Hugging Face's logo

Best000
/
f8d6bd7e-85bb-46d3-a64a-70c7d19c753a

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
f8d6bd7e-85bb-46d3-a64a-70c7d19c753a
File size: 2,964 Bytes 
c73db48
 
 
c589027
c73db48
c589027
c73db48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fcefe63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45feb7c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c589027
 
 
 
 
 
 
c73db48
 
 
 
 
 
 
 
 
 
 
 
 
 
c589027
c73db48
 
 
 
c589027
c73db48
 
 
 
 
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": 0.004565167769915545,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045651677699155445,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00045651677699155445,
      "eval_loss": NaN,
      "eval_runtime": 28.9978,
      "eval_samples_per_second": 31.83,
      "eval_steps_per_second": 15.932,
      "step": 1
    },
    {
      "epoch": 0.0009130335539831089,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0013695503309746632,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0013695503309746632,
      "eval_loss": NaN,
      "eval_runtime": 27.8352,
      "eval_samples_per_second": 33.159,
      "eval_steps_per_second": 16.598,
      "step": 3
    },
    {
      "epoch": 0.0018260671079662178,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0022825838849577723,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0027391006619493265,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0027391006619493265,
      "eval_loss": NaN,
      "eval_runtime": 27.8718,
      "eval_samples_per_second": 33.116,
      "eval_steps_per_second": 16.576,
      "step": 6
    },
    {
      "epoch": 0.003195617438940881,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0036521342159324356,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00410865099292399,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00410865099292399,
      "eval_loss": NaN,
      "eval_runtime": 27.812,
      "eval_samples_per_second": 33.187,
      "eval_steps_per_second": 16.612,
      "step": 9
    },
    {
      "epoch": 0.004565167769915545,
      "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": 1752669785948160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}