Hugging Face's logo

Hartunka
/
tiny_bert_km_50_v1_mnli

TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
tiny_bert_km_50_v1_mnli
File size: 4,720 Bytes
144bb1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.8321161270141602,
  "best_model_checkpoint": "tiny_bert_km_50_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": 0.9514528512954712,
      "learning_rate": 4.9e-05,
      "loss": 1.0082,
      "step": 1534
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5437595517065715,
      "eval_loss": 0.942550778388977,
      "eval_runtime": 3.5158,
      "eval_samples_per_second": 2791.707,
      "eval_steps_per_second": 11.093,
      "step": 1534
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3989537954330444,
      "learning_rate": 4.8e-05,
      "loss": 0.9147,
      "step": 3068
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5845134997452879,
      "eval_loss": 0.8889986276626587,
      "eval_runtime": 3.4266,
      "eval_samples_per_second": 2864.392,
      "eval_steps_per_second": 11.382,
      "step": 3068
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.4162970781326294,
      "learning_rate": 4.7e-05,
      "loss": 0.8604,
      "step": 4602
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.606316861946001,
      "eval_loss": 0.8645786046981812,
      "eval_runtime": 3.4993,
      "eval_samples_per_second": 2804.851,
      "eval_steps_per_second": 11.145,
      "step": 4602
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4847444295883179,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.8145,
      "step": 6136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.615588385124809,
      "eval_loss": 0.8447086811065674,
      "eval_runtime": 3.4418,
      "eval_samples_per_second": 2851.689,
      "eval_steps_per_second": 11.331,
      "step": 6136
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.7801928520202637,
      "learning_rate": 4.5e-05,
      "loss": 0.7652,
      "step": 7670
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6298522669383596,
      "eval_loss": 0.8321161270141602,
      "eval_runtime": 3.451,
      "eval_samples_per_second": 2844.112,
      "eval_steps_per_second": 11.301,
      "step": 7670
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.2125303745269775,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7172,
      "step": 9204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6405501782985227,
      "eval_loss": 0.84904545545578,
      "eval_runtime": 3.4667,
      "eval_samples_per_second": 2831.233,
      "eval_steps_per_second": 11.25,
      "step": 9204
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.1476242542266846,
      "learning_rate": 4.3e-05,
      "loss": 0.6722,
      "step": 10738
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6512480896586856,
      "eval_loss": 0.8362392783164978,
      "eval_runtime": 3.4933,
      "eval_samples_per_second": 2809.683,
      "eval_steps_per_second": 11.164,
      "step": 10738
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.0134174823760986,
      "learning_rate": 4.2e-05,
      "loss": 0.6289,
      "step": 12272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6459500764136525,
      "eval_loss": 0.8634655475616455,
      "eval_runtime": 3.4256,
      "eval_samples_per_second": 2865.208,
      "eval_steps_per_second": 11.385,
      "step": 12272
    },
    {
      "epoch": 9.0,
      "grad_norm": 2.7003607749938965,
      "learning_rate": 4.1e-05,
      "loss": 0.5887,
      "step": 13806
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6463576158940397,
      "eval_loss": 0.9014362096786499,
      "eval_runtime": 3.4293,
      "eval_samples_per_second": 2862.09,
      "eval_steps_per_second": 11.373,
      "step": 13806
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.0219602584838867,
      "learning_rate": 4e-05,
      "loss": 0.5489,
      "step": 15340
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6449312277126846,
      "eval_loss": 0.9343048334121704,
      "eval_runtime": 3.4187,
      "eval_samples_per_second": 2870.96,
      "eval_steps_per_second": 11.408,
      "step": 15340
    },
    {
      "epoch": 10.0,
      "step": 15340,
      "total_flos": 1.029836100834816e+17,
      "train_loss": 0.751894306048576,
      "train_runtime": 2625.2366,
      "train_samples_per_second": 7479.364,
      "train_steps_per_second": 29.216
    }
  ],
  "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
}