Hugging Face's logo

shahbakhsh
/
BalBERT

Fill-Mask
Transformers
Safetensors
PyTorch
Baluchi
xlm-roberta
balochi
low-resource
masked-language-modeling
domain-adaptive-pretraining
Eval Results (legacy)
Model card Files
xet
 Community
BalBERT
File size: 3,455 Bytes
25fe21f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "output_dir": "/kaggle/working/BalBERT/checkpoints",
  "per_device_train_batch_size": 16,
  "num_train_epochs": 10,
  "max_steps": -1,
  "learning_rate": 5e-05,
  "lr_scheduler_type": "linear",
  "lr_scheduler_kwargs": null,
  "warmup_steps": 0.06,
  "optim": "adamw_torch_fused",
  "optim_args": null,
  "weight_decay": 0.05,
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "adam_epsilon": 1e-08,
  "optim_target_modules": null,
  "gradient_accumulation_steps": 2,
  "average_tokens_across_devices": true,
  "max_grad_norm": 1.0,
  "label_smoothing_factor": 0.0,
  "bf16": true,
  "fp16": false,
  "bf16_full_eval": false,
  "fp16_full_eval": false,
  "tf32": null,
  "gradient_checkpointing": false,
  "gradient_checkpointing_kwargs": null,
  "torch_compile": false,
  "torch_compile_backend": null,
  "torch_compile_mode": null,
  "use_liger_kernel": false,
  "liger_kernel_config": null,
  "use_cache": false,
  "neftune_noise_alpha": null,
  "torch_empty_cache_steps": null,
  "auto_find_batch_size": false,
  "logging_strategy": "steps",
  "logging_steps": 50,
  "logging_first_step": false,
  "log_on_each_node": true,
  "logging_nan_inf_filter": true,
  "include_num_input_tokens_seen": "no",
  "log_level": "passive",
  "log_level_replica": "warning",
  "disable_tqdm": false,
  "report_to": [
    "tensorboard"
  ],
  "run_name": null,
  "project": "huggingface",
  "trackio_space_id": null,
  "trackio_bucket_id": null,
  "trackio_static_space_id": null,
  "eval_strategy": "steps",
  "eval_steps": 200,
  "eval_delay": 0,
  "per_device_eval_batch_size": 16,
  "prediction_loss_only": false,
  "eval_on_start": false,
  "eval_do_concat_batches": true,
  "eval_use_gather_object": false,
  "eval_accumulation_steps": null,
  "include_for_metrics": [],
  "batch_eval_metrics": false,
  "save_only_model": false,
  "save_strategy": "steps",
  "save_steps": 200,
  "save_on_each_node": false,
  "save_total_limit": 3,
  "enable_jit_checkpoint": false,
  "push_to_hub": false,
  "hub_token": "<HUB_TOKEN>",
  "hub_private_repo": null,
  "hub_model_id": null,
  "hub_strategy": "every_save",
  "hub_always_push": false,
  "hub_revision": null,
  "load_best_model_at_end": true,
  "metric_for_best_model": "eval_loss",
  "greater_is_better": false,
  "ignore_data_skip": false,
  "restore_callback_states_from_checkpoint": false,
  "full_determinism": false,
  "seed": 42,
  "data_seed": null,
  "use_cpu": false,
  "accelerator_config": {
    "split_batches": false,
    "dispatch_batches": null,
    "even_batches": true,
    "use_seedable_sampler": true,
    "non_blocking": false,
    "gradient_accumulation_kwargs": null
  },
  "parallelism_config": null,
  "dataloader_drop_last": false,
  "dataloader_num_workers": 2,
  "dataloader_pin_memory": true,
  "dataloader_persistent_workers": false,
  "dataloader_prefetch_factor": null,
  "remove_unused_columns": true,
  "label_names": null,
  "train_sampling_strategy": "random",
  "length_column_name": "length",
  "ddp_find_unused_parameters": null,
  "ddp_bucket_cap_mb": null,
  "ddp_broadcast_buffers": null,
  "ddp_static_graph": null,
  "ddp_backend": null,
  "ddp_timeout": 1800,
  "fsdp": null,
  "fsdp_config": null,
  "deepspeed": null,
  "debug": [],
  "skip_memory_metrics": true,
  "do_train": false,
  "do_eval": true,
  "do_predict": false,
  "resume_from_checkpoint": null,
  "warmup_ratio": 0.06,
  "logging_dir": "/kaggle/working/BalBERT/tensorboard_logs",
  "local_rank": -1
}