Hugging Face's logo

SamJoshua
/
EsperBERTo

Fill-Mask
Transformers
Safetensors
roberta
Inference Endpoints
Model card Files Community
EsperBERTo
File size: 4,243 Bytes 
344505a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6566850538481744,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03283425269240872,
      "grad_norm": 2.148223638534546,
      "learning_rate": 4.8358287365379566e-05,
      "loss": 7.8532,
      "step": 500
    },
    {
      "epoch": 0.06566850538481744,
      "grad_norm": 1.8999865055084229,
      "learning_rate": 4.671657473075913e-05,
      "loss": 7.2619,
      "step": 1000
    },
    {
      "epoch": 0.09850275807722617,
      "grad_norm": 1.8169187307357788,
      "learning_rate": 4.5074862096138694e-05,
      "loss": 7.078,
      "step": 1500
    },
    {
      "epoch": 0.1313370107696349,
      "grad_norm": 2.516470193862915,
      "learning_rate": 4.343314946151826e-05,
      "loss": 6.9502,
      "step": 2000
    },
    {
      "epoch": 0.1641712634620436,
      "grad_norm": 2.3785781860351562,
      "learning_rate": 4.179143682689782e-05,
      "loss": 6.8573,
      "step": 2500
    },
    {
      "epoch": 0.19700551615445233,
      "grad_norm": 2.1694188117980957,
      "learning_rate": 4.0149724192277385e-05,
      "loss": 6.8,
      "step": 3000
    },
    {
      "epoch": 0.22983976884686105,
      "grad_norm": 2.474036455154419,
      "learning_rate": 3.850801155765695e-05,
      "loss": 6.744,
      "step": 3500
    },
    {
      "epoch": 0.2626740215392698,
      "grad_norm": 2.19565749168396,
      "learning_rate": 3.686629892303651e-05,
      "loss": 6.6814,
      "step": 4000
    },
    {
      "epoch": 0.29550827423167847,
      "grad_norm": 2.747317314147949,
      "learning_rate": 3.522458628841608e-05,
      "loss": 6.5869,
      "step": 4500
    },
    {
      "epoch": 0.3283425269240872,
      "grad_norm": 3.399601936340332,
      "learning_rate": 3.358287365379564e-05,
      "loss": 6.4711,
      "step": 5000
    },
    {
      "epoch": 0.3611767796164959,
      "grad_norm": 2.9853923320770264,
      "learning_rate": 3.1941161019175205e-05,
      "loss": 6.3167,
      "step": 5500
    },
    {
      "epoch": 0.39401103230890466,
      "grad_norm": 3.57155704498291,
      "learning_rate": 3.029944838455477e-05,
      "loss": 6.2061,
      "step": 6000
    },
    {
      "epoch": 0.42684528500131336,
      "grad_norm": 3.53355073928833,
      "learning_rate": 2.8657735749934332e-05,
      "loss": 6.0795,
      "step": 6500
    },
    {
      "epoch": 0.4596795376937221,
      "grad_norm": 3.1891579627990723,
      "learning_rate": 2.70160231153139e-05,
      "loss": 5.9704,
      "step": 7000
    },
    {
      "epoch": 0.4925137903861308,
      "grad_norm": 3.8728067874908447,
      "learning_rate": 2.5374310480693457e-05,
      "loss": 5.8494,
      "step": 7500
    },
    {
      "epoch": 0.5253480430785396,
      "grad_norm": 3.752729654312134,
      "learning_rate": 2.3732597846073024e-05,
      "loss": 5.7467,
      "step": 8000
    },
    {
      "epoch": 0.5581822957709482,
      "grad_norm": 3.093104124069214,
      "learning_rate": 2.2090885211452588e-05,
      "loss": 5.6585,
      "step": 8500
    },
    {
      "epoch": 0.5910165484633569,
      "grad_norm": 3.5485284328460693,
      "learning_rate": 2.0449172576832152e-05,
      "loss": 5.5876,
      "step": 9000
    },
    {
      "epoch": 0.6238508011557657,
      "grad_norm": 3.3730971813201904,
      "learning_rate": 1.8807459942211716e-05,
      "loss": 5.5165,
      "step": 9500
    },
    {
      "epoch": 0.6566850538481744,
      "grad_norm": 3.767274856567383,
      "learning_rate": 1.716574730759128e-05,
      "loss": 5.4677,
      "step": 10000
    }
  ],
  "logging_steps": 500,
  "max_steps": 15228,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.122034184192e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}