Hugging Face's logo

dimasik1987
/
9de0dce6-b524-4295-808d-779fc72463bc

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files Community
9de0dce6-b524-4295-808d-779fc72463bc
File size: 3,272 Bytes 
3d37d70
 
 
8c05794
3d37d70
8c05794
3d37d70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c004674
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8c05794
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d37d70
 
 
 
 
 
 
 
 
 
 
 
 
 
8c05794
3d37d70
 
 
 
8c05794
3d37d70
 
 
 
 
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": 0.718562874251497,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023952095808383235,
      "eval_loss": 0.5039941072463989,
      "eval_runtime": 1.8987,
      "eval_samples_per_second": 9.48,
      "eval_steps_per_second": 4.74,
      "step": 1
    },
    {
      "epoch": 0.0718562874251497,
      "grad_norm": 6.43875789642334,
      "learning_rate": 6e-05,
      "loss": 1.9809,
      "step": 3
    },
    {
      "epoch": 0.1437125748502994,
      "grad_norm": 5.396348476409912,
      "learning_rate": 0.00012,
      "loss": 1.7005,
      "step": 6
    },
    {
      "epoch": 0.19161676646706588,
      "eval_loss": 0.024824917316436768,
      "eval_runtime": 1.9003,
      "eval_samples_per_second": 9.472,
      "eval_steps_per_second": 4.736,
      "step": 8
    },
    {
      "epoch": 0.2155688622754491,
      "grad_norm": 3.0755698680877686,
      "learning_rate": 0.00018,
      "loss": 0.2899,
      "step": 9
    },
    {
      "epoch": 0.2874251497005988,
      "grad_norm": 0.12527230381965637,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.015,
      "step": 12
    },
    {
      "epoch": 0.3592814371257485,
      "grad_norm": 0.023354211822152138,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0011,
      "step": 15
    },
    {
      "epoch": 0.38323353293413176,
      "eval_loss": 7.335327245527878e-05,
      "eval_runtime": 1.9021,
      "eval_samples_per_second": 9.463,
      "eval_steps_per_second": 4.732,
      "step": 16
    },
    {
      "epoch": 0.4311377245508982,
      "grad_norm": 0.013110329397022724,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0003,
      "step": 18
    },
    {
      "epoch": 0.5029940119760479,
      "grad_norm": 0.006351693067699671,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0002,
      "step": 21
    },
    {
      "epoch": 0.5748502994011976,
      "grad_norm": 0.009272687137126923,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0001,
      "step": 24
    },
    {
      "epoch": 0.5748502994011976,
      "eval_loss": 3.0196802981663495e-05,
      "eval_runtime": 1.9296,
      "eval_samples_per_second": 9.329,
      "eval_steps_per_second": 4.664,
      "step": 24
    },
    {
      "epoch": 0.6467065868263473,
      "grad_norm": 0.023558655753731728,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0002,
      "step": 27
    },
    {
      "epoch": 0.718562874251497,
      "grad_norm": 0.005601735319942236,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "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": 5526274525102080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}