Hugging Face's logo

pszemraj
/
long-t5-tglobal-base-16384-booksum-V12

Summarization
Transformers
PyTorch
Safetensors
longt5
text2text-generation
summary
booksum
long-document
long-form
Eval Results
Inference Endpoints
Model card Files Community
10
long-t5-tglobal-base-16384-booksum-V12
File size: 3,786 Bytes 
f702114
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
   "output_dir":"/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-base-16384-booksum-V11-ft25-booksum",
   "overwrite_output_dir":true,
   "do_train":false,
   "do_eval":false,
   "do_predict":false,
   "evaluation_strategy":"no",
   "prediction_loss_only":false,
   "per_device_train_batch_size":2,
   "per_device_eval_batch_size":1,
   "per_gpu_train_batch_size":"None",
   "per_gpu_eval_batch_size":"None",
   "gradient_accumulation_steps":32,
   "eval_accumulation_steps":"None",
   "eval_delay":0,
   "learning_rate":0.001,
   "weight_decay":0,
   "adam_beta1":0.9,
   "adam_beta2":0.999,
   "adam_epsilon":1e-08,
   "max_grad_norm":1,
   "num_train_epochs":1,
   "max_steps":-1,
   "lr_scheduler_type":"constant_with_warmup",
   "warmup_ratio":0.03,
   "warmup_steps":0,
   "log_level":-1,
   "log_level_replica":-1,
   "log_on_each_node":true,
   "logging_dir":"/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-base-16384-booksum-V11-ft25-booksum/logs",
   "logging_strategy":"steps",
   "logging_first_step":false,
   "logging_steps":2,
   "logging_nan_inf_filter":true,
   "save_strategy":"steps",
   "save_steps":25,
   "save_total_limit":1,
   "save_on_each_node":false,
   "no_cuda":false,
   "use_mps_device":false,
   "seed":42,
   "data_seed":"None",
   "jit_mode_eval":false,
   "use_ipex":false,
   "bf16":false,
   "fp16":false,
   "fp16_opt_level":"O1",
   "half_precision_backend":"auto",
   "bf16_full_eval":false,
   "fp16_full_eval":false,
   "tf32":"None",
   "local_rank":0,
   "xpu_backend":"None",
   "tpu_num_cores":"None",
   "tpu_metrics_debug":false,
   "debug":"[]",
   "dataloader_drop_last":false,
   "eval_steps":"None",
   "dataloader_num_workers":0,
   "past_index":-1,
   "run_name":"/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-base-16384-booksum-V11-ft25-booksum",
   "disable_tqdm":false,
   "remove_unused_columns":true,
   "label_names":"None",
   "load_best_model_at_end":false,
   "metric_for_best_model":"None",
   "greater_is_better":"None",
   "ignore_data_skip":false,
   "sharded_ddp":"[]",
   "fsdp":"[]",
   "fsdp_min_num_params":0,
   "fsdp_transformer_layer_cls_to_wrap":"None",
   "deepspeed":"None",
   "label_smoothing_factor":0.0,
   "optim":"adamw_hf",
   "adafactor":false,
   "group_by_length":false,
   "length_column_name":"length",
   "report_to":"['tensorboard']",
   "ddp_find_unused_parameters":"None",
   "ddp_bucket_cap_mb":"None",
   "dataloader_pin_memory":true,
   "skip_memory_metrics":false,
   "use_legacy_prediction_loop":false,
   "push_to_hub":true,
   "resume_from_checkpoint":"None",
   "hub_model_id":"long-t5-tglobal-base-16384-booksum-V11-ft25-booksum",
   "hub_strategy":"end",
   "hub_token":"<HUB_TOKEN>",
   "hub_private_repo":true,
   "gradient_checkpointing":true,
   "include_inputs_for_metrics":false,
   "fp16_backend":"auto",
   "push_to_hub_model_id":"None",
   "push_to_hub_organization":"None",
   "push_to_hub_token":"<PUSH_TO_HUB_TOKEN>",
   "_n_gpu":1,
   "mp_parameters":"",
   "auto_find_batch_size":false,
   "full_determinism":false,
   "torchdynamo":"None",
   "ray_scope":"last",
   "ddp_timeout":1800,
   "sortish_sampler":false,
   "predict_with_generate":false,
   "generation_max_length":"None",
   "generation_num_beams":"None",
   "train_batch_size":2,
   "eval_batch_size":1,
   "configs_src":"long-t5-tglobal-base-16384-booksum-V11-ft25-booksum",
   "use_adam8bit":false,
   "use_adan_optim":false,
   "optim_params":"(Adafactor (\nParameter Group 0\n    beta1: None\n    clip_threshold: 1.0\n    decay_rate: -0.8\n    eps: (1e-30, 0.001)\n    lr: 0.0\n    relative_step: True\n    scale_parameter: True\n    warmup_init: True\n    weight_decay: 0.0\n), <transformers.optimization.AdafactorSchedule object at 0x7f6ab0187890>)"
}