Add files using upload-large-folder tool

plbart_fmft_official_1e-05/checkpoint-103026/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "uclanlp/plbart-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "PLBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "plbart",
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 50005
+}

plbart_fmft_official_1e-05/checkpoint-103026/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "max_new_tokens": 256,
+  "min_new_tokens": 2,
+  "num_beams": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0"
+}

plbart_fmft_official_1e-05/checkpoint-103026/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816e43c27b9f8ed8070008a9e23d60c6eb7fc4419f313898135b6ab45b1b40a0
+size 557112860

plbart_fmft_official_1e-05/checkpoint-103026/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39a46f84b6ae50a97c033742fefa46388cdd1a21252e96859b5f9a3d5a8fb6a
+size 1113982859

plbart_fmft_official_1e-05/checkpoint-103026/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad46ce7d5f175ad6a8930587b64ba9c17d4384b051d42bbde858a2fc6389eb7
+size 14645

plbart_fmft_official_1e-05/checkpoint-103026/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c337637185fd80cd189c72d3bb64bfd33c12b6458a1e298f92773bd809f4b66e
+size 1465

plbart_fmft_official_1e-05/checkpoint-103026/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cbbe535fd7d595a9e873964ff829b32a45a17e830e6972ab43f99df4848122e
+size 8081

plbart_fmft_official_1e-05/checkpoint-117744/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "uclanlp/plbart-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "PLBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "plbart",
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 50005
+}

plbart_fmft_official_1e-05/checkpoint-117744/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "max_new_tokens": 256,
+  "min_new_tokens": 2,
+  "num_beams": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0"
+}

plbart_fmft_official_1e-05/checkpoint-117744/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd77ec5e5927764b9bc5ebad074bdf6b2fe3647157b1e0c3c9bc76e35d55cdda
+size 557112860

plbart_fmft_official_1e-05/checkpoint-117744/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f66940e600e6c65a9cdd8ee3d4519e3a0b9b0ef2ae8c9f19d1fb680ec727501
+size 1113982859

plbart_fmft_official_1e-05/checkpoint-117744/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a5951e001a9359f7e983b3b7ce52ce35cb24fbab56c5789a9b40f0b2895ee1
+size 14645

plbart_fmft_official_1e-05/checkpoint-117744/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a07404cd44d75d59cb3734047d5b90b137885eff7dda0584677aed1e8f3584a
+size 1465

plbart_fmft_official_1e-05/checkpoint-117744/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cbbe535fd7d595a9e873964ff829b32a45a17e830e6972ab43f99df4848122e
+size 8081

plbart_fmft_official_1e-05/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "uclanlp/plbart-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "PLBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "plbart",
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 50005
+}

plbart_fmft_official_1e-05/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "max_new_tokens": 256,
+  "min_new_tokens": 2,
+  "num_beams": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0"
+}

plbart_fmft_official_1e-05/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816e43c27b9f8ed8070008a9e23d60c6eb7fc4419f313898135b6ab45b1b40a0
+size 557112860

plbart_fmft_official_1e-05/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72f5d040a176945623a255484d24066f8c0da89a294359154e226efbe494b80
+size 985833

plbart_fmft_official_1e-05/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "__java__",
+    "__python__",
+    "__en_XX__"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

plbart_fmft_official_1e-05/tokenizer_config.json

@@ -0,0 +1,88 @@
+{
+  "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
+    },
+    "50001": {
+      "content": "__java__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50002": {
+      "content": "__python__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50003": {
+      "content": "__en_XX__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "__java__",
+    "__python__",
+    "__en_XX__"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "language_codes": "base",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "PLBartTokenizer",
+  "unk_token": "<unk>"
+}

plbart_fmft_official_1e-05/training_args.txt

@@ -0,0 +1,145 @@
+Seq2SeqTrainingArguments(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+average_tokens_across_devices=False,
+batch_eval_metrics=False,
+bf16=False,
+bf16_full_eval=False,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+dispatch_batches=None,
+do_eval=True,
+do_predict=False,
+do_train=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=False,
+eval_steps=None,
+eval_strategy=IntervalStrategy.EPOCH,
+eval_use_gather_object=False,
+evaluation_strategy=None,
+fp16=True,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+generation_config=GenerationConfig {
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "max_new_tokens": 256,
+  "min_new_tokens": 2,
+  "num_beams": 3,
+  "pad_token_id": 1
+}
+,
+generation_max_length=None,
+generation_num_beams=None,
+gradient_accumulation_steps=1,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs=None,
+greater_is_better=True,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=None,
+hub_private_repo=None,
+hub_strategy=HubStrategy.EVERY_SAVE,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=1e-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=./results-cc/plbart/plbart_fmft_official_1e-05/logs,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=5,
+logging_strategy=IntervalStrategy.STEPS,
+lr_scheduler_kwargs={},
+lr_scheduler_type=SchedulerType.LINEAR,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=eval_bleu_4,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_train_epochs=8,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=./results-cc/plbart/plbart_fmft_official_1e-05,
+overwrite_output_dir=False,
+past_index=-1,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=8,
+predict_with_generate=True,
+prediction_loss_only=False,
+push_to_hub=False,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=True,
+report_to=['wandb'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=plbart_fmft_official_1e-05,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=500,
+save_strategy=SaveStrategy.EPOCH,
+save_total_limit=2,
+seed=42,
+skip_memory_metrics=True,
+sortish_sampler=False,
+split_batches=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_empty_cache_steps=None,
+torchdynamo=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_liger_kernel=False,
+use_mps_device=False,
+warmup_ratio=0.0,
+warmup_steps=0,
+weight_decay=0.01,
+)