Hugging Face's logo

VERSIL91
/
5ec4e6c1-d9dc-49de-a9c1-ed512c93b2a7

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
5ec4e6c1-d9dc-49de-a9c1-ed512c93b2a7
File size: 3,461 Bytes 
4908c1f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00845522955948254,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001691045911896508,
      "eval_loss": NaN,
      "eval_runtime": 106.7099,
      "eval_samples_per_second": 23.334,
      "eval_steps_per_second": 11.667,
      "step": 1
    },
    {
      "epoch": 0.000845522955948254,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.001691045911896508,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.001691045911896508,
      "eval_loss": NaN,
      "eval_runtime": 105.6763,
      "eval_samples_per_second": 23.563,
      "eval_steps_per_second": 11.781,
      "step": 10
    },
    {
      "epoch": 0.002536568867844762,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.003382091823793016,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.003382091823793016,
      "eval_loss": NaN,
      "eval_runtime": 105.967,
      "eval_samples_per_second": 23.498,
      "eval_steps_per_second": 11.749,
      "step": 20
    },
    {
      "epoch": 0.00422761477974127,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.005073137735689524,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.005073137735689524,
      "eval_loss": NaN,
      "eval_runtime": 105.9651,
      "eval_samples_per_second": 23.498,
      "eval_steps_per_second": 11.749,
      "step": 30
    },
    {
      "epoch": 0.005918660691637778,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.006764183647586032,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.006764183647586032,
      "eval_loss": NaN,
      "eval_runtime": 106.0532,
      "eval_samples_per_second": 23.479,
      "eval_steps_per_second": 11.739,
      "step": 40
    },
    {
      "epoch": 0.007609706603534286,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.00845522955948254,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.00845522955948254,
      "eval_loss": NaN,
      "eval_runtime": 104.8702,
      "eval_samples_per_second": 23.744,
      "eval_steps_per_second": 11.872,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4868225951072256.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}