Hugging Face's logo

Hartunka
/
distilbert_rand_50_v2_sst2

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Metrics Community
distilbert_rand_50_v2_sst2
File size: 3,655 Bytes
0f0266e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.43955448269844055,
  "best_model_checkpoint": "distilbert_rand_50_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": 7.4908223152160645,
      "learning_rate": 4.9e-05,
      "loss": 0.3925,
      "step": 264
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8245412844036697,
      "eval_loss": 0.43955448269844055,
      "eval_runtime": 0.3705,
      "eval_samples_per_second": 2353.603,
      "eval_steps_per_second": 10.796,
      "step": 264
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.066856384277344,
      "learning_rate": 4.8e-05,
      "loss": 0.219,
      "step": 528
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8268348623853211,
      "eval_loss": 0.47368353605270386,
      "eval_runtime": 0.3774,
      "eval_samples_per_second": 2310.281,
      "eval_steps_per_second": 10.598,
      "step": 528
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.2119340896606445,
      "learning_rate": 4.7e-05,
      "loss": 0.1609,
      "step": 792
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8084862385321101,
      "eval_loss": 0.49463415145874023,
      "eval_runtime": 0.374,
      "eval_samples_per_second": 2331.799,
      "eval_steps_per_second": 10.696,
      "step": 792
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.589087009429932,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.1177,
      "step": 1056
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8176605504587156,
      "eval_loss": 0.6155182719230652,
      "eval_runtime": 0.3725,
      "eval_samples_per_second": 2340.769,
      "eval_steps_per_second": 10.737,
      "step": 1056
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.820615768432617,
      "learning_rate": 4.5e-05,
      "loss": 0.0889,
      "step": 1320
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8107798165137615,
      "eval_loss": 0.6215694546699524,
      "eval_runtime": 0.3663,
      "eval_samples_per_second": 2380.263,
      "eval_steps_per_second": 10.919,
      "step": 1320
    },
    {
      "epoch": 6.0,
      "grad_norm": 5.1633477210998535,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0698,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8061926605504587,
      "eval_loss": 0.765625,
      "eval_runtime": 0.3636,
      "eval_samples_per_second": 2398.386,
      "eval_steps_per_second": 11.002,
      "step": 1584
    },
    {
      "epoch": 6.0,
      "step": 1584,
      "total_flos": 2.676464049624883e+16,
      "train_loss": 0.1747924005142366,
      "train_runtime": 379.2232,
      "train_samples_per_second": 8879.864,
      "train_steps_per_second": 34.808
    }
  ],
  "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": 2.676464049624883e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}