Hugging Face's logo

nat-hunt
/
9696e9e8-f949-4f53-ba6b-c28602befa10

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
9696e9e8-f949-4f53-ba6b-c28602befa10
File size: 2,950 Bytes 
7ed9088
 
 
544960e
7ed9088
544960e
7ed9088
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f781f6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fc26f35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
544960e
 
 
 
 
 
 
7ed9088
 
 
 
 
 
 
 
 
 
 
 
 
 
544960e
7ed9088
 
 
 
544960e
7ed9088
 
 
 
 
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": 0.01784121320249777,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001784121320249777,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.001784121320249777,
      "eval_loss": NaN,
      "eval_runtime": 5.4795,
      "eval_samples_per_second": 43.069,
      "eval_steps_per_second": 21.535,
      "step": 1
    },
    {
      "epoch": 0.003568242640499554,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0053523639607493305,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0053523639607493305,
      "eval_loss": NaN,
      "eval_runtime": 4.9817,
      "eval_samples_per_second": 47.374,
      "eval_steps_per_second": 23.687,
      "step": 3
    },
    {
      "epoch": 0.007136485280999108,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.008920606601248885,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.010704727921498661,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010704727921498661,
      "eval_loss": NaN,
      "eval_runtime": 5.0615,
      "eval_samples_per_second": 46.627,
      "eval_steps_per_second": 23.313,
      "step": 6
    },
    {
      "epoch": 0.012488849241748439,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.014272970561998216,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.016057091882247992,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.016057091882247992,
      "eval_loss": NaN,
      "eval_runtime": 5.1203,
      "eval_samples_per_second": 46.091,
      "eval_steps_per_second": 23.045,
      "step": 9
    },
    {
      "epoch": 0.01784121320249777,
      "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": 26700766248960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}