Hugging Face's logo

filipesantoscv11
/
710c5c72-b571-4714-830c-59baed18da52

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
710c5c72-b571-4714-830c-59baed18da52
File size: 3,249 Bytes 
4dfc0f0
 
 
016c389
4dfc0f0
016c389
4dfc0f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0801ae6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
016c389
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4dfc0f0
 
 
 
 
 
 
 
 
 
 
 
 
 
016c389
4dfc0f0
 
 
 
016c389
4dfc0f0
 
 
 
 
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": 0.00487685930260912,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001625619767536373,
      "eval_loss": 11.5,
      "eval_runtime": 15.9213,
      "eval_samples_per_second": 162.738,
      "eval_steps_per_second": 81.4,
      "step": 1
    },
    {
      "epoch": 0.000487685930260912,
      "grad_norm": 2.1894687961321324e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": 3.593887231545523e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0013004958140290985,
      "eval_loss": 11.5,
      "eval_runtime": 15.8611,
      "eval_samples_per_second": 163.355,
      "eval_steps_per_second": 81.709,
      "step": 8
    },
    {
      "epoch": 0.001463057790782736,
      "grad_norm": 1.1856787750730291e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.001950743721043648,
      "grad_norm": 3.105643918388523e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.00243842965130456,
      "grad_norm": 2.7490754291648045e-05,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.002600991628058197,
      "eval_loss": 11.5,
      "eval_runtime": 15.9687,
      "eval_samples_per_second": 162.255,
      "eval_steps_per_second": 81.159,
      "step": 16
    },
    {
      "epoch": 0.002926115581565472,
      "grad_norm": 2.3736220100545324e-05,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.003413801511826384,
      "grad_norm": 1.9497951143421233e-05,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.003901487442087296,
      "grad_norm": 3.0179426175891422e-05,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.003901487442087296,
      "eval_loss": 11.5,
      "eval_runtime": 15.9219,
      "eval_samples_per_second": 162.732,
      "eval_steps_per_second": 81.397,
      "step": 24
    },
    {
      "epoch": 0.0043891733723482075,
      "grad_norm": 2.72399811365176e-05,
      "learning_rate": 5.449673790581611e-06,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.00487685930260912,
      "grad_norm": 1.3301386388775427e-05,
      "learning_rate": 0.0,
      "loss": 46.0,
      "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": 1196882657280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}