Upload folder using huggingface_hub

best_model/decoder/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "add_cross_attention": true,
+  "architectures": [
+    "BertLMHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

best_model/decoder/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.2"
+}

best_model/decoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fed1543b11a26201299b540cb0b859c126c31825d3e1f0b7e4dc8e69d732e5e
+size 825480985

best_model/decoder/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

best_model/decoder/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

best_model/encoder/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

best_model/encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e7902ebfef91c2dd83fc772dfede7bb7b9475e641df6e5c081f96deb1213af
+size 711484973

best_model/encoder/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

best_model/encoder/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

best_model/eval_results.txt

@@ -0,0 +1 @@
+eval_loss = 4.638601120575762e-05

best_model/model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/mbert/best_model", "cache_dir": "cache_dir/mbert", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 25, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 3200, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 0.0001, "local_rank": -1, "logging_steps": 3200, "loss_type": null, "loss_args": {}, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "bert-base-multilingual-cased-bert-base-multilingual-cased", "model_type": "bert-bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "optimizer": "AdamW", "output_dir": "outputs/mbert", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 78, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 3200, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {"name": "bert-base-multilingual-cased"}, "wandb_project": "DORE", "warmup_ratio": 0.06, "warmup_steps": 4946, "weight_decay": 0.0, "model_class": "Seq2SeqModel", "base_marian_model_name": null, "dataset_class": null, "dataset_cache_dir": null, "do_sample": false, "early_stopping": true, "evaluate_generated_text": true, "faiss_d": 768, "faiss_m": 128, "include_title_in_knowledge_dataset": true, "length_penalty": 2.0, "max_length": 20, "max_steps": -1, "num_beams": 1, "num_return_sequences": 1, "rag_embed_batch_size": 16, "repetition_penalty": 1.0, "save_knowledge_dataset": true, "save_knowledge_dataset_with_checkpoints": false, "save_recent_only": true, "split_text_character": " ", "split_text_n": 100, "src_lang": "en_XX", "tgt_lang": "ro_RO", "top_k": null, "top_p": null, "use_multiprocessed_decoding": false}

best_model/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e85bb1a0ccb2f249890c8c838326d2071eb99e3a5ec8d8a875f12f5c031083c
+size 3069268210

best_model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e256f319386c1ba3833ac29cb14870f2e80ce6f86a6405851d9a5a16fcb97e1
+size 627

best_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724cc7d33efdcd3ae19790f6f434cb90392af95a253cba395ad28e3fc2303e0e
+size 3579

checkpoint-74178-epoch-9/eval_results.txt

@@ -0,0 +1 @@
+eval_loss = 18.88406741046489

eval_results.txt

@@ -0,0 +1 @@
+eval_loss = 18.88406741046489

training_progress_scores.csv

@@ -0,0 +1,33 @@
+global_step,eval_loss,train_loss
+3200,4.638601120575762e-05,9.859441342996433e-05
+6400,0.0004333633804356752,2.2505106244352646e-05
+8242,0.0006071640122126645,0.0020425980910658836
+9600,0.0001250970983686778,7.014982838882133e-05
+12800,0.004397115739013738,0.0006558408495038748
+16000,0.00012924883208755288,4.2052179196616635e-05
+16484,6.069257284924091e-05,1.1547194844752084e-06
+19200,7.374908047934749,6.571280002593994
+22400,11.5760720029495,6.235233783721924
+24726,13.781783858183111,6.484010219573975
+25600,13.465459120267806,6.241044044494629
+28800,14.799029918968648,6.351245880126953
+32000,12.572137959890721,6.461843013763428
+32968,15.59106514027025,5.936652660369873
+35200,11.594814583261519,6.3275146484375
+38400,16.371380089209648,6.0015058517456055
+41210,14.86689023171045,5.965159893035889
+41600,15.508951940448581,6.275737762451172
+44800,14.77081819253891,6.237776279449463
+48000,14.01954884138112,6.322638511657715
+49452,16.832226444597907,6.67988920211792
+51200,18.10885695726301,6.464913368225098
+54400,15.01399333033962,5.935701370239258
+57600,17.017078648603754,6.028385162353516
+57694,16.424798103861875,6.45088529586792
+60800,19.780675463280822,5.924292087554932
+64000,17.076165711515333,6.798635482788086
+65936,17.641285376662136,6.5727362632751465
+67200,14.17987766339905,5.9465556144714355
+70400,18.60497539729415,5.827696323394775
+73600,16.498589126535087,6.554838180541992
+74178,18.88406741046489,6.478570938110352