Hugging Face's logo

locuslab
/
tofu_ft_phi-1.5

Text Generation
Transformers
Safetensors
phi
custom_code
text-generation-inference
Model card Files
xet
Community
tofu_ft_phi-1.5
File size: 2,767 Bytes 
c34da36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 4.960000000000001e-06,
      "loss": 1.9883,
      "step": 31
    },
    {
      "epoch": 0.5,
      "learning_rate": 9.920000000000002e-06,
      "loss": 1.6761,
      "step": 62
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.4880000000000002e-05,
      "loss": 1.602,
      "step": 93
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9840000000000003e-05,
      "loss": 1.5403,
      "step": 124
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.88e-05,
      "loss": 1.2675,
      "step": 155
    },
    {
      "epoch": 1.49,
      "learning_rate": 1.756e-05,
      "loss": 1.2617,
      "step": 186
    },
    {
      "epoch": 1.74,
      "learning_rate": 1.632e-05,
      "loss": 1.2548,
      "step": 217
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.5080000000000001e-05,
      "loss": 1.2142,
      "step": 248
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.384e-05,
      "loss": 0.7858,
      "step": 279
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 0.7192,
      "step": 310
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.136e-05,
      "loss": 0.7358,
      "step": 341
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.0120000000000001e-05,
      "loss": 0.7185,
      "step": 372
    },
    {
      "epoch": 3.22,
      "learning_rate": 8.880000000000001e-06,
      "loss": 0.3819,
      "step": 403
    },
    {
      "epoch": 3.47,
      "learning_rate": 7.640000000000001e-06,
      "loss": 0.3223,
      "step": 434
    },
    {
      "epoch": 3.72,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.3149,
      "step": 465
    },
    {
      "epoch": 3.97,
      "learning_rate": 5.1600000000000006e-06,
      "loss": 0.3246,
      "step": 496
    },
    {
      "epoch": 4.22,
      "learning_rate": 3.920000000000001e-06,
      "loss": 0.1583,
      "step": 527
    },
    {
      "epoch": 4.46,
      "learning_rate": 2.68e-06,
      "loss": 0.1207,
      "step": 558
    },
    {
      "epoch": 4.71,
      "learning_rate": 1.44e-06,
      "loss": 0.118,
      "step": 589
    },
    {
      "epoch": 4.96,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.1169,
      "step": 620
    }
  ],
  "logging_steps": 31,
  "max_steps": 625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 625,
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}