Hugging Face's logo

nadejdatarabukina
/
77384b98-65cc-4dc0-802e-0193a66b523f

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
77384b98-65cc-4dc0-802e-0193a66b523f
File size: 2,662 Bytes 
cd414a0
 
 
90319a3
cd414a0
90319a3
cd414a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90319a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd414a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90319a3
cd414a0
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011852905443446825,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.9264527217234124e-05,
      "eval_loss": NaN,
      "eval_runtime": 819.6237,
      "eval_samples_per_second": 8.669,
      "eval_steps_per_second": 4.335,
      "step": 1
    },
    {
      "epoch": 0.00017779358165170237,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002963226360861706,
      "eval_loss": NaN,
      "eval_runtime": 820.1006,
      "eval_samples_per_second": 8.664,
      "eval_steps_per_second": 4.332,
      "step": 5
    },
    {
      "epoch": 0.00035558716330340474,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005333807449551071,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0005926452721723412,
      "eval_loss": NaN,
      "eval_runtime": 819.4717,
      "eval_samples_per_second": 8.67,
      "eval_steps_per_second": 4.336,
      "step": 10
    },
    {
      "epoch": 0.0007111743266068095,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0008889679082585119,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0008889679082585119,
      "eval_loss": NaN,
      "eval_runtime": 821.6602,
      "eval_samples_per_second": 8.647,
      "eval_steps_per_second": 4.324,
      "step": 15
    },
    {
      "epoch": 0.0010667614899102142,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0011852905443446825,
      "eval_loss": NaN,
      "eval_runtime": 821.7182,
      "eval_samples_per_second": 8.647,
      "eval_steps_per_second": 4.324,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7031294986813440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}