Hugging Face's logo

lesso13
/
2ae8dfa8-ce6d-4fc8-a75e-e514aec2579b

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
2ae8dfa8-ce6d-4fc8-a75e-e514aec2579b
File size: 3,078 Bytes 
ff71a20
 
 
e575d40
ff71a20
e575d40
ff71a20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
854498f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e575d40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff71a20
 
 
 
 
 
 
 
 
 
 
 
 
 
e575d40
ff71a20
 
 
 
e575d40
ff71a20
 
 
 
 
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": 0.0006382741068151718,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1275803560505725e-05,
      "eval_loss": NaN,
      "eval_runtime": 4296.6887,
      "eval_samples_per_second": 4.606,
      "eval_steps_per_second": 2.303,
      "step": 1
    },
    {
      "epoch": 6.382741068151718e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00012765482136303436,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0001702064284840458,
      "eval_loss": NaN,
      "eval_runtime": 4293.2903,
      "eval_samples_per_second": 4.61,
      "eval_steps_per_second": 2.305,
      "step": 8
    },
    {
      "epoch": 0.00019148223204455152,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0002553096427260687,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0003191370534075859,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0003404128569680916,
      "eval_loss": NaN,
      "eval_runtime": 4299.0376,
      "eval_samples_per_second": 4.604,
      "eval_steps_per_second": 2.302,
      "step": 16
    },
    {
      "epoch": 0.00038296446408910305,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.00044679187477062024,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0005106192854521374,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0005106192854521374,
      "eval_loss": NaN,
      "eval_runtime": 4298.9166,
      "eval_samples_per_second": 4.604,
      "eval_steps_per_second": 2.302,
      "step": 24
    },
    {
      "epoch": 0.0005744466961336546,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0006382741068151718,
      "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": 1.054695455981568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}