Hugging Face's logo

nat-hunt
/
448dd4dc-0a20-4b45-9ede-c0530e3fb6f0

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
448dd4dc-0a20-4b45-9ede-c0530e3fb6f0
File size: 2,963 Bytes 
fd1b6b5
 
 
60f1a78
fd1b6b5
60f1a78
fd1b6b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a40833
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2027d01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60f1a78
 
 
 
 
 
 
fd1b6b5
 
 
 
 
 
 
 
 
 
 
 
 
 
60f1a78
fd1b6b5
 
 
 
60f1a78
fd1b6b5
 
 
 
 
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": 0.000242666909333576,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.42666909333576e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 2.42666909333576e-05,
      "eval_loss": NaN,
      "eval_runtime": 1081.3361,
      "eval_samples_per_second": 16.046,
      "eval_steps_per_second": 8.023,
      "step": 1
    },
    {
      "epoch": 4.85333818667152e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 7.28000728000728e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 7.28000728000728e-05,
      "eval_loss": NaN,
      "eval_runtime": 1078.7602,
      "eval_samples_per_second": 16.084,
      "eval_steps_per_second": 8.043,
      "step": 3
    },
    {
      "epoch": 9.70667637334304e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.000121333454666788,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0001456001456001456,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0001456001456001456,
      "eval_loss": NaN,
      "eval_runtime": 928.793,
      "eval_samples_per_second": 18.681,
      "eval_steps_per_second": 9.341,
      "step": 6
    },
    {
      "epoch": 0.0001698668365335032,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0001941335274668608,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0002184002184002184,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0002184002184002184,
      "eval_loss": NaN,
      "eval_runtime": 564.9958,
      "eval_samples_per_second": 30.71,
      "eval_steps_per_second": 15.356,
      "step": 9
    },
    {
      "epoch": 0.000242666909333576,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1796486530596864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}