Hugging Face's logo

gokulsrinivasagan
/
bert_tiny_lda_100_v1_book_sst2

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bert_tiny_lda_100_v1_book_sst2
File size: 3,638 Bytes 
6bb78d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.3489038348197937,
  "best_model_checkpoint": "bert_tiny_lda_100_v1_book_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": 8.271644592285156,
      "learning_rate": 4.9e-05,
      "loss": 0.3634,
      "step": 264
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8555045871559633,
      "eval_loss": 0.3489038348197937,
      "eval_runtime": 0.277,
      "eval_samples_per_second": 3148.234,
      "eval_steps_per_second": 14.441,
      "step": 264
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.306727409362793,
      "learning_rate": 4.8e-05,
      "loss": 0.2189,
      "step": 528
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8600917431192661,
      "eval_loss": 0.36337217688560486,
      "eval_runtime": 0.3273,
      "eval_samples_per_second": 2664.447,
      "eval_steps_per_second": 12.222,
      "step": 528
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.631307125091553,
      "learning_rate": 4.7e-05,
      "loss": 0.1528,
      "step": 792
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8646788990825688,
      "eval_loss": 0.4506845772266388,
      "eval_runtime": 0.2825,
      "eval_samples_per_second": 3086.85,
      "eval_steps_per_second": 14.16,
      "step": 792
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.8820979595184326,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.1199,
      "step": 1056
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8761467889908257,
      "eval_loss": 0.382750540971756,
      "eval_runtime": 0.2751,
      "eval_samples_per_second": 3169.237,
      "eval_steps_per_second": 14.538,
      "step": 1056
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.706533193588257,
      "learning_rate": 4.5e-05,
      "loss": 0.094,
      "step": 1320
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8727064220183486,
      "eval_loss": 0.3957236707210541,
      "eval_runtime": 0.2958,
      "eval_samples_per_second": 2947.786,
      "eval_steps_per_second": 13.522,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.119465351104736,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0742,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8589449541284404,
      "eval_loss": 0.47635790705680847,
      "eval_runtime": 0.3084,
      "eval_samples_per_second": 2827.358,
      "eval_steps_per_second": 12.97,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "step": 1584,
      "total_flos": 1.0596790573590528e+16,
      "train_loss": 0.1705179467345729,
      "train_runtime": 228.7859,
      "train_samples_per_second": 14718.786,
      "train_steps_per_second": 57.696
    }
  ],
  "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
}