Hugging Face's logo

philip-hightech
/
833687b1-86b1-44d4-aeed-68eaef8ceb40

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
833687b1-86b1-44d4-aeed-68eaef8ceb40
File size: 2,977 Bytes 
491502f
 
 
3b72c89
491502f
3b72c89
491502f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fcddd81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a228e8b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b72c89
 
 
 
 
 
 
491502f
 
 
 
 
 
 
 
 
 
 
 
 
 
3b72c89
491502f
 
 
 
3b72c89
491502f
 
 
 
 
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": 0.0005868630701741516,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.868630701741516e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 5.868630701741516e-05,
      "eval_loss": NaN,
      "eval_runtime": 160.8993,
      "eval_samples_per_second": 44.593,
      "eval_steps_per_second": 22.3,
      "step": 1
    },
    {
      "epoch": 0.00011737261403483032,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00017605892105224547,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00017605892105224547,
      "eval_loss": NaN,
      "eval_runtime": 157.5187,
      "eval_samples_per_second": 45.55,
      "eval_steps_per_second": 22.778,
      "step": 3
    },
    {
      "epoch": 0.00023474522806966064,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0002934315350870758,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00035211784210449095,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00035211784210449095,
      "eval_loss": NaN,
      "eval_runtime": 161.3013,
      "eval_samples_per_second": 44.482,
      "eval_steps_per_second": 22.244,
      "step": 6
    },
    {
      "epoch": 0.00041080414912190614,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0004694904561393213,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0005281767631567365,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0005281767631567365,
      "eval_loss": NaN,
      "eval_runtime": 162.7462,
      "eval_samples_per_second": 44.087,
      "eval_steps_per_second": 22.047,
      "step": 9
    },
    {
      "epoch": 0.0005868630701741516,
      "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": 53105204920320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}