Hugging Face's logo

SystemAdmin123
/
NuExtract-v1.5

Safetensors
phi3
custom_code
Model card Files
xet
Community
NuExtract-v1.5
File size: 3,663 Bytes 
8024aeb
 
 
aee9b06
8024aeb
aee9b06
8024aeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77e1502
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
09adad1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ac311df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aee9b06
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8024aeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aee9b06
8024aeb
 
 
 
 
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": 1.91287362575531,
      "eval_runtime": 19.9916,
      "eval_samples_per_second": 75.082,
      "eval_steps_per_second": 4.702,
      "step": 1
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 1.6953125,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.7788,
      "step": 10
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.1875,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.6758,
      "step": 20
    },
    {
      "epoch": 0.37735849056603776,
      "eval_loss": 1.5468029975891113,
      "eval_runtime": 19.2466,
      "eval_samples_per_second": 77.988,
      "eval_steps_per_second": 4.884,
      "step": 20
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 1.3515625,
      "learning_rate": 0.0002,
      "loss": 1.7428,
      "step": 30
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.9609375,
      "learning_rate": 0.00019984815164333163,
      "loss": 1.7482,
      "step": 40
    },
    {
      "epoch": 0.7547169811320755,
      "eval_loss": 1.5930224657058716,
      "eval_runtime": 20.8935,
      "eval_samples_per_second": 71.84,
      "eval_steps_per_second": 4.499,
      "step": 40
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 1.0078125,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.7373,
      "step": 50
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 1.015625,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.3262,
      "step": 60
    },
    {
      "epoch": 1.1320754716981132,
      "eval_loss": 1.694644570350647,
      "eval_runtime": 19.8369,
      "eval_samples_per_second": 75.667,
      "eval_steps_per_second": 4.739,
      "step": 60
    },
    {
      "epoch": 1.320754716981132,
      "grad_norm": 0.8671875,
      "learning_rate": 0.00019757963826274357,
      "loss": 1.2568,
      "step": 70
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.90234375,
      "learning_rate": 0.00019622680003092503,
      "loss": 1.072,
      "step": 80
    },
    {
      "epoch": 1.509433962264151,
      "eval_loss": 1.7398728132247925,
      "eval_runtime": 28.2186,
      "eval_samples_per_second": 53.192,
      "eval_steps_per_second": 3.331,
      "step": 80
    },
    {
      "epoch": 1.6981132075471699,
      "grad_norm": 0.85546875,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.0807,
      "step": 90
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 0.80859375,
      "learning_rate": 0.00019264940672148018,
      "loss": 1.3163,
      "step": 100
    },
    {
      "epoch": 1.8867924528301887,
      "eval_loss": 1.7708204984664917,
      "eval_runtime": 19.9313,
      "eval_samples_per_second": 75.309,
      "eval_steps_per_second": 4.716,
      "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
}