Hugging Face's logo

trenden
/
be9fafe2-026b-4fb8-a30e-5b397f8bcfa8

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
be9fafe2-026b-4fb8-a30e-5b397f8bcfa8
File size: 2,964 Bytes 
e489862
 
 
61d638b
e489862
61d638b
e489862
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
044e7d8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
704343e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61d638b
 
 
 
 
 
 
e489862
 
 
 
 
 
 
 
 
 
 
 
 
 
61d638b
e489862
 
 
 
61d638b
e489862
 
 
 
 
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": 0.0026838432635534087,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00026838432635534085,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00026838432635534085,
      "eval_loss": NaN,
      "eval_runtime": 82.8646,
      "eval_samples_per_second": 18.934,
      "eval_steps_per_second": 9.473,
      "step": 1
    },
    {
      "epoch": 0.0005367686527106817,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0008051529790660225,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0008051529790660225,
      "eval_loss": NaN,
      "eval_runtime": 81.5164,
      "eval_samples_per_second": 19.248,
      "eval_steps_per_second": 9.63,
      "step": 3
    },
    {
      "epoch": 0.0010735373054213634,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0013419216317767043,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.001610305958132045,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.001610305958132045,
      "eval_loss": NaN,
      "eval_runtime": 81.6234,
      "eval_samples_per_second": 19.222,
      "eval_steps_per_second": 9.617,
      "step": 6
    },
    {
      "epoch": 0.001878690284487386,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0021470746108427268,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0024154589371980675,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0024154589371980675,
      "eval_loss": NaN,
      "eval_runtime": 81.5929,
      "eval_samples_per_second": 19.23,
      "eval_steps_per_second": 9.621,
      "step": 9
    },
    {
      "epoch": 0.0026838432635534087,
      "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": 3505339571896320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}