Hugging Face's logo

MarineLives
/
mBert-finetuned-yiddish-experiment-3

Fill-Mask
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mBert-finetuned-yiddish-experiment-3
File size: 4,740 Bytes 
90e0c88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
175
176
177
178
179
180
181
182
183
184
 
{
  "best_metric": 1.52731454372406,
  "best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/bert-base-multilingual-cased-finetuned-yiddish-experiment-3/checkpoint-700",
  "epoch": 2.3640661938534278,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2364066193853428,
      "grad_norm": 28.178190231323242,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 11.143,
      "step": 100
    },
    {
      "epoch": 0.2364066193853428,
      "eval_loss": 7.659108638763428,
      "eval_runtime": 0.809,
      "eval_samples_per_second": 260.829,
      "eval_steps_per_second": 65.516,
      "step": 100
    },
    {
      "epoch": 0.4728132387706856,
      "grad_norm": 15.27036190032959,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 4.1737,
      "step": 200
    },
    {
      "epoch": 0.4728132387706856,
      "eval_loss": 2.2642054557800293,
      "eval_runtime": 0.8681,
      "eval_samples_per_second": 243.069,
      "eval_steps_per_second": 61.055,
      "step": 200
    },
    {
      "epoch": 0.7092198581560284,
      "grad_norm": 13.071714401245117,
      "learning_rate": 5e-06,
      "loss": 2.0579,
      "step": 300
    },
    {
      "epoch": 0.7092198581560284,
      "eval_loss": 1.7709782123565674,
      "eval_runtime": 0.8603,
      "eval_samples_per_second": 245.25,
      "eval_steps_per_second": 61.603,
      "step": 300
    },
    {
      "epoch": 0.9456264775413712,
      "grad_norm": 8.75770092010498,
      "learning_rate": 4.8727735368956745e-06,
      "loss": 1.6963,
      "step": 400
    },
    {
      "epoch": 0.9456264775413712,
      "eval_loss": 1.671216607093811,
      "eval_runtime": 0.9312,
      "eval_samples_per_second": 226.587,
      "eval_steps_per_second": 56.915,
      "step": 400
    },
    {
      "epoch": 1.1820330969267139,
      "grad_norm": 11.299208641052246,
      "learning_rate": 4.745547073791349e-06,
      "loss": 1.5705,
      "step": 500
    },
    {
      "epoch": 1.1820330969267139,
      "eval_loss": 1.6379029750823975,
      "eval_runtime": 0.872,
      "eval_samples_per_second": 241.979,
      "eval_steps_per_second": 60.782,
      "step": 500
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 7.146368980407715,
      "learning_rate": 4.618320610687023e-06,
      "loss": 1.5353,
      "step": 600
    },
    {
      "epoch": 1.4184397163120568,
      "eval_loss": 1.600274682044983,
      "eval_runtime": 0.9755,
      "eval_samples_per_second": 216.307,
      "eval_steps_per_second": 54.333,
      "step": 600
    },
    {
      "epoch": 1.6548463356973995,
      "grad_norm": 7.896175861358643,
      "learning_rate": 4.491094147582698e-06,
      "loss": 1.5213,
      "step": 700
    },
    {
      "epoch": 1.6548463356973995,
      "eval_loss": 1.52731454372406,
      "eval_runtime": 0.9375,
      "eval_samples_per_second": 225.075,
      "eval_steps_per_second": 56.535,
      "step": 700
    },
    {
      "epoch": 1.8912529550827424,
      "grad_norm": 10.965773582458496,
      "learning_rate": 4.363867684478372e-06,
      "loss": 1.4387,
      "step": 800
    },
    {
      "epoch": 1.8912529550827424,
      "eval_loss": 1.5414769649505615,
      "eval_runtime": 0.8682,
      "eval_samples_per_second": 243.03,
      "eval_steps_per_second": 61.045,
      "step": 800
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 10.384049415588379,
      "learning_rate": 4.236641221374046e-06,
      "loss": 1.3973,
      "step": 900
    },
    {
      "epoch": 2.127659574468085,
      "eval_loss": 1.5529794692993164,
      "eval_runtime": 0.9033,
      "eval_samples_per_second": 233.6,
      "eval_steps_per_second": 58.677,
      "step": 900
    },
    {
      "epoch": 2.3640661938534278,
      "grad_norm": 5.56968879699707,
      "learning_rate": 4.10941475826972e-06,
      "loss": 1.4266,
      "step": 1000
    },
    {
      "epoch": 2.3640661938534278,
      "eval_loss": 1.5328062772750854,
      "eval_runtime": 0.961,
      "eval_samples_per_second": 219.562,
      "eval_steps_per_second": 55.151,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 4230,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 131739148800000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}