Hugging Face's logo

dimasik87
/
269cd4e5-e79f-4036-899b-cd4d209ec711

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
269cd4e5-e79f-4036-899b-cd4d209ec711
File size: 3,054 Bytes 
8393a88
 
 
a4239e1
8393a88
a4239e1
8393a88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
052debe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a4239e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8393a88
 
 
 
 
 
 
 
 
 
 
 
 
 
a4239e1
8393a88
 
 
 
a4239e1
8393a88
 
 
 
 
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": 0.01083815028901734,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000361271676300578,
      "eval_loss": NaN,
      "eval_runtime": 68.9512,
      "eval_samples_per_second": 16.911,
      "eval_steps_per_second": 8.455,
      "step": 1
    },
    {
      "epoch": 0.001083815028901734,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.002167630057803468,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002890173410404624,
      "eval_loss": NaN,
      "eval_runtime": 67.4943,
      "eval_samples_per_second": 17.276,
      "eval_steps_per_second": 8.638,
      "step": 8
    },
    {
      "epoch": 0.0032514450867052024,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.004335260115606936,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00541907514450867,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.005780346820809248,
      "eval_loss": NaN,
      "eval_runtime": 67.7288,
      "eval_samples_per_second": 17.216,
      "eval_steps_per_second": 8.608,
      "step": 16
    },
    {
      "epoch": 0.006502890173410405,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.007586705202312138,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.008670520231213872,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.008670520231213872,
      "eval_loss": NaN,
      "eval_runtime": 67.6902,
      "eval_samples_per_second": 17.226,
      "eval_steps_per_second": 8.613,
      "step": 24
    },
    {
      "epoch": 0.009754335260115607,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.01083815028901734,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0810628423811072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}