Hugging Face's logo

ClarenceDan
/
af861a58-109b-40dc-bb2c-775d861877df

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
af861a58-109b-40dc-bb2c-775d861877df
File size: 2,986 Bytes 
6362b25
 
 
840583c
6362b25
840583c
6362b25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72a1e10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54a5076
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
840583c
 
 
 
 
 
 
6362b25
 
 
 
 
 
 
 
 
 
 
 
 
 
840583c
6362b25
 
 
 
840583c
6362b25
 
 
 
 
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": 0.00030799082187350817,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.079908218735082e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 20.7357,
      "step": 1
    },
    {
      "epoch": 3.079908218735082e-05,
      "eval_loss": NaN,
      "eval_runtime": 40.4032,
      "eval_samples_per_second": 338.365,
      "eval_steps_per_second": 169.195,
      "step": 1
    },
    {
      "epoch": 6.159816437470164e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 9.239724656205245e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 9.239724656205245e-05,
      "eval_loss": NaN,
      "eval_runtime": 38.6735,
      "eval_samples_per_second": 353.498,
      "eval_steps_per_second": 176.762,
      "step": 3
    },
    {
      "epoch": 0.00012319632874940327,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00015399541093675409,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0001847944931241049,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0001847944931241049,
      "eval_loss": NaN,
      "eval_runtime": 39.3408,
      "eval_samples_per_second": 347.501,
      "eval_steps_per_second": 173.763,
      "step": 6
    },
    {
      "epoch": 0.0002155935753114557,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00024639265749880655,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00027719173968615736,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00027719173968615736,
      "eval_loss": NaN,
      "eval_runtime": 39.0442,
      "eval_samples_per_second": 350.142,
      "eval_steps_per_second": 175.084,
      "step": 9
    },
    {
      "epoch": 0.00030799082187350817,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 391388430336.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}