File size: 4,255 Bytes
a24b1a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
__cached__setup_devices: !!python/object/apply:torch.device
- cuda
- 0
_n_gpu: 1
accelerator_config: !!python/object:transformers.trainer_pt_utils.AcceleratorConfig
  dispatch_batches: null
  even_batches: true
  gradient_accumulation_kwargs: null
  split_batches: false
  use_seedable_sampler: true
adafactor: false
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1.0e-08
auto_find_batch_size: false
bf16: false
bf16_full_eval: false
data_seed: null
dataloader_drop_last: false
dataloader_num_workers: 0
dataloader_persistent_workers: false
dataloader_pin_memory: true
dataloader_prefetch_factor: null
ddp_backend: null
ddp_broadcast_buffers: null
ddp_bucket_cap_mb: null
ddp_find_unused_parameters: null
ddp_timeout: 1800
debug: []
deepspeed: null
deepspeed_plugin: null
disable_tqdm: false
dispatch_batches: null
distributed_state: !!python/object:accelerate.state.PartialState
  _cpu: false
  backend: null
  debug: false
  device: !!python/object/apply:torch.device
  - cuda
  distributed_type: !!python/object/apply:accelerate.utils.dataclasses.DistributedType
  - 'NO'
  fork_launched: false
  local_process_index: 0
  num_processes: 1
  process_index: 0
do_eval: true
do_predict: false
do_train: false
eval_accumulation_steps: null
eval_delay: 0
eval_do_concat_batches: true
eval_steps: null
evaluation_strategy: !!python/object/apply:transformers.trainer_utils.IntervalStrategy
- epoch
fp16: true
fp16_backend: auto
fp16_full_eval: false
fp16_opt_level: O1
fsdp: []
fsdp_config:
  min_num_params: 0
  xla: false
  xla_fsdp_grad_ckpt: false
  xla_fsdp_v2: false
fsdp_min_num_params: 0
fsdp_transformer_layer_cls_to_wrap: null
full_determinism: false
generation_config: null
generation_max_length: null
generation_num_beams: null
gradient_accumulation_steps: 2
gradient_checkpointing: false
gradient_checkpointing_kwargs: null
greater_is_better: false
group_by_length: false
half_precision_backend: auto
hub_always_push: false
hub_model_id: donut_experiment_bayesian_trial_16
hub_private_repo: false
hub_strategy: !!python/object/apply:transformers.trainer_utils.HubStrategy
- every_save
hub_token: null
ignore_data_skip: false
include_inputs_for_metrics: false
include_num_input_tokens_seen: false
include_tokens_per_second: false
jit_mode_eval: false
label_names: null
label_smoothing_factor: 0.0
learning_rate: 0.00011219603369833024
length_column_name: length
load_best_model_at_end: true
local_rank: 0
log_level: passive
log_level_replica: warning
log_on_each_node: true
logging_dir: model_runs/donut_experiment_bayesian_trial_16/runs/Jun26_17-50-12_ip-172-16-186-191.ec2.internal
logging_first_step: false
logging_nan_inf_filter: true
logging_steps: 100
logging_strategy: !!python/object/apply:transformers.trainer_utils.IntervalStrategy
- steps
lr_scheduler_kwargs: {}
lr_scheduler_type: !!python/object/apply:transformers.trainer_utils.SchedulerType
- linear
max_grad_norm: 1.0
max_steps: -1
metric_for_best_model: loss
mp_parameters: ''
neftune_noise_alpha: null
no_cuda: false
num_train_epochs: 4
optim: !!python/object/apply:transformers.training_args.OptimizerNames
- adamw_torch
optim_args: null
optim_target_modules: null
output_dir: model_runs/donut_experiment_bayesian_trial_16
overwrite_output_dir: false
past_index: -1
per_device_eval_batch_size: 1
per_device_train_batch_size: 1
per_gpu_eval_batch_size: null
per_gpu_train_batch_size: null
predict_with_generate: true
prediction_loss_only: false
push_to_hub: true
push_to_hub_model_id: null
push_to_hub_organization: null
push_to_hub_token: null
ray_scope: last
remove_unused_columns: true
report_to:
- tensorboard
resume_from_checkpoint: null
run_name: model_runs/donut_experiment_bayesian_trial_16
save_on_each_node: false
save_only_model: false
save_safetensors: true
save_steps: 500
save_strategy: !!python/object/apply:transformers.trainer_utils.IntervalStrategy
- epoch
save_total_limit: 2
seed: 42
skip_memory_metrics: true
sortish_sampler: false
split_batches: null
tf32: null
torch_compile: false
torch_compile_backend: null
torch_compile_mode: null
torchdynamo: null
tpu_metrics_debug: false
tpu_num_cores: null
use_cpu: false
use_ipex: false
use_legacy_prediction_loop: false
use_mps_device: false
warmup_ratio: 0.0
warmup_steps: 0
weight_decay: 0.0032416433125036837