Hugging Face's logo

Hartunka
/
tiny_bert_rand_50_v1_mrpc

TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
tiny_bert_rand_50_v1_mrpc
File size: 4,556 Bytes
a52b141
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
{
  "best_metric": 0.5949084758758545,
  "best_model_checkpoint": "tiny_bert_rand_50_v1_mrpc/checkpoint-45",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8691033124923706,
      "learning_rate": 4.9e-05,
      "loss": 0.6286,
      "step": 15
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6862745098039216,
      "eval_combined_score": 0.7440660474716203,
      "eval_f1": 0.8018575851393189,
      "eval_loss": 0.604465901851654,
      "eval_runtime": 0.1601,
      "eval_samples_per_second": 2547.96,
      "eval_steps_per_second": 12.49,
      "step": 15
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3388460874557495,
      "learning_rate": 4.8e-05,
      "loss": 0.5948,
      "step": 30
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6985294117647058,
      "eval_combined_score": 0.7536192937517152,
      "eval_f1": 0.8087091757387247,
      "eval_loss": 0.5950304865837097,
      "eval_runtime": 0.1669,
      "eval_samples_per_second": 2444.764,
      "eval_steps_per_second": 11.984,
      "step": 30
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4051553010940552,
      "learning_rate": 4.7e-05,
      "loss": 0.556,
      "step": 45
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6813725490196079,
      "eval_combined_score": 0.7375116713352008,
      "eval_f1": 0.7936507936507936,
      "eval_loss": 0.5949084758758545,
      "eval_runtime": 0.1984,
      "eval_samples_per_second": 2056.454,
      "eval_steps_per_second": 10.081,
      "step": 45
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.9397245645523071,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5107,
      "step": 60
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7107843137254902,
      "eval_combined_score": 0.753316032295271,
      "eval_f1": 0.7958477508650519,
      "eval_loss": 0.6382691860198975,
      "eval_runtime": 0.1676,
      "eval_samples_per_second": 2433.718,
      "eval_steps_per_second": 11.93,
      "step": 60
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.463055372238159,
      "learning_rate": 4.5e-05,
      "loss": 0.4193,
      "step": 75
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6495098039215687,
      "eval_combined_score": 0.6930790271909869,
      "eval_f1": 0.7366482504604052,
      "eval_loss": 0.6820002794265747,
      "eval_runtime": 0.1579,
      "eval_samples_per_second": 2584.681,
      "eval_steps_per_second": 12.67,
      "step": 75
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.737268924713135,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3479,
      "step": 90
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7034313725490197,
      "eval_combined_score": 0.7517156862745098,
      "eval_f1": 0.8,
      "eval_loss": 0.8077418208122253,
      "eval_runtime": 0.1937,
      "eval_samples_per_second": 2105.958,
      "eval_steps_per_second": 10.323,
      "step": 90
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.261862277984619,
      "learning_rate": 4.3e-05,
      "loss": 0.2647,
      "step": 105
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7316553544494722,
      "eval_f1": 0.7794871794871795,
      "eval_loss": 0.8842233419418335,
      "eval_runtime": 0.1783,
      "eval_samples_per_second": 2288.185,
      "eval_steps_per_second": 11.217,
      "step": 105
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.626375198364258,
      "learning_rate": 4.2e-05,
      "loss": 0.1929,
      "step": 120
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6813725490196079,
      "eval_combined_score": 0.7323529411764707,
      "eval_f1": 0.7833333333333333,
      "eval_loss": 1.042723536491394,
      "eval_runtime": 0.1576,
      "eval_samples_per_second": 2589.547,
      "eval_steps_per_second": 12.694,
      "step": 120
    },
    {
      "epoch": 8.0,
      "step": 120,
      "total_flos": 769504676118528.0,
      "train_loss": 0.43935337861378987,
      "train_runtime": 27.1726,
      "train_samples_per_second": 6749.449,
      "train_steps_per_second": 27.601
    }
  ],
  "logging_steps": 1,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 769504676118528.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}