Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,184 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "bert-base-uncased",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "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,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "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": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "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,
+    "transformers_version": "4.26.1",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "decoder_start_token_id": 101,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "bert-base-uncased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "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,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "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": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "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,
+    "transformers_version": "4.26.1",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "eos_token_id": 102,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 128,
+  "min_length": 56,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8399abb99bf2be1de125a4695450f09d3429460d349b5c1bac5d8fd6814c3a3
+size 989644857

runs/Mar28_15-40-43_e726d06b80ed/1680018048.9185486/events.out.tfevents.1680018048.e726d06b80ed.1124.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf316817c327abf861aa0e3221df3e6e1332165ae6ac6c71f6da8418197f72b6
+size 5869

runs/Mar28_15-40-43_e726d06b80ed/events.out.tfevents.1680018048.e726d06b80ed.1124.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cdef985c8d2bd47d0acb6b050404c4fc6149f1659354a69735441a0aa04a1b4
+size 8137

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68920b34c1e49ac4d127a507049288c7cdc2da1d7f595e9a15a90f0a3f2c7aa7
+size 3579

wandb/run-20230328_153334-3xrv5t9j/files/config.yaml

@@ -0,0 +1,722 @@
+wandb_version: 1
+
+_commit_hash:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: ''
+_wandb:
+  desc: null
+  value:
+    cli_version: 0.13.10
+    framework: huggingface
+    huggingface_version: 4.26.1
+    is_jupyter_run: true
+    is_kaggle_kernel: true
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    python_version: 3.7.12
+    start_time: 1680017614.402597
+    t:
+      1:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      2:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      3:
+      - 7
+      - 23
+      4: 3.7.12
+      5: 0.13.10
+      6: 4.26.1
+      8:
+      - 1
+      - 2
+      - 5
+adafactor:
+  desc: null
+  value: false
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+add_cross_attention:
+  desc: null
+  value: false
+architectures:
+  desc: null
+  value: null
+auto_find_batch_size:
+  desc: null
+  value: false
+bad_words_ids:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value: null
+bf16:
+  desc: null
+  value: false
+bf16_full_eval:
+  desc: null
+  value: false
+bos_token_id:
+  desc: null
+  value: null
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+cross_attention_hidden_size:
+  desc: null
+  value: null
+data_seed:
+  desc: null
+  value: None
+dataloader_drop_last:
+  desc: null
+  value: false
+dataloader_num_workers:
+  desc: null
+  value: 0
+dataloader_pin_memory:
+  desc: null
+  value: true
+ddp_bucket_cap_mb:
+  desc: null
+  value: None
+ddp_find_unused_parameters:
+  desc: null
+  value: None
+ddp_timeout:
+  desc: null
+  value: 1800
+debug:
+  desc: null
+  value: '[]'
+decoder:
+  desc: null
+  value:
+    _name_or_path: bert-base-uncased
+    add_cross_attention: true
+    architectures:
+    - BertForMaskedLM
+    attention_probs_dropout_prob: 0.1
+    bad_words_ids: null
+    begin_suppress_tokens: null
+    bos_token_id: null
+    chunk_size_feed_forward: 0
+    classifier_dropout: null
+    cross_attention_hidden_size: null
+    decoder_start_token_id: null
+    diversity_penalty: 0.0
+    do_sample: false
+    early_stopping: false
+    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
+    gradient_checkpointing: false
+    hidden_act: gelu
+    hidden_dropout_prob: 0.1
+    hidden_size: 768
+    id2label:
