Hugging Face's logo

nour4286
/
ArabartModel

Transformers
TensorBoard
Safetensors
mbart
text2text-generation
Model card Files
xet
Metrics Community
ArabartModel
File size: 3,811 Bytes
6a94eb2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 27.5466,
  "best_model_checkpoint": "/content/drive/MyDrive/ArabartModel/checkpoint-7486",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 7486,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1335826876836762,
      "grad_norm": 3.816420078277588,
      "learning_rate": 4.7773621871938735e-05,
      "loss": 2.0568,
      "step": 500
    },
    {
      "epoch": 0.2671653753673524,
      "grad_norm": 4.217596054077148,
      "learning_rate": 4.554724374387746e-05,
      "loss": 1.949,
      "step": 1000
    },
    {
      "epoch": 0.4007480630510286,
      "grad_norm": 3.4469385147094727,
      "learning_rate": 4.332086561581619e-05,
      "loss": 1.9236,
      "step": 1500
    },
    {
      "epoch": 0.5343307507347048,
      "grad_norm": 3.3545796871185303,
      "learning_rate": 4.1094487487754926e-05,
      "loss": 1.9083,
      "step": 2000
    },
    {
      "epoch": 0.667913438418381,
      "grad_norm": 3.905182361602783,
      "learning_rate": 3.886810935969365e-05,
      "loss": 1.8793,
      "step": 2500
    },
    {
      "epoch": 0.8014961261020572,
      "grad_norm": 3.746492862701416,
      "learning_rate": 3.6641731231632384e-05,
      "loss": 1.8767,
      "step": 3000
    },
    {
      "epoch": 0.9350788137857333,
      "grad_norm": 3.5829365253448486,
      "learning_rate": 3.441535310357111e-05,
      "loss": 1.8613,
      "step": 3500
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4695754051208496,
      "eval_rouge1": 27.3427,
      "eval_rouge2": 11.5623,
      "eval_rougeL": 23.8752,
      "eval_runtime": 854.6158,
      "eval_samples_per_second": 5.487,
      "eval_steps_per_second": 0.549,
      "step": 3743
    },
    {
      "epoch": 1.0686615014694096,
      "grad_norm": 3.6381685733795166,
      "learning_rate": 3.218897497550984e-05,
      "loss": 1.7299,
      "step": 4000
    },
    {
      "epoch": 1.2022441891530857,
      "grad_norm": 3.850755453109741,
      "learning_rate": 2.9962596847448572e-05,
      "loss": 1.6235,
      "step": 4500
    },
    {
      "epoch": 1.3358268768367618,
      "grad_norm": 3.5649123191833496,
      "learning_rate": 2.77362187193873e-05,
      "loss": 1.6276,
      "step": 5000
    },
    {
      "epoch": 1.4694095645204381,
      "grad_norm": 3.684051036834717,
      "learning_rate": 2.5509840591326034e-05,
      "loss": 1.635,
      "step": 5500
    },
    {
      "epoch": 1.6029922522041145,
      "grad_norm": 3.216923236846924,
      "learning_rate": 2.3283462463264763e-05,
      "loss": 1.6329,
      "step": 6000
    },
    {
      "epoch": 1.7365749398877905,
      "grad_norm": 3.666384220123291,
      "learning_rate": 2.1057084335203492e-05,
      "loss": 1.628,
      "step": 6500
    },
    {
      "epoch": 1.8701576275714666,
      "grad_norm": 3.5083119869232178,
      "learning_rate": 1.883070620714222e-05,
      "loss": 1.619,
      "step": 7000
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.552595376968384,
      "eval_rouge1": 27.5466,
      "eval_rouge2": 11.7619,
      "eval_rougeL": 24.0393,
      "eval_runtime": 855.3721,
      "eval_samples_per_second": 5.482,
      "eval_steps_per_second": 0.548,
      "step": 7486
    }
  ],
  "logging_steps": 500,
  "max_steps": 11229,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.390892214460416e+16,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}