Hugging Face's logo

kk-aivio
/
aadee33b-7d04-4625-a97c-06c74536ab19

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
aadee33b-7d04-4625-a97c-06c74536ab19
File size: 2,940 Bytes 
acf3a76
 
 
a98eae1
acf3a76
a98eae1
acf3a76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cdfa65c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da64a85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a98eae1
 
 
 
 
 
 
acf3a76
 
 
 
 
 
 
 
 
 
 
 
 
 
a98eae1
acf3a76
 
 
 
a98eae1
acf3a76
 
 
 
 
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": 0.024891101431238332,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002489110143123833,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 2.2213,
      "step": 1
    },
    {
      "epoch": 0.002489110143123833,
      "eval_loss": NaN,
      "eval_runtime": 11.2693,
      "eval_samples_per_second": 15.085,
      "eval_steps_per_second": 7.543,
      "step": 1
    },
    {
      "epoch": 0.004978220286247666,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0074673304293715,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0074673304293715,
      "eval_loss": NaN,
      "eval_runtime": 9.8824,
      "eval_samples_per_second": 17.202,
      "eval_steps_per_second": 8.601,
      "step": 3
    },
    {
      "epoch": 0.009956440572495333,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.012445550715619166,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.014934660858743,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.014934660858743,
      "eval_loss": NaN,
      "eval_runtime": 10.1456,
      "eval_samples_per_second": 16.756,
      "eval_steps_per_second": 8.378,
      "step": 6
    },
    {
      "epoch": 0.017423771001866834,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.019912881144990666,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0224019912881145,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0224019912881145,
      "eval_loss": NaN,
      "eval_runtime": 10.0263,
      "eval_samples_per_second": 16.955,
      "eval_steps_per_second": 8.478,
      "step": 9
    },
    {
      "epoch": 0.024891101431238332,
      "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": 3886500085235712.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}