Hugging Face's logo

aaronmena02
/
priority-model-mailclassifier

Safetensors
roberta
Model card Files
xet
 Community
priority-model-mailclassifier
File size: 3,939 Bytes
6d4bddd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.9329080276448697,
  "best_model_checkpoint": "./priority_model\\checkpoint-92",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 115,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 5.8311944007873535,
      "learning_rate": 1.8550724637681162e-05,
      "loss": 1.0181,
      "step": 10
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 7.023670196533203,
      "learning_rate": 1.710144927536232e-05,
      "loss": 0.8761,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8888888888888888,
      "eval_f1": 0.8887926887926887,
      "eval_loss": 0.6216873526573181,
      "eval_runtime": 1.0711,
      "eval_samples_per_second": 42.014,
      "eval_steps_per_second": 5.602,
      "step": 23
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 5.623006820678711,
      "learning_rate": 1.565217391304348e-05,
      "loss": 0.7532,
      "step": 30
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 9.884881973266602,
      "learning_rate": 1.420289855072464e-05,
      "loss": 0.5316,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9111111111111111,
      "eval_f1": 0.9095029239766083,
      "eval_loss": 0.3368909955024719,
      "eval_runtime": 1.0808,
      "eval_samples_per_second": 41.635,
      "eval_steps_per_second": 5.551,
      "step": 46
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 4.106278896331787,
      "learning_rate": 1.2753623188405797e-05,
      "loss": 0.3776,
      "step": 50
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 3.0185980796813965,
      "learning_rate": 1.1304347826086957e-05,
      "loss": 0.2772,
      "step": 60
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_f1": 0.9318062180540958,
      "eval_loss": 0.22048650681972504,
      "eval_runtime": 1.0754,
      "eval_samples_per_second": 41.846,
      "eval_steps_per_second": 5.579,
      "step": 69
    },
    {
      "epoch": 3.0434782608695654,
      "grad_norm": 5.088245391845703,
      "learning_rate": 9.855072463768118e-06,
      "loss": 0.2582,
      "step": 70
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 7.887622356414795,
      "learning_rate": 8.405797101449275e-06,
      "loss": 0.1718,
      "step": 80
    },
    {
      "epoch": 3.9130434782608696,
      "grad_norm": 2.031566619873047,
      "learning_rate": 6.956521739130435e-06,
      "loss": 0.1757,
      "step": 90
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_f1": 0.9329080276448697,
      "eval_loss": 0.17431004345417023,
      "eval_runtime": 1.0809,
      "eval_samples_per_second": 41.631,
      "eval_steps_per_second": 5.551,
      "step": 92
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 1.8258976936340332,
      "learning_rate": 5.507246376811595e-06,
      "loss": 0.1246,
      "step": 100
    },
    {
      "epoch": 4.782608695652174,
      "grad_norm": 1.9977986812591553,
      "learning_rate": 4.057971014492754e-06,
      "loss": 0.0982,
      "step": 110
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9333333333333333,
      "eval_f1": 0.9329080276448697,
      "eval_loss": 0.16062292456626892,
      "eval_runtime": 1.0756,
      "eval_samples_per_second": 41.837,
      "eval_steps_per_second": 5.578,
      "step": 115
    }
  ],
  "logging_steps": 10,
  "max_steps": 138,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 40931608832100.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}