End of training

.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_5
+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: 2.0e-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_5/runs/May14_14-13-52_ip-172-16-23-1.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_5
+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_5
+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: 0.01

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: naver-clova-ix/donut-base
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+- wer
+model-index:
+- name: donut_experiment_5
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# donut_experiment_5
+
+This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3987
+- Bleu: 0.0661
+- Precisions: [0.8020833333333334, 0.7375886524822695, 0.6994535519125683, 0.6601941747572816]
+- Brevity Penalty: 0.0915
+- Length Ratio: 0.2948
+- Translation Length: 480
+- Reference Length: 1628
+- Cer: 0.7576
+- Wer: 0.8280
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Precisions                                                                       | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Cer    | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
+| 0.3274        | 1.0   | 253  | 0.4698          | 0.0586 | [0.7707006369426752, 0.6956521739130435, 0.6582633053221288, 0.62]               | 0.0857          | 0.2893       | 471                | 1628             | 0.7660 | 0.8432 |
+| 0.2539        | 2.0   | 506  | 0.4198          | 0.0643 | [0.799163179916318, 0.7315914489311164, 0.6868131868131868, 0.6416938110749185]  | 0.0902          | 0.2936       | 478                | 1628             | 0.7605 | 0.8313 |
+| 0.224         | 3.0   | 759  | 0.3941          | 0.0658 | [0.8075313807531381, 0.7387173396674585, 0.7060439560439561, 0.6710097719869706] | 0.0902          | 0.2936       | 478                | 1628             | 0.7573 | 0.8283 |
+| 0.1566        | 4.0   | 1012 | 0.3987          | 0.0661 | [0.8020833333333334, 0.7375886524822695, 0.6994535519125683, 0.6601941747572816] | 0.0915          | 0.2948       | 480                | 1628             | 0.7576 | 0.8280 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.1.0
+- Datasets 2.18.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "</s_address>": 57532,
+  "</s_company>": 57530,
+  "</s_date>": 57528,
+  "</s_total>": 57526,
+  "<s_address>": 57531,
+  "<s_company>": 57529,
+  "<s_date>": 57527,
+  "<s_iitcdip>": 57523,
+  "<s_synthdog>": 57524,
+  "<s_total>": 57525,
+  "<sep/>": 57522
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.40.0"
+}

metrics.jsonl

@@ -1,3 +1,4 @@
 {"eval_loss": 0.46984946727752686, "eval_bleu": 0.058638588671502775, "eval_precisions": [0.7707006369426752, 0.6956521739130435, 0.6582633053221288, 0.62], "eval_brevity_penalty": 0.08573659052650866, "eval_length_ratio": 0.2893120393120393, "eval_translation_length": 471, "eval_reference_length": 1628, "eval_cer": 0.7660104054123782, "eval_wer": 0.8431764116699929, "eval_runtime": 75.9302, "eval_samples_per_second": 0.751, "eval_steps_per_second": 0.751, "epoch": 1.0}
 {"eval_loss": 0.4197552800178528, "eval_bleu": 0.06425647536525644, "eval_precisions": [0.799163179916318, 0.7315914489311164, 0.6868131868131868, 0.6416938110749185], "eval_brevity_penalty": 0.0901881044262292, "eval_length_ratio": 0.2936117936117936, "eval_translation_length": 478, "eval_reference_length": 1628, "eval_cer": 0.7604681276252823, "eval_wer": 0.8312649598507473, "eval_runtime": 75.4245, "eval_samples_per_second": 0.756, "eval_steps_per_second": 0.756, "epoch": 2.0}
 {"eval_loss": 0.39413073658943176, "eval_bleu": 0.06575803552373187, "eval_precisions": [0.8075313807531381, 0.7387173396674585, 0.7060439560439561, 0.6710097719869706], "eval_brevity_penalty": 0.0901881044262292, "eval_length_ratio": 0.2936117936117936, "eval_translation_length": 478, "eval_reference_length": 1628, "eval_cer": 0.757338139839836, "eval_wer": 0.8282692162386603, "eval_runtime": 75.0128, "eval_samples_per_second": 0.76, "eval_steps_per_second": 0.76, "epoch": 3.0}
+{"eval_loss": 0.39874938130378723, "eval_bleu": 0.06613455502080588, "eval_precisions": [0.8020833333333334, 0.7375886524822695, 0.6994535519125683, 0.6601941747572816], "eval_brevity_penalty": 0.09147709493048638, "eval_length_ratio": 0.29484029484029484, "eval_translation_length": 480, "eval_reference_length": 1628, "eval_cer": 0.7576375295447421, "eval_wer": 0.8280149631962583, "eval_runtime": 75.4844, "eval_samples_per_second": 0.755, "eval_steps_per_second": 0.755, "epoch": 4.0}

preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_thumbnail",
+    "do_align_long_axis",
+    "do_pad",
+    "random_padding",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_align_long_axis": false,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DonutImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": [
+    720,
+    960
+  ]
+}

runs/May14_14-13-52_ip-172-16-23-1.ec2.internal/events.out.tfevents.1715696032.ip-172-16-23-1.ec2.internal.9483.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b5643fea30751143a3ae7226cecbc575c888f251d32abc4b02d6208cbffeb4
-size 12558
+oid sha256:a9061dc95c2de5cbbb5a34d446b653ba2f5061f26bb18564a576b8c654204120
+size 14195

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json

@@ -0,0 +1,123 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,156 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57521": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57522": {
+      "content": "<sep/>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57523": {
+      "content": "<s_iitcdip>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57524": {
+      "content": "<s_synthdog>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57525": {
+      "content": "<s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57526": {
+      "content": "</s_total>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57527": {
+      "content": "<s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57528": {
+      "content": "</s_date>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57529": {
+      "content": "<s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57530": {
+      "content": "</s_company>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57531": {
+      "content": "<s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57532": {
+      "content": "</s_address>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s_total>",
+    "</s_total>",
+    "<s_date>",
+    "</s_date>",
+    "<s_company>",
+    "</s_company>",
+    "<s_address>",
+    "</s_address>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}