Hugging Face's logo

kk-aivio
/
29fe2450-46be-4bb4-80c0-48a642daeb9c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
29fe2450-46be-4bb4-80c0-48a642daeb9c
File size: 2,969 Bytes 
d846460
 
 
5f99f6a
d846460
5f99f6a
d846460
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dcaa61f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0eeb35b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f99f6a
 
 
 
 
 
 
d846460
 
 
 
 
 
 
 
 
 
 
 
 
 
5f99f6a
d846460
 
 
 
5f99f6a
d846460
 
 
 
 
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": 0.003182432970005569,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003182432970005569,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.4965,
      "step": 1
    },
    {
      "epoch": 0.0003182432970005569,
      "eval_loss": NaN,
      "eval_runtime": 75.1726,
      "eval_samples_per_second": 17.613,
      "eval_steps_per_second": 8.806,
      "step": 1
    },
    {
      "epoch": 0.0006364865940011138,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0009547298910016707,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0009547298910016707,
      "eval_loss": NaN,
      "eval_runtime": 74.1338,
      "eval_samples_per_second": 17.86,
      "eval_steps_per_second": 8.93,
      "step": 3
    },
    {
      "epoch": 0.0012729731880022277,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0015912164850027846,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0019094597820033415,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 1.06,
      "step": 6
    },
    {
      "epoch": 0.0019094597820033415,
      "eval_loss": NaN,
      "eval_runtime": 74.1717,
      "eval_samples_per_second": 17.85,
      "eval_steps_per_second": 8.925,
      "step": 6
    },
    {
      "epoch": 0.0022277030790038986,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 1.1596,
      "step": 7
    },
    {
      "epoch": 0.0025459463760044553,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0028641896730050125,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0028641896730050125,
      "eval_loss": NaN,
      "eval_runtime": 74.1463,
      "eval_samples_per_second": 17.857,
      "eval_steps_per_second": 8.928,
      "step": 9
    },
    {
      "epoch": 0.003182432970005569,
      "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": 4283942672793600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}