Hugging Face's logo

nat-hunt
/
d814ffac-8147-4099-8c8c-1ff5dd867728

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d814ffac-8147-4099-8c8c-1ff5dd867728
File size: 3,195 Bytes 
44a03ca
 
 
b656c85
44a03ca
b656c85
44a03ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ba2095a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cde823d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b656c85
 
 
 
 
 
 
44a03ca
 
 
 
 
 
 
 
 
 
 
 
 
 
b656c85
44a03ca
 
 
 
b656c85
44a03ca
 
 
 
 
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": 0.007493443237167478,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007493443237167478,
      "grad_norm": 1.9591301679611206,
      "learning_rate": 2e-05,
      "loss": 1.1304,
      "step": 1
    },
    {
      "epoch": 0.0007493443237167478,
      "eval_loss": 1.6104313135147095,
      "eval_runtime": 18.4473,
      "eval_samples_per_second": 30.465,
      "eval_steps_per_second": 15.233,
      "step": 1
    },
    {
      "epoch": 0.0014986886474334957,
      "grad_norm": 2.605159044265747,
      "learning_rate": 4e-05,
      "loss": 1.5799,
      "step": 2
    },
    {
      "epoch": 0.0022480329711502436,
      "grad_norm": 1.5223053693771362,
      "learning_rate": 6e-05,
      "loss": 1.0511,
      "step": 3
    },
    {
      "epoch": 0.0022480329711502436,
      "eval_loss": 1.585645318031311,
      "eval_runtime": 17.0837,
      "eval_samples_per_second": 32.897,
      "eval_steps_per_second": 16.448,
      "step": 3
    },
    {
      "epoch": 0.0029973772948669914,
      "grad_norm": 2.100321054458618,
      "learning_rate": 8e-05,
      "loss": 1.1017,
      "step": 4
    },
    {
      "epoch": 0.003746721618583739,
      "grad_norm": 2.4209630489349365,
      "learning_rate": 0.0001,
      "loss": 1.0456,
      "step": 5
    },
    {
      "epoch": 0.004496065942300487,
      "grad_norm": 2.812591075897217,
      "learning_rate": 0.00012,
      "loss": 1.1463,
      "step": 6
    },
    {
      "epoch": 0.004496065942300487,
      "eval_loss": 1.1415724754333496,
      "eval_runtime": 17.1185,
      "eval_samples_per_second": 32.83,
      "eval_steps_per_second": 16.415,
      "step": 6
    },
    {
      "epoch": 0.005245410266017235,
      "grad_norm": 2.0659966468811035,
      "learning_rate": 0.00014,
      "loss": 0.7369,
      "step": 7
    },
    {
      "epoch": 0.005994754589733983,
      "grad_norm": 2.8209569454193115,
      "learning_rate": 0.00016,
      "loss": 0.6041,
      "step": 8
    },
    {
      "epoch": 0.0067440989134507304,
      "grad_norm": 7.074996471405029,
      "learning_rate": 0.00018,
      "loss": 0.6503,
      "step": 9
    },
    {
      "epoch": 0.0067440989134507304,
      "eval_loss": 0.537443995475769,
      "eval_runtime": 17.145,
      "eval_samples_per_second": 32.779,
      "eval_steps_per_second": 16.39,
      "step": 9
    },
    {
      "epoch": 0.007493443237167478,
      "grad_norm": 2.3110404014587402,
      "learning_rate": 0.0002,
      "loss": 0.3925,
      "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": 1895803354349568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}