Hugging Face's logo

Hartunka
/
tiny_bert_rand_100_v1_qqp

TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
tiny_bert_rand_100_v1_qqp
File size: 4,630 Bytes
4eba8be
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.4153307378292084,
  "best_model_checkpoint": "tiny_bert_rand_100_v1_qqp/checkpoint-4266",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 11376,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.7541351318359375,
      "learning_rate": 4.9e-05,
      "loss": 0.496,
      "step": 1422
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7838486272569873,
      "eval_combined_score": 0.7322145289141401,
      "eval_f1": 0.6805804305712928,
      "eval_loss": 0.4491816461086273,
      "eval_runtime": 14.8017,
      "eval_samples_per_second": 2731.443,
      "eval_steps_per_second": 10.674,
      "step": 1422
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.7397406101226807,
      "learning_rate": 4.8e-05,
      "loss": 0.4089,
      "step": 2844
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8033638387336136,
      "eval_combined_score": 0.7612324811645597,
      "eval_f1": 0.7191011235955056,
      "eval_loss": 0.4195970892906189,
      "eval_runtime": 14.1267,
      "eval_samples_per_second": 2861.947,
      "eval_steps_per_second": 11.184,
      "step": 2844
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.006162405014038,
      "learning_rate": 4.7e-05,
      "loss": 0.3518,
      "step": 4266
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8110066782092505,
      "eval_combined_score": 0.7764890548375805,
      "eval_f1": 0.7419714314659103,
      "eval_loss": 0.4153307378292084,
      "eval_runtime": 14.1896,
      "eval_samples_per_second": 2849.272,
      "eval_steps_per_second": 11.135,
      "step": 4266
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.5791120529174805,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3062,
      "step": 5688
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8186495176848875,
      "eval_combined_score": 0.780485228372211,
      "eval_f1": 0.7423209390595347,
      "eval_loss": 0.4295639395713806,
      "eval_runtime": 14.2354,
      "eval_samples_per_second": 2840.098,
      "eval_steps_per_second": 11.099,
      "step": 5688
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.346965789794922,
      "learning_rate": 4.5e-05,
      "loss": 0.2689,
      "step": 7110
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8198367548849864,
      "eval_combined_score": 0.7865778193281611,
      "eval_f1": 0.7533188837713357,
      "eval_loss": 0.4466039538383484,
      "eval_runtime": 13.8417,
      "eval_samples_per_second": 2920.893,
      "eval_steps_per_second": 11.415,
      "step": 7110
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.1513712406158447,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.239,
      "step": 8532
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8201582982933465,
      "eval_combined_score": 0.7912292357791229,
      "eval_f1": 0.7623001732648992,
      "eval_loss": 0.4361380636692047,
      "eval_runtime": 13.8654,
      "eval_samples_per_second": 2915.885,
      "eval_steps_per_second": 11.395,
      "step": 8532
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.002156734466553,
      "learning_rate": 4.3e-05,
      "loss": 0.2131,
      "step": 9954
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8231016571852585,
      "eval_combined_score": 0.7940583854332128,
      "eval_f1": 0.765015113681167,
      "eval_loss": 0.46639078855514526,
      "eval_runtime": 13.9853,
      "eval_samples_per_second": 2890.887,
      "eval_steps_per_second": 11.298,
      "step": 9954
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.098388910293579,
      "learning_rate": 4.2e-05,
      "loss": 0.1896,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8200840959683403,
      "eval_combined_score": 0.7939181654809773,
      "eval_f1": 0.7677522349936143,
      "eval_loss": 0.5052474141120911,
      "eval_runtime": 13.808,
      "eval_samples_per_second": 2928.009,
      "eval_steps_per_second": 11.443,
      "step": 11376
    },
    {
      "epoch": 8.0,
      "step": 11376,
      "total_flos": 7.633075201391002e+16,
      "train_loss": 0.3091887569293359,
      "train_runtime": 2020.2759,
      "train_samples_per_second": 9004.859,
      "train_steps_per_second": 35.193
    }
  ],
  "logging_steps": 1,
  "max_steps": 71100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "total_flos": 7.633075201391002e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}