Hugging Face's logo

gguichard
/
verbnet_train

Token Classification
Transformers
Safetensors
roberta
Inference Endpoints
Model card Files Community
verbnet_train
File size: 3,192 Bytes 
2d92c80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.6925345659255981,
  "best_model_checkpoint": "verbnet_train/checkpoint-62460",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 62460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 13.90185260772705,
      "learning_rate": 1.960034582132565e-05,
      "loss": 1.9688,
      "step": 10410
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0218104124069214,
      "eval_runtime": 27.1535,
      "eval_samples_per_second": 161.453,
      "eval_steps_per_second": 20.182,
      "step": 10410
    },
    {
      "epoch": 2.0,
      "grad_norm": 35.40193176269531,
      "learning_rate": 1.9200499519692607e-05,
      "loss": 0.9642,
      "step": 20820
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8278869986534119,
      "eval_runtime": 27.1826,
      "eval_samples_per_second": 161.28,
      "eval_steps_per_second": 20.16,
      "step": 20820
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9018324613571167,
      "learning_rate": 1.8800653218059558e-05,
      "loss": 0.7979,
      "step": 31230
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7543942928314209,
      "eval_runtime": 27.2955,
      "eval_samples_per_second": 160.612,
      "eval_steps_per_second": 20.077,
      "step": 31230
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.808300018310547,
      "learning_rate": 1.840073006724304e-05,
      "loss": 0.7172,
      "step": 41640
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.7305750250816345,
      "eval_runtime": 27.2998,
      "eval_samples_per_second": 160.587,
      "eval_steps_per_second": 20.073,
      "step": 41640
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.197155714035034,
      "learning_rate": 1.8000922190201732e-05,
      "loss": 0.6632,
      "step": 52050
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7061994671821594,
      "eval_runtime": 27.2802,
      "eval_samples_per_second": 160.703,
      "eval_steps_per_second": 20.088,
      "step": 52050
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.914452075958252,
      "learning_rate": 1.7601075888568687e-05,
      "loss": 0.6295,
      "step": 62460
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6925345659255981,
      "eval_runtime": 27.2037,
      "eval_samples_per_second": 161.154,
      "eval_steps_per_second": 20.144,
      "step": 62460
    }
  ],
  "logging_steps": 500,
  "max_steps": 520500,
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.543390648920925e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}