Hugging Face's logo

tarabukinivan
/
38ae0cc9-8095-40d8-b020-611230d2ecd8

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
38ae0cc9-8095-40d8-b020-611230d2ecd8
File size: 3,287 Bytes 
64a1bbd
 
 
d2778fb
64a1bbd
d2778fb
64a1bbd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a53703b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2778fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64a1bbd
 
 
 
 
 
 
 
 
 
 
 
 
 
d2778fb
64a1bbd
 
 
 
d2778fb
64a1bbd
 
 
 
 
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": 0.015037593984962405,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005012531328320802,
      "eval_loss": 1.1545190811157227,
      "eval_runtime": 74.7335,
      "eval_samples_per_second": 11.253,
      "eval_steps_per_second": 5.633,
      "step": 1
    },
    {
      "epoch": 0.0015037593984962407,
      "grad_norm": 14.427947998046875,
      "learning_rate": 6e-05,
      "loss": 4.5286,
      "step": 3
    },
    {
      "epoch": 0.0030075187969924814,
      "grad_norm": 8.940759658813477,
      "learning_rate": 0.00012,
      "loss": 4.4594,
      "step": 6
    },
    {
      "epoch": 0.0040100250626566416,
      "eval_loss": 0.9068899750709534,
      "eval_runtime": 74.1327,
      "eval_samples_per_second": 11.345,
      "eval_steps_per_second": 5.679,
      "step": 8
    },
    {
      "epoch": 0.004511278195488722,
      "grad_norm": 4.615734100341797,
      "learning_rate": 0.00018,
      "loss": 3.3499,
      "step": 9
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 4.977766036987305,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.2685,
      "step": 12
    },
    {
      "epoch": 0.007518796992481203,
      "grad_norm": 5.421140670776367,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.538,
      "step": 15
    },
    {
      "epoch": 0.008020050125313283,
      "eval_loss": 0.8385846018791199,
      "eval_runtime": 74.4233,
      "eval_samples_per_second": 11.3,
      "eval_steps_per_second": 5.657,
      "step": 16
    },
    {
      "epoch": 0.009022556390977444,
      "grad_norm": 6.071444034576416,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.5141,
      "step": 18
    },
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 7.219034194946289,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.5675,
      "step": 21
    },
    {
      "epoch": 0.012030075187969926,
      "grad_norm": 4.945723533630371,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.3491,
      "step": 24
    },
    {
      "epoch": 0.012030075187969926,
      "eval_loss": 0.8206897377967834,
      "eval_runtime": 74.5024,
      "eval_samples_per_second": 11.288,
      "eval_steps_per_second": 5.651,
      "step": 24
    },
    {
      "epoch": 0.013533834586466165,
      "grad_norm": 6.191557884216309,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.6754,
      "step": 27
    },
    {
      "epoch": 0.015037593984962405,
      "grad_norm": 4.54865837097168,
      "learning_rate": 0.0,
      "loss": 3.6574,
      "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": 1.0898513470685184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}