Hugging Face's logo

nour4286
/
ArabartModel

Text2Text Generation
Transformers
TensorBoard
Safetensors
mbart
Inference Endpoints
Model card Files Metrics Community
ArabartModel
File size: 4,010 Bytes 
d1576f7
f5574c8
 
 
d1576f7
f5574c8
d1576f7
 
 
 
 
 
2b2ee02
 
 
d1576f7
 
 
 
2b2ee02
 
 
d1576f7
 
 
 
2b2ee02
 
 
d1576f7
 
 
 
2b2ee02
 
 
 
 
 
 
d1576f7
d86cffb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ff4859
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f5574c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d1576f7
 
 
2b2ee02
d1576f7
2b2ee02
d1576f7
 
 
 
 
 
 
 
f5574c8
d1576f7
 
 
 
f5574c8
d1576f7
 
 
 
 
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
 
{
  "best_metric": 26.4112,
  "best_model_checkpoint": "my-model/checkpoint-6112",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 6112,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32722513089005234,
      "grad_norm": 1.6467379331588745,
      "learning_rate": 4.5909685863874345e-05,
      "loss": 0.0168,
      "step": 500
    },
    {
      "epoch": 0.6544502617801047,
      "grad_norm": 1.3730037212371826,
      "learning_rate": 4.181937172774869e-05,
      "loss": 0.0246,
      "step": 1000
    },
    {
      "epoch": 0.981675392670157,
      "grad_norm": 1.1599562168121338,
      "learning_rate": 3.7729057591623044e-05,
      "loss": 0.0308,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_loss": 5.495022296905518,
      "eval_rouge1": 24.8013,
      "eval_rouge2": 9.5895,
      "eval_rougeL": 21.5936,
      "eval_runtime": 434.7617,
      "eval_samples_per_second": 5.049,
      "eval_steps_per_second": 0.506,
      "step": 1528
    },
    {
      "epoch": 1.3089005235602094,
      "grad_norm": 3.42366361618042,
      "learning_rate": 3.3638743455497386e-05,
      "loss": 0.0539,
      "step": 2000
    },
    {
      "epoch": 1.6361256544502618,
      "grad_norm": 3.776289701461792,
      "learning_rate": 2.954842931937173e-05,
      "loss": 0.0727,
      "step": 2500
    },
    {
      "epoch": 1.9633507853403143,
      "grad_norm": 5.072182655334473,
      "learning_rate": 2.545811518324607e-05,
      "loss": 0.1352,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_loss": 5.219298839569092,
      "eval_rouge1": 24.8743,
      "eval_rouge2": 9.8439,
      "eval_rougeL": 21.6411,
      "eval_runtime": 433.0859,
      "eval_samples_per_second": 5.068,
      "eval_steps_per_second": 0.508,
      "step": 3056
    },
    {
      "epoch": 2.2905759162303667,
      "grad_norm": 6.1271209716796875,
      "learning_rate": 2.136780104712042e-05,
      "loss": 0.4727,
      "step": 3500
    },
    {
      "epoch": 2.6178010471204187,
      "grad_norm": 5.5732316970825195,
      "learning_rate": 1.7277486910994763e-05,
      "loss": 0.6959,
      "step": 4000
    },
    {
      "epoch": 2.945026178010471,
      "grad_norm": 5.73837423324585,
      "learning_rate": 1.3187172774869111e-05,
      "loss": 0.9382,
      "step": 4500
    },
    {
      "epoch": 3.0,
      "eval_loss": 3.44022798538208,
      "eval_rouge1": 26.0341,
      "eval_rouge2": 10.6222,
      "eval_rougeL": 22.7685,
      "eval_runtime": 417.9997,
      "eval_samples_per_second": 5.251,
      "eval_steps_per_second": 0.526,
      "step": 4584
    },
    {
      "epoch": 3.2722513089005236,
      "grad_norm": 5.353453159332275,
      "learning_rate": 9.096858638743457e-06,
      "loss": 0.9969,
      "step": 5000
    },
    {
      "epoch": 3.599476439790576,
      "grad_norm": 5.323329925537109,
      "learning_rate": 5.006544502617801e-06,
      "loss": 1.0924,
      "step": 5500
    },
    {
      "epoch": 3.9267015706806285,
      "grad_norm": 6.1474175453186035,
      "learning_rate": 9.162303664921465e-07,
      "loss": 1.2208,
      "step": 6000
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.21282958984375,
      "eval_rouge1": 26.4112,
      "eval_rouge2": 10.9605,
      "eval_rougeL": 23.0258,
      "eval_runtime": 417.2936,
      "eval_samples_per_second": 5.26,
      "eval_steps_per_second": 0.527,
      "step": 6112
    }
  ],
  "logging_steps": 500,
  "max_steps": 6112,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.930549272296653e+16,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}