Spaces:

kingabzpro
/

Urdu-ASR-SOTA

Sleeping

App Files Files Community

Abid commited on Mar 17, 2022

Commit

de1a0f3

•

1 Parent(s): 5a7ca9f

Sota Results

Browse files

Files changed (3) hide show

metrics.csv +6 -13
notebook.ipynb +0 -0
params.yml +88 -89

metrics.csv CHANGED Viewed

@@ -1,14 +1,7 @@
 Name,Value,Timestamp,Step
-train_runtime,1310.619,1646910000000,1
-train_samples_per_second,0.618,1646910000000,1
-train_steps_per_second,0.019,1646910000000,1
-total_flos,1.03E+17,1646910000000,1
-train_loss,0.6416,1646910000000,1
-epoch,184.62,1646910000000,1
-eval_loss,0.9889,1646910000000,1
-eval_wer,0.5607,1646910000000,1
-eval_cer,0.237,1646910000000,1
-eval_runtime,119.2739,1646910000000,1
-eval_samples_per_second,2.859,1646910000000,1
-eval_steps_per_second,0.361,1646910000000,1
-epoch,184.62,1646910000000,1

 Name,Value,Timestamp,Step
+"epoch",184.62,1647505277782,1
+"eval_cer",0.237,1647505277782,1
+"eval_wer",0.5607,1647505277782,1
+"Steps",2400,1647505277782,1
+"eval_loss",0.9889,1647505277782,1
+"loss",0.6416,1647505277782,1

notebook.ipynb CHANGED Viewed

The diff for this file is too large to render. See raw diff

params.yml CHANGED Viewed

@@ -1,89 +1,88 @@
-model: facebook/wav2vec2-xls-r-300m
-trainer:
-  _n_gpu: 1
-  adafactor: false
-  adam_beta1: 0.9
-  adam_beta2: 0.999
-  adam_epsilon: 1.0e-08
-  bf16: false
-  bf16_full_eval: false
-  dataloader_drop_last: false
-  dataloader_num_workers: 0
-  dataloader_pin_memory: true
-  ddp_bucket_cap_mb: null
-  ddp_find_unused_parameters: null
-  debug: '[]'
-  deepspeed: null
-  disable_tqdm: false
-  do_eval: true
-  do_predict: false
-  do_train: false
-  eval_accumulation_steps: null
-  eval_steps: 500
-  evaluation_strategy: steps
-  fp16: true
-  fp16_backend: auto
-  fp16_full_eval: false
-  fp16_opt_level: O1
-  gradient_accumulation_steps: 2
-  gradient_checkpointing: true
-  greater_is_better: null
-  group_by_length: true
-  half_precision_backend: amp
-  hub_model_id: null
-  hub_strategy: every_save
-  hub_token: <HUB_TOKEN>
-  ignore_data_skip: false
-  label_names: null
-  label_smoothing_factor: 0.0
-  learning_rate: 0.0001
-  length_column_name: length
-  load_best_model_at_end: false
-  local_rank: -1
-  log_level: -1
-  log_level_replica: -1
-  log_on_each_node: true
-  logging_dir: wav2vec2-large-xls-r-300m-Urdu-CV8/runs/Mar10_09-33-33_c7ab98cbc2d3
-  logging_first_step: false
-  logging_nan_inf_filter: true
-  logging_steps: 500
-  logging_strategy: steps
-  lr_scheduler_type: linear
-  max_grad_norm: 1.0
-  max_steps: -1
-  metric_for_best_model: null
-  mp_parameters: ''
-  no_cuda: false
-  num_train_epochs: 200
-  optim: adamw_hf
-  output_dir: wav2vec2-large-xls-r-300m-Urdu-CV8
-  overwrite_output_dir: false
-  past_index: -1
-  per_device_eval_batch_size: 8
-  per_device_train_batch_size: 32
-  per_gpu_eval_batch_size: null
-  per_gpu_train_batch_size: null
-  prediction_loss_only: false
-  push_to_hub: true
-  push_to_hub_model_id: null
-  push_to_hub_organization: null
-  push_to_hub_token: <PUSH_TO_HUB_TOKEN>
-  remove_unused_columns: true
-  report_to: '[''mlflow'', ''tensorboard'']'
-  resume_from_checkpoint: null
-  run_name: wav2vec2-large-xls-r-300m-Urdu-CV8
-  save_on_each_node: false
-  save_steps: 500
-  save_strategy: steps
-  save_total_limit: 1
-  seed: 42
-  sharded_ddp: '[]'
-  skip_memory_metrics: true
-  tf32: null
-  tpu_metrics_debug: false
-  tpu_num_cores: null
-  use_legacy_prediction_loop: false
-  warmup_ratio: 0.0
-  warmup_steps: 10
-  weight_decay: 0.0
-  xpu_backend: null

+_n_gpu: 1
+adafactor: false
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+bf16: false
+bf16_full_eval: false
+dataloader_drop_last: false
+dataloader_num_workers: 0
+dataloader_pin_memory: true
+ddp_bucket_cap_mb: null
+ddp_find_unused_parameters: null
+debug: '[]'
+deepspeed: null
+disable_tqdm: false
+do_eval: true
+do_predict: false
+do_train: false
+eval_accumulation_steps: null
+eval_steps: 400
+evaluation_strategy: steps
+fp16: true
+fp16_backend: auto
+fp16_full_eval: false
+fp16_opt_level: O1
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+greater_is_better: null
+group_by_length: true
+half_precision_backend: amp
+hub_model_id: null
+hub_strategy: every_save
+hub_token: <HUB_TOKEN>
+ignore_data_skip: false
+label_names: null
+label_smoothing_factor: 0.0
+learning_rate: 0.0001
+length_column_name: length
+load_best_model_at_end: false
+local_rank: -1
+log_level: -1
+log_level_replica: -1
+log_on_each_node: true
+logging_dir: Model/runs/Mar17_07-52-06_7da6d8561539
+logging_first_step: false
+logging_nan_inf_filter: true
+logging_steps: 400
+logging_strategy: steps
+lr_scheduler_type: linear
+max_grad_norm: 1.0
+max_steps: -1
+metric_for_best_model: null
+model_class: wav2vec2-xls-r-300m
+mp_parameters: ''
+no_cuda: false
+num_train_epochs: 200
+optim: adamw_hf
+output_dir: Model
+overwrite_output_dir: false
+past_index: -1
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 32
+per_gpu_eval_batch_size: null
+per_gpu_train_batch_size: null
+prediction_loss_only: false
+push_to_hub: false
+push_to_hub_model_id: null
+push_to_hub_organization: null
+push_to_hub_token: <PUSH_TO_HUB_TOKEN>
+remove_unused_columns: true
+report_to: '[''mlflow'', ''tensorboard'']'
+resume_from_checkpoint: null
+run_name: Model
+save_on_each_node: false
+save_steps: 400
+save_strategy: steps
+save_total_limit: 2
+seed: 42
+sharded_ddp: '[]'
+skip_memory_metrics: true
+tf32: null
+tpu_metrics_debug: false
+tpu_num_cores: null
+use_legacy_prediction_loop: false
+warmup_ratio: 0.0
+warmup_steps: 1000
+weight_decay: 0.0
+xpu_backend: null