| { |
| "scope": "universal", |
| "ordinary_version": null, |
| "task": "statement", |
| "initialization": "/home/henryh/pylingual-runs/hub/Salesforce--codet5-base", |
| "initial_weights_sha256": "bf6d33ae2678bf6c2ecbbd19049a304b4a1ad2c39f91c396020dca53b8b2a4cd", |
| "data_manifest": { |
| "scope": "universal", |
| "bindings": {}, |
| "split": "train", |
| "task": "statement", |
| "journal_sha256": "98cf9ae8f79afb03367e926aeae16f69d41f8dc39b4d893744ec159c7f925c96", |
| "files": 50000, |
| "smoke_only": false, |
| "encoding_implementation_sha256": "127eebcd5d7b399b63667d5bfac738be6d89ae8379af37e37c2b78be4c21f9a7", |
| "tokenizer_json_sha256": "576881c7af5310402326eff7bf5584ad6e2f88dcfd4c998d4e8b6a26f243153f", |
| "registry_sha256": "522c85e983dcca62d12b648ca24f4fe4a5c554720eaf69aa130db6dffab495e4", |
| "versions": { |
| "3.6": 5556, |
| "3.7": 5556, |
| "3.8": 5556, |
| "3.9": 5556, |
| "3.10": 5556, |
| "3.11": 5555, |
| "3.12": 5555, |
| "3.13": 5555, |
| "3.14": 5555 |
| }, |
| "corpora": { |
| "pypi": 45000, |
| "csn": 5000 |
| }, |
| "raw_examples": 4663180, |
| "all_converter_rows": true, |
| "limits": { |
| "statement_input": 256, |
| "statement_target": 256, |
| "segmentation_window": 512, |
| "stride": 128 |
| }, |
| "complete": true, |
| "encoded_rows": 4663180, |
| "dataset_fingerprint": "6c2dc84fd509e91b", |
| "seconds": 2375.584766071057 |
| }, |
| "tokenizer_registry_fingerprint": "c66d4184e9f396c0f2c18d45930d65f589303f7f66dd0b4f3a6b9c171af5b03b", |
| "training_arguments": { |
| "output_dir": "/home/henryh/pylingual-runs/universal/statement/training", |
| "per_device_train_batch_size": 24, |
| "num_train_epochs": 2, |
| "max_steps": -1, |
| "learning_rate": 2e-05, |
| "lr_scheduler_type": "linear", |
| "lr_scheduler_kwargs": null, |
| "warmup_steps": 0, |
| "optim": "adamw_torch_fused", |
| "optim_args": null, |
| "weight_decay": 0.01, |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.999, |
| "adam_epsilon": 1e-08, |
| "optim_target_modules": null, |
| "gradient_accumulation_steps": 3, |
| "average_tokens_across_devices": true, |
| "max_grad_norm": 1.0, |
| "label_smoothing_factor": 0.0, |
| "bf16": false, |
| "fp16": true, |
| "bf16_full_eval": false, |
| "fp16_full_eval": false, |
| "tf32": null, |
| "gradient_checkpointing": false, |
| "gradient_checkpointing_kwargs": null, |
| "torch_compile": false, |
| "torch_compile_backend": null, |
| "torch_compile_mode": null, |
| "use_liger_kernel": false, |
| "liger_kernel_config": null, |
| "use_cache": false, |
| "neftune_noise_alpha": null, |
| "torch_empty_cache_steps": null, |
| "auto_find_batch_size": false, |
| "logging_strategy": "steps", |
| "logging_steps": 1000, |
| "logging_first_step": false, |
| "log_on_each_node": true, |
| "logging_nan_inf_filter": false, |
| "include_num_input_tokens_seen": "no", |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "disable_tqdm": true, |
| "report_to": [], |
| "run_name": null, |
| "project": "huggingface", |
| "trackio_space_id": null, |
| "trackio_bucket_id": null, |
| "trackio_static_space_id": null, |
| "eval_strategy": "no", |
| "eval_steps": null, |
| "eval_delay": 0, |
| "per_device_eval_batch_size": 8, |
| "prediction_loss_only": false, |
| "eval_on_start": false, |
| "eval_do_concat_batches": true, |
| "eval_use_gather_object": false, |
| "eval_accumulation_steps": null, |
| "include_for_metrics": [], |
| "batch_eval_metrics": false, |
| "save_only_model": false, |
| "save_strategy": "steps", |
| "save_steps": 10000, |
| "save_on_each_node": false, |
| "save_total_limit": 2, |
| "enable_jit_checkpoint": false, |
| "push_to_hub": false, |
| "hub_token": "<HUB_TOKEN>", |
| "hub_private_repo": null, |
| "hub_model_id": null, |
| "hub_strategy": "every_save", |
| "hub_always_push": false, |
| "hub_revision": null, |
| "load_best_model_at_end": false, |
| "metric_for_best_model": null, |
| "greater_is_better": null, |
| "ignore_data_skip": false, |
| "restore_callback_states_from_checkpoint": false, |
| "full_determinism": false, |
| "seed": 20261020, |
| "data_seed": null, |
| "use_cpu": false, |
| "accelerator_config": { |
| "split_batches": false, |
| "dispatch_batches": null, |
| "even_batches": true, |
| "use_seedable_sampler": true, |
| "non_blocking": false, |
| "gradient_accumulation_kwargs": null |
| }, |
| "parallelism_config": null, |
| "dataloader_drop_last": false, |
| "dataloader_num_workers": 2, |
| "dataloader_pin_memory": true, |
| "dataloader_persistent_workers": false, |
| "dataloader_prefetch_factor": null, |
| "dataloader_multiprocessing_context": null, |
| "dataloader_in_order": true, |
| "remove_unused_columns": false, |
| "label_names": null, |
| "train_sampling_strategy": "random", |
| "length_column_name": "length", |
| "ddp_find_unused_parameters": false, |
| "ddp_bucket_cap_mb": null, |
| "ddp_broadcast_buffers": null, |
| "ddp_static_graph": null, |
| "ddp_backend": null, |
| "ddp_timeout": 1800, |
| "fsdp": null, |
| "fsdp_config": null, |
| "deepspeed": null, |
| "debug": [], |
| "skip_memory_metrics": true, |
| "do_train": false, |
| "do_eval": false, |
| "do_predict": false, |
| "resume_from_checkpoint": null, |
| "local_rank": -1, |
| "sortish_sampler": false, |
| "predict_with_generate": false, |
| "generation_max_length": null, |
| "generation_num_beams": null, |
| "generation_config": null |
| }, |
| "original_vocab": 32100, |
| "vocab": 11577, |
| "torch": "2.14.0+cu130", |
| "transformers": "5.17.0", |
| "python": "3.12.16", |
| "hostname": "triplesec1-gpu", |
| "smoke_only": false, |
| "script_sha256": "0647e466755f5c2995b095ac4e1119b0a3b6380d7c4271d952d76e3d1ffeed9f", |
| "world_size": 1, |
| "loss_normalization": "global-supervised-token-mean-v1", |
| "loss_normalization_sha256": "3d8e6217caddd6b6e66f35df704c9fa7b7fb0b29849e84fa2cb91d597383c274" |
| } |
|
|
