Hugging Face's logo

yitzshapiro
/
yitzandyeshaya-phi-2

Text Generation
Safetensors
Trained with AutoTrain
conversational
Inference Endpoints
Model card Files Community
yitzandyeshaya-phi-2
File size: 3,134 Bytes 
876b420
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.285714285714286,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.57,
      "grad_norm": 0.2423473596572876,
      "learning_rate": 0.0001,
      "loss": 4.0857,
      "step": 1
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.2876349985599518,
      "learning_rate": 0.0002,
      "loss": 4.396,
      "step": 2
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.25892937183380127,
      "learning_rate": 0.0001875,
      "loss": 4.257,
      "step": 3
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.24695058166980743,
      "learning_rate": 0.000175,
      "loss": 4.2171,
      "step": 4
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.439170777797699,
      "learning_rate": 0.00016250000000000002,
      "loss": 4.0037,
      "step": 5
    },
    {
      "epoch": 3.43,
      "grad_norm": 0.3510642647743225,
      "learning_rate": 0.00015000000000000001,
      "loss": 4.1377,
      "step": 6
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3439651131629944,
      "learning_rate": 0.0001375,
      "loss": 4.0279,
      "step": 7
    },
    {
      "epoch": 4.57,
      "grad_norm": 0.3093964159488678,
      "learning_rate": 0.000125,
      "loss": 3.8389,
      "step": 8
    },
    {
      "epoch": 5.14,
      "grad_norm": 0.3536764979362488,
      "learning_rate": 0.00011250000000000001,
      "loss": 4.1566,
      "step": 9
    },
    {
      "epoch": 5.71,
      "grad_norm": 0.3965250849723816,
      "learning_rate": 0.0001,
      "loss": 3.969,
      "step": 10
    },
    {
      "epoch": 6.29,
      "grad_norm": 0.4037889838218689,
      "learning_rate": 8.75e-05,
      "loss": 3.9695,
      "step": 11
    },
    {
      "epoch": 6.86,
      "grad_norm": 0.3280973434448242,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.7841,
      "step": 12
    },
    {
      "epoch": 7.43,
      "grad_norm": 0.3607095777988434,
      "learning_rate": 6.25e-05,
      "loss": 3.8726,
      "step": 13
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.3536747992038727,
      "learning_rate": 5e-05,
      "loss": 3.8848,
      "step": 14
    },
    {
      "epoch": 8.57,
      "grad_norm": 0.42837923765182495,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 3.8312,
      "step": 15
    },
    {
      "epoch": 9.14,
      "grad_norm": 0.3861906826496124,
      "learning_rate": 2.5e-05,
      "loss": 3.9284,
      "step": 16
    },
    {
      "epoch": 9.71,
      "grad_norm": 0.3450121581554413,
      "learning_rate": 1.25e-05,
      "loss": 3.8218,
      "step": 17
    },
    {
      "epoch": 10.29,
      "grad_norm": 0.3705593943595886,
      "learning_rate": 0.0,
      "loss": 3.726,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 18,
  "save_steps": 500,
  "total_flos": 5730050919936000.0,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}