Hugging Face's logo

Hartunka
/
tiny_bert_km_5_v2_sst2

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Metrics Community
tiny_bert_km_5_v2_sst2
File size: 3,664 Bytes
e87b756
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_global_step": 264,
  "best_metric": 0.44193360209465027,
  "best_model_checkpoint": "tiny_bert_km_5_v2_sst2/checkpoint-264",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1584,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 7.1062188148498535,
      "learning_rate": 4.9e-05,
      "loss": 0.4137,
      "step": 264
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8130733944954128,
      "eval_loss": 0.44193360209465027,
      "eval_runtime": 0.2752,
      "eval_samples_per_second": 3168.51,
      "eval_steps_per_second": 14.534,
      "step": 264
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.389181137084961,
      "learning_rate": 4.8e-05,
      "loss": 0.2547,
      "step": 528
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8107798165137615,
      "eval_loss": 0.47274479269981384,
      "eval_runtime": 0.2612,
      "eval_samples_per_second": 3338.177,
      "eval_steps_per_second": 15.313,
      "step": 528
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.381705284118652,
      "learning_rate": 4.7e-05,
      "loss": 0.1972,
      "step": 792
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8107798165137615,
      "eval_loss": 0.4966350197792053,
      "eval_runtime": 0.2609,
      "eval_samples_per_second": 3342.151,
      "eval_steps_per_second": 15.331,
      "step": 792
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.678281307220459,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.1623,
      "step": 1056
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8176605504587156,
      "eval_loss": 0.46778005361557007,
      "eval_runtime": 0.2752,
      "eval_samples_per_second": 3168.123,
      "eval_steps_per_second": 14.533,
      "step": 1056
    },
    {
      "epoch": 5.0,
      "grad_norm": 6.3953351974487305,
      "learning_rate": 4.5e-05,
      "loss": 0.1359,
      "step": 1320
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8096330275229358,
      "eval_loss": 0.5381088256835938,
      "eval_runtime": 0.2676,
      "eval_samples_per_second": 3259.102,
      "eval_steps_per_second": 14.95,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.137275218963623,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.1171,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8142201834862385,
      "eval_loss": 0.6161597967147827,
      "eval_runtime": 0.2605,
      "eval_samples_per_second": 3347.238,
      "eval_steps_per_second": 15.354,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "step": 1584,
      "total_flos": 1.0596790573590528e+16,
      "train_loss": 0.21348130221318717,
      "train_runtime": 215.8494,
      "train_samples_per_second": 15600.923,
      "train_steps_per_second": 61.154
    }
  ],
  "logging_steps": 1,
  "max_steps": 13200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0596790573590528e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}