Hugging Face's logo

nat-hunt
/
cf338ee4-4394-4508-bd90-dc8e103f33aa

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cf338ee4-4394-4508-bd90-dc8e103f33aa
File size: 2,988 Bytes 
5917859
 
 
b44f124
5917859
b44f124
5917859
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98f3bf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
abdb03e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b44f124
 
 
 
 
 
 
5917859
 
 
 
 
 
 
 
 
 
 
 
 
 
b44f124
5917859
 
 
 
b44f124
5917859
 
 
 
 
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": 0.0004348109659325608,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.3481096593256084e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 4.3481096593256084e-05,
      "eval_loss": NaN,
      "eval_runtime": 293.2042,
      "eval_samples_per_second": 33.028,
      "eval_steps_per_second": 16.514,
      "step": 1
    },
    {
      "epoch": 8.696219318651217e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00013044328977976824,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00013044328977976824,
      "eval_loss": NaN,
      "eval_runtime": 291.8496,
      "eval_samples_per_second": 33.181,
      "eval_steps_per_second": 16.591,
      "step": 3
    },
    {
      "epoch": 0.00017392438637302434,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0002174054829662804,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0002608865795595365,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0002608865795595365,
      "eval_loss": NaN,
      "eval_runtime": 292.3071,
      "eval_samples_per_second": 33.13,
      "eval_steps_per_second": 16.565,
      "step": 6
    },
    {
      "epoch": 0.00030436767615279255,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0003478487727460487,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 2.4797,
      "step": 8
    },
    {
      "epoch": 0.00039132986933930475,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.7781,
      "step": 9
    },
    {
      "epoch": 0.00039132986933930475,
      "eval_loss": NaN,
      "eval_runtime": 292.3145,
      "eval_samples_per_second": 33.129,
      "eval_steps_per_second": 16.564,
      "step": 9
    },
    {
      "epoch": 0.0004348109659325608,
      "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": 1684243331678208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}