Hugging Face's logo

nat-hunt
/
6716bef0-46d1-4b0a-84bc-7b7201d23a37

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
6716bef0-46d1-4b0a-84bc-7b7201d23a37
File size: 3,205 Bytes 
2049e69
 
 
dfaecb6
2049e69
dfaecb6
2049e69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1c4d17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91b4ee3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dfaecb6
 
 
 
 
 
 
2049e69
 
 
 
 
 
 
 
 
 
 
 
 
 
dfaecb6
2049e69
 
 
 
dfaecb6
2049e69
 
 
 
 
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": 0.0012305420537746877,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012305420537746877,
      "grad_norm": 0.8632257580757141,
      "learning_rate": 2e-05,
      "loss": 0.748,
      "step": 1
    },
    {
      "epoch": 0.00012305420537746877,
      "eval_loss": 0.879511833190918,
      "eval_runtime": 129.4136,
      "eval_samples_per_second": 26.442,
      "eval_steps_per_second": 13.221,
      "step": 1
    },
    {
      "epoch": 0.00024610841075493753,
      "grad_norm": 0.734817385673523,
      "learning_rate": 4e-05,
      "loss": 0.6559,
      "step": 2
    },
    {
      "epoch": 0.0003691626161324063,
      "grad_norm": 1.451820731163025,
      "learning_rate": 6e-05,
      "loss": 0.7293,
      "step": 3
    },
    {
      "epoch": 0.0003691626161324063,
      "eval_loss": 0.8606021404266357,
      "eval_runtime": 128.1351,
      "eval_samples_per_second": 26.706,
      "eval_steps_per_second": 13.353,
      "step": 3
    },
    {
      "epoch": 0.0004922168215098751,
      "grad_norm": 1.176847219467163,
      "learning_rate": 8e-05,
      "loss": 1.0256,
      "step": 4
    },
    {
      "epoch": 0.0006152710268873438,
      "grad_norm": 0.9159776568412781,
      "learning_rate": 0.0001,
      "loss": 0.7577,
      "step": 5
    },
    {
      "epoch": 0.0007383252322648126,
      "grad_norm": 0.7881878018379211,
      "learning_rate": 0.00012,
      "loss": 0.5812,
      "step": 6
    },
    {
      "epoch": 0.0007383252322648126,
      "eval_loss": 0.5984408259391785,
      "eval_runtime": 128.1993,
      "eval_samples_per_second": 26.693,
      "eval_steps_per_second": 13.346,
      "step": 6
    },
    {
      "epoch": 0.0008613794376422815,
      "grad_norm": 0.7859431505203247,
      "learning_rate": 0.00014,
      "loss": 0.4963,
      "step": 7
    },
    {
      "epoch": 0.0009844336430197501,
      "grad_norm": 1.107433795928955,
      "learning_rate": 0.00016,
      "loss": 0.44,
      "step": 8
    },
    {
      "epoch": 0.001107487848397219,
      "grad_norm": 1.0245170593261719,
      "learning_rate": 0.00018,
      "loss": 0.2713,
      "step": 9
    },
    {
      "epoch": 0.001107487848397219,
      "eval_loss": 0.1577470749616623,
      "eval_runtime": 128.0679,
      "eval_samples_per_second": 26.72,
      "eval_steps_per_second": 13.36,
      "step": 9
    },
    {
      "epoch": 0.0012305420537746877,
      "grad_norm": 1.437125563621521,
      "learning_rate": 0.0002,
      "loss": 0.1699,
      "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": 2358194416386048.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}