Training in progress, epoch 1

config.json

@@ -0,0 +1,192 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 4,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 512,
+    "max_position_embeddings": 1536,
+    "min_length": 0,
+    "model_type": "mbart",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 57533
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      960,
+      720
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 10
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0"
+}

donut_experiment_bayesian_trial_0/hyperparameters.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/metrics.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}

hyperparameters_tuned.json

@@ -0,0 +1 @@
+{"learning_rate": {"type": "loguniform", "low": 1e-05, "high": 0.0002}, "weight_decay": {"type": "loguniform", "low": 0.001, "high": 0.1}, "num_train_epochs": {"type": "int", "low": 2, "high": 5}}

model.safetensors

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d8365c727c579b2e90538a00196cd2a23ff9cec2ac53071871b61fff21e660
+size 10274

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8f76e2abd36bd7382aa347681f01dc3e4858ffd1bd6255bdbdb7630ede45845
+size 5240