+      '0': LABEL_0
+      '1': LABEL_1
+    initializer_range: 0.02
+    intermediate_size: 3072
+    is_decoder: true
+    is_encoder_decoder: false
+    label2id:
+      LABEL_0: 0
+      LABEL_1: 1
+    layer_norm_eps: 1.0e-12
+    length_penalty: 1.0
+    max_length: 20
+    max_position_embeddings: 512
+    min_length: 0
+    model_type: bert
+    no_repeat_ngram_size: 0
+    num_attention_heads: 12
+    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: 0
+    position_embedding_type: absolute
+    prefix: null
+    problem_type: null
+    pruned_heads: {}
+    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
+    transformers_version: 4.26.1
+    type_vocab_size: 2
+    typical_p: 1.0
+    use_bfloat16: false
+    use_cache: true
+    vocab_size: 30522
+decoder_start_token_id:
+  desc: null
+  value: 101
+deepspeed:
+  desc: null
+  value: None
+disable_tqdm:
+  desc: null
+  value: false
+diversity_penalty:
+  desc: null
+  value: 0.0
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+do_sample:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: true
+encoder:
+  desc: null
+  value:
+    _name_or_path: bert-base-uncased
+    add_cross_attention: false
+    architectures:
+    - BertForMaskedLM
+    attention_probs_dropout_prob: 0.1
+    bad_words_ids: null
+    begin_suppress_tokens: null
+    bos_token_id: null
+    chunk_size_feed_forward: 0
+    classifier_dropout: null
+    cross_attention_hidden_size: null
+    decoder_start_token_id: null
+    diversity_penalty: 0.0
+    do_sample: false
+    early_stopping: false
+    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
+    gradient_checkpointing: false
+    hidden_act: gelu
+    hidden_dropout_prob: 0.1
+    hidden_size: 768
+    id2label:
+      '0': LABEL_0
+      '1': LABEL_1
+    initializer_range: 0.02
+    intermediate_size: 3072
+    is_decoder: false
+    is_encoder_decoder: false
+    label2id:
+      LABEL_0: 0
+      LABEL_1: 1
+    layer_norm_eps: 1.0e-12
+    length_penalty: 1.0
+    max_length: 20
+    max_position_embeddings: 512
+    min_length: 0
+    model_type: bert
+    no_repeat_ngram_size: 0
+    num_attention_heads: 12
+    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: 0
+    position_embedding_type: absolute
+    prefix: null
+    problem_type: null
+    pruned_heads: {}
+    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
+    transformers_version: 4.26.1
+    type_vocab_size: 2
+    typical_p: 1.0
+    use_bfloat16: false
+    use_cache: true
+    vocab_size: 30522
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+eos_token_id:
+  desc: null
+  value: 102
+eval_accumulation_steps:
+  desc: null
+  value: None
+eval_batch_size:
+  desc: null
+  value: 16
+eval_delay:
+  desc: null
+  value: 0
+eval_steps:
+  desc: null
+  value: 2000
+evaluation_strategy:
+  desc: null
+  value: steps
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+finetuning_task:
+  desc: null
+  value: null
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+fp16:
+  desc: null
+  value: true
+fp16_backend:
+  desc: null
+  value: auto
+fp16_full_eval:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+fsdp:
+  desc: null
+  value: '[]'
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: None
+full_determinism:
+  desc: null
+  value: false
+generation_max_length:
+  desc: null
+  value: None
+generation_num_beams:
+  desc: null
+  value: None
+gradient_accumulation_steps:
+  desc: null
+  value: 1
+gradient_checkpointing:
+  desc: null
+  value: false
+greater_is_better:
+  desc: null
+  value: None
+group_by_length:
+  desc: null
+  value: false
+half_precision_backend:
+  desc: null
+  value: cuda_amp
+hub_model_id:
+  desc: null
+  value: None
+hub_private_repo:
+  desc: null
+  value: false
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+ignore_data_skip:
+  desc: null
+  value: false
+include_inputs_for_metrics:
+  desc: null
+  value: false
+is_decoder:
+  desc: null
+  value: false
+is_encoder_decoder:
+  desc: null
+  value: true
+jit_mode_eval:
+  desc: null
+  value: false
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+label_names:
+  desc: null
+  value: None
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+learning_rate:
