| { |
| "mlflow": { |
| "run_info": { |
| "run_id": "8e49dfe3fcc945858fcde727586b65ba", |
| "experiment_id": "13", |
| "experiment_name": "Multitask_Classification", |
| "start_time": "2025-10-09 14:38:51", |
| "end_time": "2025-10-09 15:04:07", |
| "status": "FINISHED", |
| "artifact_uri": "/opt/chl_ai/mlflow-shared/artifacts/13/8e49dfe3fcc945858fcde727586b65ba/artifacts" |
| }, |
| "metrics": { |
| "loss": 2.3214, |
| "grad_norm": 16.057979583740234, |
| "learning_rate": 1.8203883495145632e-07, |
| "epoch": 12.0, |
| "eval_avg_acc": 0.6536885245901639, |
| "eval_avg_precision": 0.6310791053371948, |
| "eval_avg_recall": 0.6536885245901639, |
| "eval_avg_f1": 0.6310872540018378, |
| "eval_main_acc": 0.6994535519125683, |
| "eval_main_precision": 0.6950549785486344, |
| "eval_main_recall": 0.6994535519125683, |
| "eval_main_f1": 0.6942266690646444, |
| "eval_sub_acc": 0.5806010928961749, |
| "eval_sub_precision": 0.5781261111877007, |
| "eval_sub_recall": 0.5806010928961749, |
| "eval_sub_f1": 0.5734874502215787, |
| "eval_interv_acc": 0.6953551912568307, |
| "eval_interv_precision": 0.6753778417197009, |
| "eval_interv_recall": 0.6953551912568307, |
| "eval_interv_f1": 0.6720282592209204, |
| "eval_priority_acc": 0.639344262295082, |
| "eval_priority_precision": 0.5757574898927432, |
| "eval_priority_recall": 0.639344262295082, |
| "eval_priority_f1": 0.584606637500208, |
| "eval_runtime": 3.9426, |
| "eval_samples_per_second": 185.666, |
| "eval_steps_per_second": 11.668, |
| "train_runtime": 1506.6762, |
| "train_samples_per_second": 52.423, |
| "train_steps_per_second": 3.281, |
| "total_flos": 1.047735897882624e+16, |
| "train_loss": 3.697303699444027 |
| }, |
| "params": { |
| "num_epochs": "12", |
| "num_sub_categories": "65", |
| "test_size": "0.1", |
| "random_seed": "42", |
| "vocab_size": "30522", |
| "max_position_embeddings": "512", |
| "sinusoidal_pos_embds": "False", |
| "n_layers": "6", |
| "n_heads": "12", |
| "dim": "768", |
| "hidden_dim": "3072", |
| "dropout": "0.1", |
| "attention_dropout": "0.1", |
| "activation": "gelu", |
| "initializer_range": "0.02", |
| "qa_dropout": "0.1", |
| "seq_classif_dropout": "0.2", |
| "return_dict": "True", |
| "output_hidden_states": "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": "None", |
| "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": "None", |
| "num_return_sequences": "1", |
| "output_scores": "False", |
| "return_dict_in_generate": "False", |
| "forced_bos_token_id": "None", |
| "forced_eos_token_id": "None", |
| "remove_invalid_values": "False", |
| "exponential_decay_length_penalty": "None", |
| "suppress_tokens": "None", |
| "begin_suppress_tokens": "None", |
| "architectures": "['DistilBertForMaskedLM']", |
| "finetuning_task": "None", |
| "batch_size": "16", |
| "logging_dir": "./logs", |
| "logging_strategy": "steps", |
| "logging_first_step": "False", |
| "logging_steps": "100", |
| "logging_nan_inf_filter": "True", |
| "save_strategy": "epoch", |
| "save_steps": "500", |
| "save_total_limit": "None", |
| "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": "None", |
| "jit_mode_eval": "False", |
| "use_ipex": "False", |
| "bf16": "False", |
| "fp16": "False", |
| "fp16_opt_level": "O1", |
| "half_precision_backend": "auto", |
| "bf16_full_eval": "False", |
| "fp16_full_eval": "False", |
| "tf32": "None", |
| "local_rank": "0", |
| "ddp_backend": "None", |
| "tpu_num_cores": "None", |
| "tpu_metrics_debug": "False", |
| "debug": "[]", |
| "dataloader_drop_last": "False", |
| "eval_steps": "None", |
| "dataloader_num_workers": "0", |
| "dataloader_prefetch_factor": "None", |
| "past_index": "-1", |
| "run_name": "./results", |
| "disable_tqdm": "False", |
| "remove_unused_columns": "True", |
| "label_names": "None", |
| "load_best_model_at_end": "True", |
| "metric_for_best_model": "eval_avg_acc", |
| "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": "None", |
