Hugging Face's logo

trenden
/
782e3d85-5a50-48a7-aec3-5663e6786735

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
782e3d85-5a50-48a7-aec3-5663e6786735
File size: 2,811 Bytes 
52cb8d2
 
 
e74b671
52cb8d2
e74b671
52cb8d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aba5b03
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e74b671
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52cb8d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e74b671
52cb8d2
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021608643457382955,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024009603841536613,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0024009603841536613,
      "eval_loss": NaN,
      "eval_runtime": 7.6037,
      "eval_samples_per_second": 23.146,
      "eval_steps_per_second": 11.573,
      "step": 1
    },
    {
      "epoch": 0.004801920768307323,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.007202881152460984,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.007202881152460984,
      "eval_loss": NaN,
      "eval_runtime": 6.3712,
      "eval_samples_per_second": 27.624,
      "eval_steps_per_second": 13.812,
      "step": 3
    },
    {
      "epoch": 0.009603841536614645,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.012004801920768308,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.014405762304921969,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.014405762304921969,
      "eval_loss": NaN,
      "eval_runtime": 6.4347,
      "eval_samples_per_second": 27.352,
      "eval_steps_per_second": 13.676,
      "step": 6
    },
    {
      "epoch": 0.01680672268907563,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.01920768307322929,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.021608643457382955,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.021608643457382955,
      "eval_loss": NaN,
      "eval_runtime": 6.4566,
      "eval_samples_per_second": 27.259,
      "eval_steps_per_second": 13.629,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1927938979135488.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}