File size: 9,286 Bytes
e86707e dce605a dc59786 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
12/14/2022 11:27:46 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True
12/14/2022 11:27:46 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=True,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=1000,
evaluation_strategy=steps,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_max_length=225,
generation_num_beams=None,
gradient_accumulation_steps=1,
gradient_checkpointing=True,
greater_is_better=False,
group_by_length=False,
half_precision_backend=auto,
hub_model_id=ales/whisper-small-belarusian,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=True,
include_inputs_for_metrics=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=0.0001,
length_column_name=length,
load_best_model_at_end=True,
local_rank=-1,
log_level=passive,
log_level_replica=passive,
log_on_each_node=True,
logging_dir=./runs/Dec14_11-27-46_129-213-88-66,
logging_first_step=True,
logging_nan_inf_filter=True,
logging_steps=50,
logging_strategy=steps,
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=12000,
metric_for_best_model=wer,
mp_parameters=,
no_cuda=False,
num_train_epochs=3.0,
optim=adamw_hf,
optim_args=None,
output_dir=./,
overwrite_output_dir=False,
past_index=-1,
per_device_eval_batch_size=64,
per_device_train_batch_size=64,
predict_with_generate=True,
prediction_loss_only=False,
push_to_hub=True,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=./,
save_on_each_node=False,
save_steps=1000,
save_strategy=steps,
save_total_limit=None,
seed=42,
sharded_ddp=[],
skip_memory_metrics=True,
sortish_sampler=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=500,
weight_decay=0.0,
xpu_backend=None,
)
12/14/2022 11:27:46 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=True,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=1000,
evaluation_strategy=steps,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_max_length=225,
generation_num_beams=None,
gradient_accumulation_steps=1,
gradient_checkpointing=True,
greater_is_better=False,
group_by_length=False,
half_precision_backend=auto,
hub_model_id=ales/whisper-small-belarusian,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=True,
include_inputs_for_metrics=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=0.0001,
length_column_name=length,
load_best_model_at_end=True,
local_rank=-1,
log_level=passive,
log_level_replica=passive,
log_on_each_node=True,
logging_dir=./runs/Dec14_11-27-46_129-213-88-66,
logging_first_step=True,
logging_nan_inf_filter=True,
logging_steps=50,
logging_strategy=steps,
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=12000,
metric_for_best_model=wer,
mp_parameters=,
no_cuda=False,
num_train_epochs=3.0,
optim=adamw_hf,
optim_args=None,
output_dir=./,
overwrite_output_dir=False,
past_index=-1,
per_device_eval_batch_size=64,
per_device_train_batch_size=64,
predict_with_generate=True,
prediction_loss_only=False,
push_to_hub=True,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=./,
save_on_each_node=False,
save_steps=1000,
save_strategy=steps,
save_total_limit=None,
seed=42,
sharded_ddp=[],
skip_memory_metrics=True,
sortish_sampler=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=500,
weight_decay=0.0,
xpu_backend=None,
)
12/14/2022 11:27:46 - INFO - __main__ - output_dir already exists. will try to load last checkpoint.
12/14/2022 11:27:46 - INFO - __main__ - last_checkpoint is None. will try to read from training_args.resume_from_checkpoint
12/14/2022 11:27:46 - INFO - __main__ - last_checkpoint is None. resume_from_checkpoint is either None or not existing dir. will try to read from the model saved in the root of output_dir.
12/14/2022 11:27:46 - INFO - __main__ - dir is not empty, but contains only: ['src', '.gitattributes', '.git', 'train_run_1.log', 'train_20221214-112746.log']. it is OK - will start training
12/14/2022 11:27:46 - INFO - datasets.info - Loading Dataset Infos from /home/ubuntu/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/14/2022 11:27:47 - INFO - datasets.info - Loading Dataset Infos from /home/ubuntu/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/14/2022 11:28:05 - WARNING - huggingface_hub.repository - /home/ubuntu/whisper-small-belarusian/./ is already a clone of https://huggingface.co/ales/whisper-small-belarusian. Make sure you pull the latest changes with `repo.git_pull()`.
12/15/2022 17:58:42 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20]
12/15/2022 18:01:33 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20]
12/15/2022 18:01:48 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [2/20]
12/15/2022 18:02:03 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [3/20]
12/15/2022 18:02:18 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [4/20]
12/15/2022 18:02:33 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [5/20]
12/15/2022 18:02:48 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [6/20]
12/15/2022 18:03:03 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [7/20]
12/15/2022 18:03:18 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [8/20]
12/15/2022 18:03:33 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [9/20]
12/15/2022 18:03:48 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [10/20]
12/15/2022 18:04:03 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [11/20]
12/15/2022 18:04:18 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [12/20]
12/15/2022 18:04:33 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [13/20]
12/15/2022 18:04:38 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [14/20]
12/15/2022 18:04:43 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [15/20]
12/16/2022 19:47:58 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
12/16/2022 19:47:58 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
12/16/2022 19:48:02 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...
remote: LFS file scan complete.
To https://huggingface.co/ales/whisper-small-belarusian
72e5d42..1d54c35 main -> main
|