Hugging Face's logo

VERSIL91
/
254d8db6-9b67-4e4d-9aed-f616e0c4da60

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
254d8db6-9b67-4e4d-9aed-f616e0c4da60
File size: 2,951 Bytes 
abf7f63
 
 
ce94f83
abf7f63
ce94f83
abf7f63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a657da6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d67778a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce94f83
 
 
 
 
 
 
abf7f63
 
 
 
 
 
 
 
 
 
 
 
 
 
ce94f83
abf7f63
 
 
 
ce94f83
abf7f63
 
 
 
 
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": 0.013846819558632626,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013846819558632627,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0013846819558632627,
      "eval_loss": NaN,
      "eval_runtime": 270.0853,
      "eval_samples_per_second": 4.506,
      "eval_steps_per_second": 2.255,
      "step": 1
    },
    {
      "epoch": 0.0027693639117265254,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004154045867589788,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.004154045867589788,
      "eval_loss": NaN,
      "eval_runtime": 117.8854,
      "eval_samples_per_second": 10.324,
      "eval_steps_per_second": 5.166,
      "step": 3
    },
    {
      "epoch": 0.005538727823453051,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.006923409779316313,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.008308091735179575,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.008308091735179575,
      "eval_loss": NaN,
      "eval_runtime": 117.5313,
      "eval_samples_per_second": 10.355,
      "eval_steps_per_second": 5.182,
      "step": 6
    },
    {
      "epoch": 0.00969277369104284,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.011077455646906102,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.012462137602769364,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.012462137602769364,
      "eval_loss": NaN,
      "eval_runtime": 117.5745,
      "eval_samples_per_second": 10.351,
      "eval_steps_per_second": 5.18,
      "step": 9
    },
    {
      "epoch": 0.013846819558632626,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "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": 1.3049588952858624e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}