Hugging Face's logo

kk-aivio
/
d59e7bc4-de72-4495-94bb-416af32eb9e4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d59e7bc4-de72-4495-94bb-416af32eb9e4
File size: 2,957 Bytes 
ebabe8e
 
 
2867598
ebabe8e
2867598
ebabe8e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f964eaa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2e3ba4b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2867598
 
 
 
 
 
 
ebabe8e
 
 
 
 
 
 
 
 
 
 
 
 
 
2867598
ebabe8e
 
 
 
2867598
ebabe8e
 
 
 
 
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": 0.012566760917373547,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012566760917373547,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0012566760917373547,
      "eval_loss": NaN,
      "eval_runtime": 18.805,
      "eval_samples_per_second": 17.814,
      "eval_steps_per_second": 8.934,
      "step": 1
    },
    {
      "epoch": 0.0025133521834747093,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.003770028275212064,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.003770028275212064,
      "eval_loss": NaN,
      "eval_runtime": 16.766,
      "eval_samples_per_second": 19.981,
      "eval_steps_per_second": 10.02,
      "step": 3
    },
    {
      "epoch": 0.005026704366949419,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.006283380458686773,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.007540056550424128,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.6208,
      "step": 6
    },
    {
      "epoch": 0.007540056550424128,
      "eval_loss": NaN,
      "eval_runtime": 16.8263,
      "eval_samples_per_second": 19.909,
      "eval_steps_per_second": 9.984,
      "step": 6
    },
    {
      "epoch": 0.008796732642161484,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 1.526,
      "step": 7
    },
    {
      "epoch": 0.010053408733898837,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.011310084825636193,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.011310084825636193,
      "eval_loss": NaN,
      "eval_runtime": 16.7839,
      "eval_samples_per_second": 19.96,
      "eval_steps_per_second": 10.01,
      "step": 9
    },
    {
      "epoch": 0.012566760917373547,
      "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": 3122012029452288.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}