Training in progress, epoch 2

donut_experiment_bayesian_trial_0/.ipynb_checkpoints/hyperparameters-checkpoint.yaml

@@ -0,0 +1,160 @@
+__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_1
+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: 3.476033118766737e-05
+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_1/runs/May20_16-34-26_ip-172-16-167-107.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: 2
+optim: !!python/object/apply:transformers.training_args.OptimizerNames
+- adamw_torch
+optim_args: null
+optim_target_modules: null
+output_dir: model_runs/donut_experiment_bayesian_1
+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_1
+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: 0.001930584169502962

donut_experiment_bayesian_trial_0/.ipynb_checkpoints/metrics-checkpoint.jsonl

@@ -0,0 +1 @@
+{"eval_loss": 0.43816685676574707, "eval_bleu": 0.06408670006728434, "eval_precisions": [0.8294243070362474, 0.7742718446601942, 0.7352112676056338, 0.7013422818791947], "eval_brevity_penalty": 0.0844821210838816, "eval_length_ratio": 0.2880835380835381, "eval_translation_length": 469, "eval_reference_length": 1628, "eval_cer": 0.7588007367632248, "eval_wer": 0.8260088637359255, "eval_runtime": 72.3994, "eval_samples_per_second": 0.787, "eval_steps_per_second": 0.787, "epoch": 1.0}

donut_experiment_bayesian_trial_0/metrics.jsonl

@@ -1 +1,2 @@
 {"eval_loss": 0.43816685676574707, "eval_bleu": 0.06408670006728434, "eval_precisions": [0.8294243070362474, 0.7742718446601942, 0.7352112676056338, 0.7013422818791947], "eval_brevity_penalty": 0.0844821210838816, "eval_length_ratio": 0.2880835380835381, "eval_translation_length": 469, "eval_reference_length": 1628, "eval_cer": 0.7588007367632248, "eval_wer": 0.8260088637359255, "eval_runtime": 72.3994, "eval_samples_per_second": 0.787, "eval_steps_per_second": 0.787, "epoch": 1.0}
+{"eval_loss": 0.4537677764892578, "eval_bleu": 0.06656125232590335, "eval_precisions": [0.8336842105263158, 0.7751196172248804, 0.7313019390581718, 0.6842105263157895], "eval_brevity_penalty": 0.08826881356184386, "eval_length_ratio": 0.2917690417690418, "eval_translation_length": 475, "eval_reference_length": 1628, "eval_cer": 0.7502191876462136, "eval_wer": 0.8199087588657978, "eval_runtime": 71.9659, "eval_samples_per_second": 0.792, "eval_steps_per_second": 0.792, "epoch": 2.0}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0f156c3750a8cfde01721752878c36cc36127c43ad7ed590a15b6e5bb0a67d
+oid sha256:0a1c11c560b2d37406f92ae4ac062575bdea9eeb145205dc3b486d7684c251fd
 size 809103512

runs/May20_16-34-26_ip-172-16-167-107.ec2.internal/events.out.tfevents.1716222867.ip-172-16-167-107.ec2.internal.15611.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d8365c727c579b2e90538a00196cd2a23ff9cec2ac53071871b61fff21e660
-size 10274
+oid sha256:374a85d7394806b709b0c20575f7371ec81cba471d17cab038d7668bcaa7b6c1
+size 11911