Hugging Face's logo

SystemAdmin123
/
Phi-3.5-mini-instruct

Safetensors
phi3
custom_code
Model card Files
xet
Community
Phi-3.5-mini-instruct
File size: 3,659 Bytes 
ca9486c
 
 
93af456
d7c6958
93af456
ca9486c
 
 
 
 
d7c6958
 
 
 
 
ca9486c
 
 
8feead2
d7c6958
 
 
 
ca9486c
 
8feead2
37a2d37
d7c6958
 
 
015871b
 
d7c6958
 
 
 
 
 
6aa038f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78f8d63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
117f36d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93af456
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ca9486c
 
 
d7c6958
ca9486c
d7c6958
 
ca9486c
 
 
 
 
 
 
 
 
 
 
 
93af456
ca9486c
 
 
 
 
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": 1.8867924528301887,
  "eval_steps": 20,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018867924528301886,
      "eval_loss": 2.0760505199432373,
      "eval_runtime": 19.9612,
      "eval_samples_per_second": 75.196,
      "eval_steps_per_second": 4.709,
      "step": 1
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 2.0625,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.8165,
      "step": 10
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.2578125,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6773,
      "step": 20
    },
    {
      "epoch": 0.37735849056603776,
      "eval_loss": 1.5448647737503052,
      "eval_runtime": 19.4232,
      "eval_samples_per_second": 77.279,
      "eval_steps_per_second": 4.84,
      "step": 20
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0002,
      "loss": 1.7454,
      "step": 30
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.96875,
      "learning_rate": 0.00019984815164333163,
      "loss": 1.752,
      "step": 40
    },
    {
      "epoch": 0.7547169811320755,
      "eval_loss": 1.5965954065322876,
      "eval_runtime": 29.2724,
      "eval_samples_per_second": 51.277,
      "eval_steps_per_second": 3.211,
      "step": 40
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 0.96875,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.7421,
      "step": 50
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 1.0234375,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.3307,
      "step": 60
    },
    {
      "epoch": 1.1320754716981132,
      "eval_loss": 1.6943310499191284,
      "eval_runtime": 21.4164,
      "eval_samples_per_second": 70.087,
      "eval_steps_per_second": 4.389,
      "step": 60
    },
    {
      "epoch": 1.320754716981132,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00019757963826274357,
      "loss": 1.2583,
      "step": 70
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.90625,
      "learning_rate": 0.00019622680003092503,
      "loss": 1.0736,
      "step": 80
    },
    {
      "epoch": 1.509433962264151,
      "eval_loss": 1.7416529655456543,
      "eval_runtime": 32.0268,
      "eval_samples_per_second": 46.867,
      "eval_steps_per_second": 2.935,
      "step": 80
    },
    {
      "epoch": 1.6981132075471699,
      "grad_norm": 0.86328125,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.0759,
      "step": 90
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 0.828125,
      "learning_rate": 0.00019264940672148018,
      "loss": 1.2902,
      "step": 100
    },
    {
      "epoch": 1.8867924528301887,
      "eval_loss": 1.7835454940795898,
      "eval_runtime": 20.8305,
      "eval_samples_per_second": 72.058,
      "eval_steps_per_second": 4.513,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.313993814455091e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}