Hugging Face's logo

VERSIL91
/
d84aae25-72be-4452-a733-b23ce462f38d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d84aae25-72be-4452-a733-b23ce462f38d
File size: 3,210 Bytes 
b5bd160
 
 
dea8a4e
b5bd160
dea8a4e
b5bd160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5997de5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c562156
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dea8a4e
 
 
 
 
 
 
b5bd160
 
 
 
 
 
 
 
 
 
 
 
 
 
dea8a4e
b5bd160
 
 
 
dea8a4e
b5bd160
 
 
 
 
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": 0.0033751713954224237,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033751713954224236,
      "grad_norm": 0.4469277560710907,
      "learning_rate": 1e-05,
      "loss": 1.1908,
      "step": 1
    },
    {
      "epoch": 0.00033751713954224236,
      "eval_loss": 1.1857836246490479,
      "eval_runtime": 255.5797,
      "eval_samples_per_second": 19.524,
      "eval_steps_per_second": 9.762,
      "step": 1
    },
    {
      "epoch": 0.0006750342790844847,
      "grad_norm": 0.40224871039390564,
      "learning_rate": 2e-05,
      "loss": 1.1118,
      "step": 2
    },
    {
      "epoch": 0.0010125514186267272,
      "grad_norm": 0.34902000427246094,
      "learning_rate": 3e-05,
      "loss": 1.0579,
      "step": 3
    },
    {
      "epoch": 0.0010125514186267272,
      "eval_loss": 1.1678147315979004,
      "eval_runtime": 176.6542,
      "eval_samples_per_second": 28.247,
      "eval_steps_per_second": 14.124,
      "step": 3
    },
    {
      "epoch": 0.0013500685581689694,
      "grad_norm": 0.41233962774276733,
      "learning_rate": 4e-05,
      "loss": 1.1444,
      "step": 4
    },
    {
      "epoch": 0.0016875856977112118,
      "grad_norm": 0.3759932518005371,
      "learning_rate": 5e-05,
      "loss": 1.1329,
      "step": 5
    },
    {
      "epoch": 0.0020251028372534545,
      "grad_norm": 0.42395076155662537,
      "learning_rate": 6e-05,
      "loss": 1.1086,
      "step": 6
    },
    {
      "epoch": 0.0020251028372534545,
      "eval_loss": 1.1323615312576294,
      "eval_runtime": 176.7605,
      "eval_samples_per_second": 28.23,
      "eval_steps_per_second": 14.115,
      "step": 6
    },
    {
      "epoch": 0.0023626199767956967,
      "grad_norm": 0.5308507680892944,
      "learning_rate": 7e-05,
      "loss": 1.2025,
      "step": 7
    },
    {
      "epoch": 0.002700137116337939,
      "grad_norm": 0.47383561730384827,
      "learning_rate": 8e-05,
      "loss": 0.9867,
      "step": 8
    },
    {
      "epoch": 0.0030376542558801815,
      "grad_norm": 0.4871196150779724,
      "learning_rate": 9e-05,
      "loss": 1.0586,
      "step": 9
    },
    {
      "epoch": 0.0030376542558801815,
      "eval_loss": 1.0454866886138916,
      "eval_runtime": 176.7058,
      "eval_samples_per_second": 28.239,
      "eval_steps_per_second": 14.12,
      "step": 9
    },
    {
      "epoch": 0.0033751713954224237,
      "grad_norm": 0.3529665470123291,
      "learning_rate": 0.0001,
      "loss": 1.029,
      "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": 1.07108490018816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}