Hugging Face's logo

AbdoTW
/
arabic-ocr-checkpoints

Safetensors
Model card Files
xet
 Community
arabic-ocr-checkpoints
File size: 4,712 Bytes
6279980
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
185
186
187
188
189
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7777777777777777,
  "eval_steps": 50,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1984126984126984,
      "grad_norm": 1.0922354459762573,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.8473,
      "step": 25
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 0.7849488854408264,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.3692,
      "step": 50
    },
    {
      "epoch": 0.3968253968253968,
      "eval_loss": 0.3103943467140198,
      "eval_runtime": 10.1545,
      "eval_samples_per_second": 4.136,
      "eval_steps_per_second": 2.068,
      "step": 50
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.4042750298976898,
      "learning_rate": 2.9365079365079366e-05,
      "loss": 0.249,
      "step": 75
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.505721926689148,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.2248,
      "step": 100
    },
    {
      "epoch": 0.7936507936507936,
      "eval_loss": 0.23757970333099365,
      "eval_runtime": 10.1307,
      "eval_samples_per_second": 4.146,
      "eval_steps_per_second": 2.073,
      "step": 100
    },
    {
      "epoch": 0.9920634920634921,
      "grad_norm": 0.39118653535842896,
      "learning_rate": 4.9206349206349204e-05,
      "loss": 0.1997,
      "step": 125
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.4834806025028229,
      "learning_rate": 5.912698412698413e-05,
      "loss": 0.1717,
      "step": 150
    },
    {
      "epoch": 1.1904761904761905,
      "eval_loss": 0.20604592561721802,
      "eval_runtime": 10.1545,
      "eval_samples_per_second": 4.136,
      "eval_steps_per_second": 2.068,
      "step": 150
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 0.38224297761917114,
      "learning_rate": 6.904761904761905e-05,
      "loss": 0.1684,
      "step": 175
    },
    {
      "epoch": 1.5873015873015874,
      "grad_norm": 0.35443320870399475,
      "learning_rate": 7.896825396825397e-05,
      "loss": 0.1502,
      "step": 200
    },
    {
      "epoch": 1.5873015873015874,
      "eval_loss": 0.19332902133464813,
      "eval_runtime": 10.0977,
      "eval_samples_per_second": 4.159,
      "eval_steps_per_second": 2.08,
      "step": 200
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.3137013614177704,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.1549,
      "step": 225
    },
    {
      "epoch": 1.9841269841269842,
      "grad_norm": 0.30676764249801636,
      "learning_rate": 9.880952380952381e-05,
      "loss": 0.1449,
      "step": 250
    },
    {
      "epoch": 1.9841269841269842,
      "eval_loss": 0.17996199429035187,
      "eval_runtime": 10.0168,
      "eval_samples_per_second": 4.193,
      "eval_steps_per_second": 2.096,
      "step": 250
    },
    {
      "epoch": 2.1825396825396823,
      "grad_norm": 0.31375375390052795,
      "learning_rate": 9.997678517546382e-05,
      "loss": 0.1111,
      "step": 275
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.2725541293621063,
      "learning_rate": 9.989407561073525e-05,
      "loss": 0.1016,
      "step": 300
    },
    {
      "epoch": 2.380952380952381,
      "eval_loss": 0.17762605845928192,
      "eval_runtime": 10.0289,
      "eval_samples_per_second": 4.188,
      "eval_steps_per_second": 2.094,
      "step": 300
    },
    {
      "epoch": 2.5793650793650795,
      "grad_norm": 0.31162211298942566,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.1044,
      "step": 325
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.2855686843395233,
      "learning_rate": 9.954934556197257e-05,
      "loss": 0.1087,
      "step": 350
    },
    {
      "epoch": 2.7777777777777777,
      "eval_loss": 0.1633986085653305,
      "eval_runtime": 10.056,
      "eval_samples_per_second": 4.177,
      "eval_steps_per_second": 2.088,
      "step": 350
    }
  ],
  "logging_steps": 25,
  "max_steps": 2520,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.120760763166546e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}