Hugging Face's logo

sergioalves
/
f9cb36f0-7170-436f-93d6-0dd0cfa20f35

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
f9cb36f0-7170-436f-93d6-0dd0cfa20f35
File size: 3,072 Bytes 
eacb6fb
 
 
111865b
eacb6fb
111865b
eacb6fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e2f349
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111865b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eacb6fb
 
 
 
 
 
 
 
 
 
 
 
 
 
111865b
eacb6fb
 
 
 
111865b
eacb6fb
 
 
 
 
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": 0.0008367500627562547,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7891668758541825e-05,
      "eval_loss": NaN,
      "eval_runtime": 2335.0065,
      "eval_samples_per_second": 6.466,
      "eval_steps_per_second": 3.233,
      "step": 1
    },
    {
      "epoch": 8.367500627562547e-05,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00016735001255125095,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0002231333500683346,
      "eval_loss": NaN,
      "eval_runtime": 2334.6079,
      "eval_samples_per_second": 6.467,
      "eval_steps_per_second": 3.234,
      "step": 8
    },
    {
      "epoch": 0.0002510250188268764,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0003347000251025019,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00041837503137812733,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0004462667001366692,
      "eval_loss": NaN,
      "eval_runtime": 2334.0846,
      "eval_samples_per_second": 6.468,
      "eval_steps_per_second": 3.234,
      "step": 16
    },
    {
      "epoch": 0.0005020500376537528,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0005857250439293783,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0006694000502050038,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0006694000502050038,
      "eval_loss": NaN,
      "eval_runtime": 2336.7538,
      "eval_samples_per_second": 6.461,
      "eval_steps_per_second": 3.231,
      "step": 24
    },
    {
      "epoch": 0.0007530750564806293,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0008367500627562547,
      "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": 1.4238372348297216e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}