+  desc: null
+  value: 5.0e-05
+length_column_name:
+  desc: null
+  value: length
+length_penalty:
+  desc: null
+  value: 2.0
+load_best_model_at_end:
+  desc: null
+  value: false
+local_rank:
+  desc: null
+  value: -1
+log_level:
+  desc: null
+  value: passive
+log_level_replica:
+  desc: null
+  value: passive
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/Mar28_15-40-43_e726d06b80ed
+logging_first_step:
+  desc: null
+  value: false
+logging_nan_inf_filter:
+  desc: null
+  value: true
+logging_steps:
+  desc: null
+  value: 1000
+logging_strategy:
+  desc: null
+  value: steps
+lr_scheduler_type:
+  desc: null
+  value: linear
+max_grad_norm:
+  desc: null
+  value: 1.0
+max_length:
+  desc: null
+  value: 128
+max_steps:
+  desc: null
+  value: -1
+metric_for_best_model:
+  desc: null
+  value: None
+min_length:
+  desc: null
+  value: 56
+model_type:
+  desc: null
+  value: encoder-decoder
+mp_parameters:
+  desc: null
+  value: ''
+no_cuda:
+  desc: null
+  value: false
+no_repeat_ngram_size:
+  desc: null
+  value: 3
+num_beam_groups:
+  desc: null
+  value: 1
+num_beams:
+  desc: null
+  value: 4
+num_return_sequences:
+  desc: null
+  value: 1
+num_train_epochs:
+  desc: null
+  value: 3.0
+optim:
+  desc: null
+  value: adamw_hf
+optim_args:
+  desc: null
+  value: None
+output_attentions:
+  desc: null
+  value: false
+output_dir:
+  desc: null
+  value: ./
+output_hidden_states:
+  desc: null
+  value: false
+output_scores:
+  desc: null
+  value: false
+overwrite_output_dir:
+  desc: null
+  value: true
+pad_token_id:
+  desc: null
+  value: 0
+past_index:
+  desc: null
+  value: -1
+per_device_eval_batch_size:
+  desc: null
+  value: 8
+per_device_train_batch_size:
+  desc: null
+  value: 8
+per_gpu_eval_batch_size:
+  desc: null
+  value: None
+per_gpu_train_batch_size:
+  desc: null
+  value: None
+predict_with_generate:
+  desc: null
+  value: true
+prediction_loss_only:
+  desc: null
+  value: false
+prefix:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+pruned_heads:
+  desc: null
+  value: {}
+push_to_hub:
+  desc: null
+  value: true
+push_to_hub_model_id:
+  desc: null
+  value: None
+push_to_hub_organization:
+  desc: null
+  value: None
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+ray_scope:
+  desc: null
+  value: last
+remove_invalid_values:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+repetition_penalty:
+  desc: null
+  value: 1.0
+report_to:
+  desc: null
+  value: '[''tensorboard'', ''wandb'']'
+resume_from_checkpoint:
+  desc: null
+  value: None
+return_dict:
+  desc: null
+  value: true
+return_dict_in_generate:
+  desc: null
+  value: false
+run_name:
+  desc: null
+  value: ./
+save_on_each_node:
+  desc: null
+  value: false
+save_steps:
+  desc: null
+  value: 500
+save_strategy:
+  desc: null
+  value: steps
+save_total_limit:
+  desc: null
+  value: 3
+seed:
+  desc: null
+  value: 42
+sep_token_id:
+  desc: null
+  value: null
+sharded_ddp:
+  desc: null
+  value: '[]'
+skip_memory_metrics:
+  desc: null
+  value: true
+sortish_sampler:
+  desc: null
+  value: false
+suppress_tokens:
+  desc: null
+  value: null
+task_specific_params:
+  desc: null
+  value: null
+temperature:
+  desc: null
+  value: 1.0
+tf32:
+  desc: null
+  value: None
+tf_legacy_loss:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+tie_word_embeddings:
+  desc: null
+  value: true
+tokenizer_class:
+  desc: null
+  value: null
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: None
+torch_compile_mode:
+  desc: null
+  value: None
+torch_dtype:
+  desc: null
+  value: null
+torchdynamo:
+  desc: null
+  value: None
+torchscript:
+  desc: null
+  value: false
+tpu_metrics_debug:
+  desc: null
+  value: false
+tpu_num_cores:
+  desc: null
+  value: None
+train_batch_size:
+  desc: null
+  value: 16
+transformers_version:
+  desc: null
+  value: null
+typical_p:
+  desc: null
+  value: 1.0
+use_bfloat16:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+vocab_size:
+  desc: null
+  value: 30522
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 1000
+weight_decay:
+  desc: null
+  value: 0.0
+xpu_backend:
+  desc: null
+  value: None