Hugging Face's logo

chauhoang
/
f4ceaa19-6420-4b44-a08d-f9e4b1bc8dc3

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
f4ceaa19-6420-4b44-a08d-f9e4b1bc8dc3
File size: 3,746 Bytes
9946b81
 
 
a4a1193
9bf114e
a4a1193
9946b81
 
 
 
 
 
 
9bf114e
 
 
9946b81
9bf114e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21778c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
358a80b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a4a1193
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9946b81
 
 
9bf114e
9946b81
 
9bf114e
9946b81
 
 
 
 
 
 
a4a1193
9946b81
 
 
 
a4a1193
9946b81
 
 
 
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": 0.0008680781617576847,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7361563235153692e-05,
      "eval_loss": 3.2406625747680664,
      "eval_runtime": 1557.6717,
      "eval_samples_per_second": 15.569,
      "eval_steps_per_second": 7.785,
      "step": 1
    },
    {
      "epoch": 8.680781617576846e-05,
      "grad_norm": 57.20978927612305,
      "learning_rate": 5e-05,
      "loss": 12.0897,
      "step": 5
    },
    {
      "epoch": 0.00017361563235153692,
      "grad_norm": 54.81013107299805,
      "learning_rate": 0.0001,
      "loss": 8.6169,
      "step": 10
    },
    {
      "epoch": 0.00017361563235153692,
      "eval_loss": 1.9173833131790161,
      "eval_runtime": 1562.5591,
      "eval_samples_per_second": 15.521,
      "eval_steps_per_second": 7.76,
      "step": 10
    },
    {
      "epoch": 0.0002604234485273054,
      "grad_norm": 30.663660049438477,
      "learning_rate": 9.619397662556435e-05,
      "loss": 7.1643,
      "step": 15
    },
    {
      "epoch": 0.00034723126470307384,
      "grad_norm": 31.651548385620117,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.5708,
      "step": 20
    },
    {
      "epoch": 0.00034723126470307384,
      "eval_loss": 1.364366888999939,
      "eval_runtime": 1565.5286,
      "eval_samples_per_second": 15.491,
      "eval_steps_per_second": 7.746,
      "step": 20
    },
    {
      "epoch": 0.00043403908087884236,
      "grad_norm": 27.65591812133789,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.2812,
      "step": 25
    },
    {
      "epoch": 0.0005208468970546108,
      "grad_norm": 23.687255859375,
      "learning_rate": 5e-05,
      "loss": 5.1417,
      "step": 30
    },
    {
      "epoch": 0.0005208468970546108,
      "eval_loss": 1.267388105392456,
      "eval_runtime": 2133.9119,
      "eval_samples_per_second": 11.365,
      "eval_steps_per_second": 5.683,
      "step": 30
    },
    {
      "epoch": 0.0006076547132303793,
      "grad_norm": 21.283479690551758,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.6944,
      "step": 35
    },
    {
      "epoch": 0.0006944625294061477,
      "grad_norm": 19.084383010864258,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 5.3045,
      "step": 40
    },
    {
      "epoch": 0.0006944625294061477,
      "eval_loss": 1.2451889514923096,
      "eval_runtime": 2665.7266,
      "eval_samples_per_second": 9.098,
      "eval_steps_per_second": 4.549,
      "step": 40
    },
    {
      "epoch": 0.0007812703455819162,
      "grad_norm": 21.01182746887207,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.2542,
      "step": 45
    },
    {
      "epoch": 0.0008680781617576847,
      "grad_norm": 18.80780029296875,
      "learning_rate": 0.0,
      "loss": 4.3926,
      "step": 50
    },
    {
      "epoch": 0.0008680781617576847,
      "eval_loss": 1.2397698163986206,
      "eval_runtime": 3028.9488,
      "eval_samples_per_second": 8.007,
      "eval_steps_per_second": 4.003,
      "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": 8763509991014400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}