Hugging Face's logo

TRnlp
/
bart-base-Abstract-Title-CSPubSum

Transformers
Safetensors
bart
text2text-generation
Model card Files
xet
Community
bart-base-Abstract-Title-CSPubSum
File size: 2,357 Bytes 
0027423
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 46.9335,
  "best_model_checkpoint": "Models/bart-base-Abstract-Title/checkpoint-508",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 508,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3937007874015748,
      "grad_norm": 7.6463422775268555,
      "learning_rate": 3.697637795275591e-05,
      "loss": 3.0716,
      "step": 100
    },
    {
      "epoch": 0.7874015748031497,
      "grad_norm": 4.727579116821289,
      "learning_rate": 3.3826771653543314e-05,
      "loss": 1.9716,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 17.1893,
      "eval_loss": 1.94315505027771,
      "eval_rouge1": 46.7551,
      "eval_rouge2": 26.2207,
      "eval_rougeL": 40.5839,
      "eval_rougeLsum": 40.5779,
      "eval_runtime": 33.994,
      "eval_samples_per_second": 29.829,
      "eval_steps_per_second": 0.941,
      "step": 254
    },
    {
      "epoch": 1.1811023622047245,
      "grad_norm": 4.367326736450195,
      "learning_rate": 3.067716535433071e-05,
      "loss": 1.7492,
      "step": 300
    },
    {
      "epoch": 1.574803149606299,
      "grad_norm": 4.451642990112305,
      "learning_rate": 2.7527559055118113e-05,
      "loss": 1.6464,
      "step": 400
    },
    {
      "epoch": 1.968503937007874,
      "grad_norm": 4.022191047668457,
      "learning_rate": 2.4377952755905516e-05,
      "loss": 1.642,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 16.0178,
      "eval_loss": 1.8481199741363525,
      "eval_rouge1": 46.9335,
      "eval_rouge2": 26.4562,
      "eval_rougeL": 41.1114,
      "eval_rougeLsum": 41.1786,
      "eval_runtime": 33.2681,
      "eval_samples_per_second": 30.48,
      "eval_steps_per_second": 0.962,
      "step": 508
    }
  ],
  "logging_steps": 100,
  "max_steps": 1270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4951060040908800.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}