Hugging Face's logo

VERSIL91
/
980da22e-fa49-4189-8776-5ff3b65be07c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
980da22e-fa49-4189-8776-5ff3b65be07c
File size: 2,822 Bytes 
92ee1d0
 
 
1a56183
92ee1d0
1a56183
92ee1d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c43a8a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1a56183
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92ee1d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1a56183
92ee1d0
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0024655001198507004,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002739444577611889,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0002739444577611889,
      "eval_loss": NaN,
      "eval_runtime": 289.6935,
      "eval_samples_per_second": 21.222,
      "eval_steps_per_second": 10.611,
      "step": 1
    },
    {
      "epoch": 0.0005478889155223778,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0008218333732835667,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0008218333732835667,
      "eval_loss": NaN,
      "eval_runtime": 164.6021,
      "eval_samples_per_second": 37.351,
      "eval_steps_per_second": 18.675,
      "step": 3
    },
    {
      "epoch": 0.0010957778310447556,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0013697222888059445,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0016436667465671334,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0016436667465671334,
      "eval_loss": NaN,
      "eval_runtime": 164.5567,
      "eval_samples_per_second": 37.361,
      "eval_steps_per_second": 18.68,
      "step": 6
    },
    {
      "epoch": 0.0019176112043283223,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0021915556620895112,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0024655001198507004,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0024655001198507004,
      "eval_loss": NaN,
      "eval_runtime": 164.9532,
      "eval_samples_per_second": 37.271,
      "eval_steps_per_second": 18.636,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 786267969159168.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}