Hugging Face's logo

Hartunka
/
tiny_bert_km_100_v1_mnli

TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
tiny_bert_km_100_v1_mnli
File size: 4,719 Bytes
90ee3f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
 
{
  "best_metric": 0.8314237594604492,
  "best_model_checkpoint": "tiny_bert_km_100_v1_mnli/checkpoint-7670",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 15340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.0091803073883057,
      "learning_rate": 4.9e-05,
      "loss": 1.0013,
      "step": 1534
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5437595517065715,
      "eval_loss": 0.9410763382911682,
      "eval_runtime": 3.652,
      "eval_samples_per_second": 2687.553,
      "eval_steps_per_second": 10.679,
      "step": 1534
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4369374513626099,
      "learning_rate": 4.8e-05,
      "loss": 0.9118,
      "step": 3068
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5828833418237391,
      "eval_loss": 0.8921328783035278,
      "eval_runtime": 3.5758,
      "eval_samples_per_second": 2744.85,
      "eval_steps_per_second": 10.907,
      "step": 3068
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.5986831188201904,
      "learning_rate": 4.7e-05,
      "loss": 0.8579,
      "step": 4602
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.604890473764646,
      "eval_loss": 0.8575275540351868,
      "eval_runtime": 3.6158,
      "eval_samples_per_second": 2714.455,
      "eval_steps_per_second": 10.786,
      "step": 4602
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.148224353790283,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.811,
      "step": 6136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6191543555781966,
      "eval_loss": 0.8428041934967041,
      "eval_runtime": 3.6078,
      "eval_samples_per_second": 2720.467,
      "eval_steps_per_second": 10.81,
      "step": 6136
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.6634807586669922,
      "learning_rate": 4.5e-05,
      "loss": 0.7625,
      "step": 7670
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6323993886907794,
      "eval_loss": 0.8314237594604492,
      "eval_runtime": 3.4027,
      "eval_samples_per_second": 2884.439,
      "eval_steps_per_second": 11.461,
      "step": 7670
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.022226572036743,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7165,
      "step": 9204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6408558329088131,
      "eval_loss": 0.8437779545783997,
      "eval_runtime": 3.4697,
      "eval_samples_per_second": 2828.773,
      "eval_steps_per_second": 11.24,
      "step": 9204
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.9079397916793823,
      "learning_rate": 4.3e-05,
      "loss": 0.6721,
      "step": 10738
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6440142638818136,
      "eval_loss": 0.8497779369354248,
      "eval_runtime": 3.4052,
      "eval_samples_per_second": 2882.342,
      "eval_steps_per_second": 11.453,
      "step": 10738
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.122452735900879,
      "learning_rate": 4.2e-05,
      "loss": 0.6294,
      "step": 12272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6461538461538462,
      "eval_loss": 0.8689283132553101,
      "eval_runtime": 3.4287,
      "eval_samples_per_second": 2862.621,
      "eval_steps_per_second": 11.375,
      "step": 12272
    },
    {
      "epoch": 9.0,
      "grad_norm": 2.5950520038604736,
      "learning_rate": 4.1e-05,
      "loss": 0.5874,
      "step": 13806
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6465613856342333,
      "eval_loss": 0.9019529223442078,
      "eval_runtime": 3.4591,
      "eval_samples_per_second": 2837.477,
      "eval_steps_per_second": 11.275,
      "step": 13806
    },
    {
      "epoch": 10.0,
      "grad_norm": 2.372058153152466,
      "learning_rate": 4e-05,
      "loss": 0.5462,
      "step": 15340
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6472745797249109,
      "eval_loss": 0.9525629281997681,
      "eval_runtime": 3.4343,
      "eval_samples_per_second": 2857.97,
      "eval_steps_per_second": 11.356,
      "step": 15340
    },
    {
      "epoch": 10.0,
      "step": 15340,
      "total_flos": 1.029836100834816e+17,
      "train_loss": 0.7496155541132762,
      "train_runtime": 2650.3053,
      "train_samples_per_second": 7408.618,
      "train_steps_per_second": 28.94
    }
  ],
  "logging_steps": 1,
  "max_steps": 76700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 1.029836100834816e+17,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}