Hugging Face's logo

fpadovani
/
en_wiki_mlm_30_new

Fill-Mask
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
en_wiki_mlm_30_new
File size: 4,403 Bytes 
6f51129
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 6.440639972686768,
  "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained_last/en_wiki_mlm_30/checkpoint-24000",
  "epoch": 13.582342954159593,
  "eval_steps": 2000,
  "global_step": 24000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1318619128466327,
      "eval_loss": 7.872045516967773,
      "eval_runtime": 3.9374,
      "eval_samples_per_second": 1252.08,
      "eval_steps_per_second": 78.477,
      "step": 2000
    },
    {
      "epoch": 2.2637238256932655,
      "grad_norm": 1.0014455318450928,
      "learning_rate": 1e-05,
      "loss": 7.9236,
      "step": 4000
    },
    {
      "epoch": 2.2637238256932655,
      "eval_loss": 7.107393264770508,
      "eval_runtime": 3.9376,
      "eval_samples_per_second": 1252.036,
      "eval_steps_per_second": 78.474,
      "step": 4000
    },
    {
      "epoch": 3.395585738539898,
      "eval_loss": 7.030406951904297,
      "eval_runtime": 3.9404,
      "eval_samples_per_second": 1251.146,
      "eval_steps_per_second": 78.419,
      "step": 6000
    },
    {
      "epoch": 4.527447651386531,
      "grad_norm": 1.1162114143371582,
      "learning_rate": 2e-05,
      "loss": 7.0257,
      "step": 8000
    },
    {
      "epoch": 4.527447651386531,
      "eval_loss": 6.953151226043701,
      "eval_runtime": 4.0906,
      "eval_samples_per_second": 1205.208,
      "eval_steps_per_second": 75.539,
      "step": 8000
    },
    {
      "epoch": 5.659309564233164,
      "eval_loss": 6.87604284286499,
      "eval_runtime": 3.912,
      "eval_samples_per_second": 1260.235,
      "eval_steps_per_second": 78.988,
      "step": 10000
    },
    {
      "epoch": 6.791171477079796,
      "grad_norm": 1.346594214439392,
      "learning_rate": 3e-05,
      "loss": 6.8811,
      "step": 12000
    },
    {
      "epoch": 6.791171477079796,
      "eval_loss": 6.811014175415039,
      "eval_runtime": 3.951,
      "eval_samples_per_second": 1247.773,
      "eval_steps_per_second": 78.207,
      "step": 12000
    },
    {
      "epoch": 7.923033389926429,
      "eval_loss": 6.731590747833252,
      "eval_runtime": 3.8635,
      "eval_samples_per_second": 1276.05,
      "eval_steps_per_second": 79.98,
      "step": 14000
    },
    {
      "epoch": 9.054895302773062,
      "grad_norm": 1.458003044128418,
      "learning_rate": 4e-05,
      "loss": 6.7587,
      "step": 16000
    },
    {
      "epoch": 9.054895302773062,
      "eval_loss": 6.689206600189209,
      "eval_runtime": 3.8397,
      "eval_samples_per_second": 1283.96,
      "eval_steps_per_second": 80.475,
      "step": 16000
    },
    {
      "epoch": 10.186757215619695,
      "eval_loss": 6.650099754333496,
      "eval_runtime": 3.9002,
      "eval_samples_per_second": 1264.041,
      "eval_steps_per_second": 79.227,
      "step": 18000
    },
    {
      "epoch": 11.318619128466327,
      "grad_norm": 1.5871217250823975,
      "learning_rate": 5e-05,
      "loss": 6.6566,
      "step": 20000
    },
    {
      "epoch": 11.318619128466327,
      "eval_loss": 6.595088958740234,
      "eval_runtime": 3.9235,
      "eval_samples_per_second": 1256.533,
      "eval_steps_per_second": 78.756,
      "step": 20000
    },
    {
      "epoch": 12.45048104131296,
      "eval_loss": 6.525483131408691,
      "eval_runtime": 3.8651,
      "eval_samples_per_second": 1275.512,
      "eval_steps_per_second": 79.946,
      "step": 22000
    },
    {
      "epoch": 13.582342954159593,
      "grad_norm": 2.502711296081543,
      "learning_rate": 6e-05,
      "loss": 6.546,
      "step": 24000
    },
    {
      "epoch": 13.582342954159593,
      "eval_loss": 6.440639972686768,
      "eval_runtime": 3.8611,
      "eval_samples_per_second": 1276.85,
      "eval_steps_per_second": 80.03,
      "step": 24000
    }
  ],
  "logging_steps": 4000,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 57,
  "save_steps": 4000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7485719972806656.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}