Hugging Face's logo

anoaky
/
sbf-bart-speakerMinority

Text Classification
Transformers
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
sbf-bart-speakerMinority
File size: 3,295 Bytes 
eb58171
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d395bc9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb58171
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.991437584497522,
  "eval_steps": 500,
  "global_step": 2770,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_f1": 0.018691588785046728,
      "eval_loss": 0.8330444097518921,
      "eval_precision": 0.009461009174311927,
      "eval_recall": 0.7674418604651163,
      "eval_runtime": 51.6093,
      "eval_samples_per_second": 90.546,
      "eval_steps_per_second": 11.335,
      "step": 0
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4809592068195343,
      "learning_rate": 3.998194945848376e-05,
      "loss": 0.0586,
      "step": 555
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.0,
      "eval_loss": 0.059180792421102524,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 52.6196,
      "eval_samples_per_second": 88.807,
      "eval_steps_per_second": 11.118,
      "step": 555
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.132050514221191,
      "learning_rate": 2.996389891696751e-05,
      "loss": 0.0557,
      "step": 1110
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.0,
      "eval_loss": 0.05642171949148178,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 40.9562,
      "eval_samples_per_second": 114.097,
      "eval_steps_per_second": 14.284,
      "step": 1110
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.548943996429443,
      "learning_rate": 1.9945848375451266e-05,
      "loss": 0.0553,
      "step": 1665
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.0,
      "eval_loss": 0.05951603502035141,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 40.9175,
      "eval_samples_per_second": 114.205,
      "eval_steps_per_second": 14.297,
      "step": 1665
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.44529011845588684,
      "learning_rate": 9.927797833935018e-06,
      "loss": 0.0558,
      "step": 2220
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.0,
      "eval_loss": 0.059898294508457184,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 40.5657,
      "eval_samples_per_second": 115.196,
      "eval_steps_per_second": 14.421,
      "step": 2220
    },
    {
      "epoch": 4.991437584497522,
      "grad_norm": 14.272518157958984,
      "learning_rate": 0.0,
      "loss": 0.0559,
      "step": 2770
    },
    {
      "epoch": 4.991437584497522,
      "eval_f1": 0.0,
      "eval_loss": 0.058250606060028076,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 43.3617,
      "eval_samples_per_second": 107.768,
      "eval_steps_per_second": 13.491,
      "step": 2770
    }
  ],
  "logging_steps": 500,
  "max_steps": 2770,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.629766539300045e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}