Hugging Face's logo

cwaud
/
d1bb4b46-4693-45b0-8918-c7aad01b32c2

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
d1bb4b46-4693-45b0-8918-c7aad01b32c2
File size: 2,940 Bytes 
34d5685
 
 
17be55a
34d5685
17be55a
34d5685
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6399047
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19a5798
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17be55a
 
 
 
 
 
 
34d5685
 
 
 
 
 
 
 
 
 
 
 
 
 
17be55a
34d5685
 
 
 
17be55a
34d5685
 
 
 
 
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": 0.05194805194805195,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005194805194805195,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.005194805194805195,
      "eval_loss": NaN,
      "eval_runtime": 7.0631,
      "eval_samples_per_second": 11.468,
      "eval_steps_per_second": 5.805,
      "step": 1
    },
    {
      "epoch": 0.01038961038961039,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.015584415584415584,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.015584415584415584,
      "eval_loss": NaN,
      "eval_runtime": 6.2275,
      "eval_samples_per_second": 13.007,
      "eval_steps_per_second": 6.584,
      "step": 3
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.03116883116883117,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.03116883116883117,
      "eval_loss": NaN,
      "eval_runtime": 6.3572,
      "eval_samples_per_second": 12.741,
      "eval_steps_per_second": 6.449,
      "step": 6
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.046753246753246755,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.046753246753246755,
      "eval_loss": NaN,
      "eval_runtime": 6.4282,
      "eval_samples_per_second": 12.601,
      "eval_steps_per_second": 6.378,
      "step": 9
    },
    {
      "epoch": 0.05194805194805195,
      "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": 1752671799214080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}