Hugging Face's logo

tuantmdev
/
15f7175d-c3f1-4ba5-8956-5db5b672045b

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
15f7175d-c3f1-4ba5-8956-5db5b672045b
File size: 2,707 Bytes 
4c5ac30
 
 
cfd76b9
4c5ac30
cfd76b9
4c5ac30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0714af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6b67deb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10036df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cfd76b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4c5ac30
 
 
 
 
 
 
 
 
 
 
 
 
 
cfd76b9
4c5ac30
 
 
 
cfd76b9
4c5ac30
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013250517598343685,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.625258799171843e-05,
      "eval_loss": NaN,
      "eval_runtime": 3989.9649,
      "eval_samples_per_second": 6.371,
      "eval_steps_per_second": 3.186,
      "step": 1
    },
    {
      "epoch": 0.002650103519668737,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.002650103519668737,
      "eval_loss": NaN,
      "eval_runtime": 3986.9682,
      "eval_samples_per_second": 6.376,
      "eval_steps_per_second": 3.188,
      "step": 40
    },
    {
      "epoch": 0.005300207039337474,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.005300207039337474,
      "eval_loss": NaN,
      "eval_runtime": 3989.1243,
      "eval_samples_per_second": 6.373,
      "eval_steps_per_second": 3.186,
      "step": 80
    },
    {
      "epoch": 0.007950310559006211,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.007950310559006211,
      "eval_loss": NaN,
      "eval_runtime": 3989.9051,
      "eval_samples_per_second": 6.371,
      "eval_steps_per_second": 3.186,
      "step": 120
    },
    {
      "epoch": 0.010600414078674947,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.010600414078674947,
      "eval_loss": NaN,
      "eval_runtime": 3987.3185,
      "eval_samples_per_second": 6.375,
      "eval_steps_per_second": 3.188,
      "step": 160
    },
    {
      "epoch": 0.013250517598343685,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.013250517598343685,
      "eval_loss": NaN,
      "eval_runtime": 3987.784,
      "eval_samples_per_second": 6.375,
      "eval_steps_per_second": 3.187,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.957752586798367e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}