| "accelerator_config": "{'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}", |
| "deepspeed": "None", |
| "label_smoothing_factor": "0.0", |
| "optim": "adamw_torch", |
| "optim_args": "None", |
| "adafactor": "False", |
| "group_by_length": "False", |
| "length_column_name": "length", |
| "report_to": "['mlflow', 'tensorboard']", |
| "ddp_find_unused_parameters": "None", |
| "ddp_bucket_cap_mb": "None", |
| "ddp_broadcast_buffers": "None", |
| "dataloader_pin_memory": "True", |
| "dataloader_persistent_workers": "False", |
| "skip_memory_metrics": "True", |
| "use_legacy_prediction_loop": "False", |
| "push_to_hub": "False", |
| "resume_from_checkpoint": "None", |
| "hub_model_id": "None", |
| "hub_strategy": "every_save", |
| "hub_token": "<HUB_TOKEN>", |
| "hub_private_repo": "None", |
| "hub_always_push": "False", |
| "hub_revision": "None", |
| "gradient_checkpointing": "False", |
| "gradient_checkpointing_kwargs": "None", |
| "include_inputs_for_metrics": "False", |
| "include_for_metrics": "[]", |
| "eval_do_concat_batches": "True", |
| "fp16_backend": "auto", |
| "push_to_hub_model_id": "None", |
| "num_interventions": "5", |
| "learning_rate": "2e-05", |
| "num_main_categories": "7", |
| "num_priorities": "3", |
| "id2label": "{0: 'LABEL_0', 1: 'LABEL_1'}", |
| "label2id": "{'LABEL_0': 0, 'LABEL_1': 1}", |
| "tokenizer_class": "None", |
| "prefix": "None", |
| "bos_token_id": "None", |
| "pad_token_id": "0", |
| "eos_token_id": "None", |
| "sep_token_id": "None", |
| "decoder_start_token_id": "None", |
| "task_specific_params": "None", |
| "problem_type": "None", |
| "_name_or_path": "distilbert-base-uncased", |
| "transformers_version": "4.53.2", |
| "model_type": "distilbert", |
| "tie_weights_": "True", |
| "output_attentions": "False", |
| "output_dir": "./results", |
| "overwrite_output_dir": "False", |
| "do_train": "False", |
| "do_eval": "True", |
| "do_predict": "False", |
| "eval_strategy": "epoch", |
| "prediction_loss_only": "False", |
| "per_device_train_batch_size": "16", |
| "per_device_eval_batch_size": "16", |
| "per_gpu_train_batch_size": "None", |
| "per_gpu_eval_batch_size": "None", |
| "gradient_accumulation_steps": "1", |
| "eval_accumulation_steps": "None", |
| "eval_delay": "0", |
| "torch_empty_cache_steps": "None", |
| "weight_decay": "0.01", |
| "adam_beta1": "0.9", |
| "adam_beta2": "0.999", |
| "adam_epsilon": "1e-08", |
| "max_grad_norm": "1.0", |
| "num_train_epochs": "12", |
| "max_steps": "-1", |
| "lr_scheduler_type": "linear", |
| "lr_scheduler_kwargs": "{}", |
| "warmup_ratio": "0.0", |
| "warmup_steps": "0", |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "log_on_each_node": "True", |
| "push_to_hub_organization": "None", |
| "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", |
| "mp_parameters": "", |
| "auto_find_batch_size": "False", |
| "full_determinism": "False", |
| "torchdynamo": "None", |
| "ray_scope": "last", |
| "ddp_timeout": "1800", |
| "torch_compile": "False", |
| "torch_compile_backend": "None", |
| "torch_compile_mode": "None", |
| "include_tokens_per_second": "False", |
| "include_num_input_tokens_seen": "False", |
| "neftune_noise_alpha": "None", |
| "optim_target_modules": "None", |
| "batch_eval_metrics": "False", |
| "eval_on_start": "False", |
| "use_liger_kernel": "False", |
| "liger_kernel_config": "None", |
| "eval_use_gather_object": "False", |
| "average_tokens_across_devices": "False" |
| }, |
| "tags": { |
| "mlflow.user": "rogendo", |
| "mlflow.source.name": "trainer.py", |
| "mlflow.source.type": "LOCAL", |
| "mlflow.source.git.commit": "cb31c1906ac879a031eb203b9608e6388b750a32", |
| "mlflow.runName": "multitask_distilbert_training_20251009_143851" |
| } |
| }, |
| "user": {}, |
| "export": { |
| "method": "unknown", |
| "timestamp": "2025-10-09T16:43:46.510577", |
| "version": "8", |
| "mode": "tensorboard_only" |
| } |
| } |
