Hugging Face's logo

harsh580g
/
BART_Layman

Safetensors
bart
Model card Files
xet
 Community
BART_Layman
File size: 4,476 Bytes
e7d1b5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 1.693805456161499,
  "best_model_checkpoint": "./BART/checkpoint-3080",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 3080,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.8580667972564697,
      "eval_rouge1": 15.4451,
      "eval_rouge2": 7.2478,
      "eval_rougeL": 13.17,
      "eval_rougeLsum": 14.0774,
      "eval_runtime": 9.1697,
      "eval_samples_per_second": 10.905,
      "eval_steps_per_second": 0.763,
      "step": 440
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 3.0643959045410156,
      "learning_rate": 1.9843637462342498e-05,
      "loss": 1.9394,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.7797517776489258,
      "eval_rouge1": 15.3282,
      "eval_rouge2": 7.1147,
      "eval_rougeL": 13.0747,
      "eval_rougeLsum": 14.2107,
      "eval_runtime": 9.0361,
      "eval_samples_per_second": 11.067,
      "eval_steps_per_second": 0.775,
      "step": 880
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 5.788974761962891,
      "learning_rate": 1.937447803209855e-05,
      "loss": 1.6636,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.7304754257202148,
      "eval_rouge1": 15.6545,
      "eval_rouge2": 6.9151,
      "eval_rougeL": 13.0932,
      "eval_rougeLsum": 14.3822,
      "eval_runtime": 9.2209,
      "eval_samples_per_second": 10.845,
      "eval_steps_per_second": 0.759,
      "step": 1320
    },
    {
      "epoch": 3.409090909090909,
      "grad_norm": 3.81870698928833,
      "learning_rate": 1.860742027003944e-05,
      "loss": 1.5132,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.7133750915527344,
      "eval_rouge1": 16.2201,
      "eval_rouge2": 8.0653,
      "eval_rougeL": 14.0536,
      "eval_rougeLsum": 15.088,
      "eval_runtime": 7.0109,
      "eval_samples_per_second": 14.264,
      "eval_steps_per_second": 0.998,
      "step": 1760
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 2.5344793796539307,
      "learning_rate": 1.756683942425267e-05,
      "loss": 1.404,
      "step": 2000
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.7092199325561523,
      "eval_rouge1": 16.1558,
      "eval_rouge2": 7.4414,
      "eval_rougeL": 13.6423,
      "eval_rougeLsum": 14.6771,
      "eval_runtime": 7.0032,
      "eval_samples_per_second": 14.279,
      "eval_steps_per_second": 1.0,
      "step": 2200
    },
    {
      "epoch": 5.681818181818182,
      "grad_norm": 2.570192575454712,
      "learning_rate": 1.6285802647599156e-05,
      "loss": 1.3153,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.6954882144927979,
      "eval_rouge1": 15.8485,
      "eval_rouge2": 7.8577,
      "eval_rougeL": 13.518,
      "eval_rougeLsum": 14.7491,
      "eval_runtime": 6.9893,
      "eval_samples_per_second": 14.308,
      "eval_steps_per_second": 1.002,
      "step": 2640
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 2.7792255878448486,
      "learning_rate": 1.4805018203243235e-05,
      "loss": 1.2473,
      "step": 3000
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 21.0,
      "eval_loss": 1.693805456161499,
      "eval_rouge1": 17.0591,
      "eval_rouge2": 8.3853,
      "eval_rougeL": 14.3266,
      "eval_rougeLsum": 15.6269,
      "eval_runtime": 6.9975,
      "eval_samples_per_second": 14.291,
      "eval_steps_per_second": 1.0,
      "step": 3080
    }
  ],
  "logging_steps": 500,
  "max_steps": 8800,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0664321746993152e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}