| { | |
| "dataset_config": { | |
| "name_dataset": "RWF2000", | |
| "frac_dataset": 1.0, | |
| "val_fraction": 0.1, | |
| "seed": 30, | |
| "num_frames": 16, | |
| "sample_rate": 4, | |
| "fps": 30, | |
| "mean": [ | |
| 0.45, | |
| 0.45, | |
| 0.45 | |
| ], | |
| "std": [ | |
| 0.225, | |
| 0.225, | |
| 0.225 | |
| ], | |
| "resize_to": [ | |
| 224, | |
| 224 | |
| ], | |
| "flag_only_person": false | |
| }, | |
| "model_config": { | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "output_attentions": false, | |
| "torchscript": false, | |
| "torch_dtype": "float32", | |
| "use_bfloat16": false, | |
| "tf_legacy_loss": false, | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "is_decoder": false, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "remove_invalid_values": false, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "architectures": [ | |
| "VideoMobileViTForVideoClassification" | |
| ], | |
| "finetuning_task": null, | |
| "id2label": null, | |
| "label2id": null, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": null, | |
| "pad_token_id": null, | |
| "eos_token_id": null, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "_name_or_path": "", | |
| "transformers_version": "4.45.2", | |
| "num_classes": 2, | |
| "num_frames": 16, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 4, | |
| "distillation_type": "kl", | |
| "model_version": "videomobilevit", | |
| "is_pretrained": true, | |
| "is_master": false, | |
| "model_type": "videomobilevit" | |
| }, | |
| "training_args": { | |
| "output_dir": "student_videomobilevit_not_learning_RWF2000", | |
| "overwrite_output_dir": false, | |
| "do_train": false, | |
| "do_eval": true, | |
| "do_predict": false, | |
| "eval_strategy": "steps", | |
| "prediction_loss_only": false, | |
| "per_device_train_batch_size": 20, | |
| "per_device_eval_batch_size": 20, | |
| "per_gpu_train_batch_size": null, | |
| "per_gpu_eval_batch_size": null, | |
| "gradient_accumulation_steps": 1, | |
| "eval_accumulation_steps": null, | |
| "eval_delay": 0, | |
| "torch_empty_cache_steps": null, | |
| "learning_rate": 1e-05, | |
| "weight_decay": 0.01, | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.999, | |
| "adam_epsilon": 1e-08, | |
| "max_grad_norm": 1.0, | |
| "num_train_epochs": 3.0, | |
| "max_steps": 1800, | |
| "lr_scheduler_type": "linear", | |
| "lr_scheduler_kwargs": {}, | |
| "warmup_ratio": 0.0, | |
| "warmup_steps": 180, | |
| "log_level": "passive", | |
| "log_level_replica": "warning", | |
| "log_on_each_node": true, | |
| "logging_dir": "student_videomobilevit_not_learning_RWF2000/runs/Oct07_20-26-00_3ff85290add4", | |
| "logging_strategy": "steps", | |
| "logging_first_step": false, | |
| "logging_steps": 50, | |
| "logging_nan_inf_filter": true, | |
| "save_strategy": "steps", | |
| "save_steps": 180, | |
| "save_total_limit": null, | |
| "save_safetensors": true, | |
| "save_on_each_node": false, | |
| "save_only_model": false, | |
| "restore_callback_states_from_checkpoint": false, | |
| "no_cuda": false, | |
| "use_cpu": false, | |
| "use_mps_device": false, | |
| "seed": 42, | |
| "data_seed": null, | |
| "jit_mode_eval": false, | |
| "use_ipex": false, | |
| "bf16": false, | |
| "fp16": true, | |
| "fp16_opt_level": "O1", | |
| "half_precision_backend": "auto", | |
| "bf16_full_eval": false, | |
| "fp16_full_eval": false, | |
| "tf32": null, | |
| "local_rank": 0, | |
| "ddp_backend": null, | |
| "tpu_num_cores": null, | |
| "tpu_metrics_debug": false, | |
| "debug": [], | |
| "dataloader_drop_last": false, | |
| "eval_steps": 180, | |
| "dataloader_num_workers": 4, | |
| "dataloader_prefetch_factor": null, | |
| "past_index": -1, | |
| "run_name": "student_videomobilevit_not_learning_RWF2000", | |
| "disable_tqdm": false, | |
| "remove_unused_columns": false, | |
| "label_names": null, | |
| "load_best_model_at_end": true, | |
| "metric_for_best_model": "f1", | |
| "greater_is_better": true, | |
| "ignore_data_skip": false, | |
| "fsdp": [], | |
| "fsdp_min_num_params": 0, | |
| "fsdp_config": { | |
| "min_num_params": 0, | |
| "xla": false, | |
| "xla_fsdp_v2": false, | |
| "xla_fsdp_grad_ckpt": false | |
| }, | |
| "fsdp_transformer_layer_cls_to_wrap": null, | |
| "accelerator_config": { | |
| "split_batches": false, | |
| "dispatch_batches": null, | |
| "even_batches": true, | |
| "use_seedable_sampler": true, | |
| "non_blocking": false, | |
| "gradient_accumulation_kwargs": null | |
| }, | |
| "deepspeed": null, | |
| "label_smoothing_factor": 0.0, | |
| "optim": "adamw_torch", | |
| "optim_args": null, | |
| "adafactor": false, | |
| "group_by_length": false, | |
| "length_column_name": "length", | |
| "report_to": [ | |
| "tensorboard" | |
| ], | |
| "ddp_find_unused_parameters": null, | |
| "ddp_bucket_cap_mb": null, | |
| "ddp_broadcast_buffers": null, | |
| "dataloader_pin_memory": true, | |
| "dataloader_persistent_workers": false, | |
| "skip_memory_metrics": true, | |
| "use_legacy_prediction_loop": false, | |
| "push_to_hub": true, | |
| "resume_from_checkpoint": null, | |
| "hub_model_id": null, | |
| "hub_strategy": "every_save", | |
| "hub_token": "<HUB_TOKEN>", | |
| "hub_private_repo": false, | |
| "hub_always_push": false, | |
| "gradient_checkpointing": false, | |
| "gradient_checkpointing_kwargs": null, | |
| "include_inputs_for_metrics": false, | |
| "eval_do_concat_batches": true, | |
| "fp16_backend": "auto", | |
| "evaluation_strategy": null, | |
| "push_to_hub_model_id": null, | |
| "push_to_hub_organization": null, | |
| "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", | |
| "mp_parameters": "", | |
| "auto_find_batch_size": false, | |
| "full_determinism": false, | |
| "torchdynamo": null, | |
| "ray_scope": "last", | |
| "ddp_timeout": 1800, | |
| "torch_compile": false, | |
| "torch_compile_backend": null, | |
| "torch_compile_mode": null, | |
| "dispatch_batches": null, | |
| "split_batches": null, | |
| "include_tokens_per_second": false, | |
| "include_num_input_tokens_seen": false, | |
| "neftune_noise_alpha": null, | |
| "optim_target_modules": null, | |
| "batch_eval_metrics": false, | |
| "eval_on_start": false, | |
| "use_liger_kernel": false, | |
| "eval_use_gather_object": false | |
| }, | |
| "batch_size": 20, | |
| "num_epochs": 25, | |
| "learning_rate": 1e-05, | |
| "weight_decay": 0.01, | |
| "early_stopping_patience": 7, | |
| "early_stopping_threshold": 0.0025, | |
| "warmup_ratio": 0.1, | |
| "seed": 42 | |
| } |