Hugging Face's logo

tuantmdev
/
029943c9-349f-4a1f-98f3-69a643747ad9

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files
xet
Community
029943c9-349f-4a1f-98f3-69a643747ad9
File size: 2,745 Bytes 
3ab2c42
 
 
2c142f7
3ab2c42
2c142f7
3ab2c42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a88972d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24bd373
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2c142f7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ab2c42
 
 
 
 
 
 
 
 
 
 
 
 
 
2c142f7
3ab2c42
 
 
 
 
 
 
 
2c142f7
3ab2c42
 
 
 
2c142f7
3ab2c42
 
 
 
 
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
 
{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.07561079344076367,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00037805396720381833,
      "eval_loss": NaN,
      "eval_runtime": 248.662,
      "eval_samples_per_second": 8.96,
      "eval_steps_per_second": 4.48,
      "step": 1
    },
    {
      "epoch": 0.015122158688152735,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.018902698360190918,
      "eval_loss": NaN,
      "eval_runtime": 247.6685,
      "eval_samples_per_second": 8.996,
      "eval_steps_per_second": 4.498,
      "step": 50
    },
    {
      "epoch": 0.03024431737630547,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.037805396720381836,
      "eval_loss": NaN,
      "eval_runtime": 248.6322,
      "eval_samples_per_second": 8.961,
      "eval_steps_per_second": 4.481,
      "step": 100
    },
    {
      "epoch": 0.0453664760644582,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.05670809508057275,
      "eval_loss": NaN,
      "eval_runtime": 248.69,
      "eval_samples_per_second": 8.959,
      "eval_steps_per_second": 4.479,
      "step": 150
    },
    {
      "epoch": 0.06048863475261094,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.07561079344076367,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.07561079344076367,
      "eval_loss": NaN,
      "eval_runtime": 248.3165,
      "eval_samples_per_second": 8.972,
      "eval_steps_per_second": 4.486,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3118833670121062e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}