
 
 
 
 
 
 
 
a6f394e
14802d0
 
 
 
a6f394e
14802d0
 
 
 
 
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": 0.0012489721999604491,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.1632406665348305e-05,
      "eval_loss": NaN,
      "eval_runtime": 223.8076,
      "eval_samples_per_second": 45.191,
      "eval_steps_per_second": 22.595,
      "step": 1
    },
    {
      "epoch": 0.00012489721999604493,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00024979443999208987,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00033305925332278644,
      "eval_loss": NaN,
      "eval_runtime": 223.3852,
      "eval_samples_per_second": 45.276,
      "eval_steps_per_second": 22.638,
      "step": 8
    },
    {
      "epoch": 0.00037469165998813475,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0004995888799841797,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0006244860999802246,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0006661185066455729,
      "eval_loss": NaN,
      "eval_runtime": 223.5077,
      "eval_samples_per_second": 45.251,
      "eval_steps_per_second": 22.626,
      "step": 16
    },
    {
      "epoch": 0.0007493833199762695,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0008742805399723144,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0009991777599683595,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0009991777599683595,
      "eval_loss": NaN,
      "eval_runtime": 222.8241,
      "eval_samples_per_second": 45.39,
      "eval_steps_per_second": 22.695,
      "step": 24
    },
    {
      "epoch": 0.0011240749799644042,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0012489721999604491,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 1838672882171904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}