trishachetani's picture
Initial commit with model files
26bc096
{
"label_list": [
"O",
"B-city",
"I-city",
"B-country_code",
"I-country_code",
"B-zipcode",
"I-zipcode",
"B-start_date",
"I-start_date",
"B-end_date",
"I-end_date",
"B-time_period",
"I-time_period",
"B-days",
"I-days"
],
"label_to_id": {
"O": 0,
"B-city": 1,
"I-city": 2,
"B-country_code": 3,
"I-country_code": 4,
"B-zipcode": 5,
"I-zipcode": 6,
"B-start_date": 7,
"I-start_date": 8,
"B-end_date": 9,
"I-end_date": 10,
"B-time_period": 11,
"I-time_period": 12,
"B-days": 13,
"I-days": 14
},
"id_to_label": {
"0": "O",
"1": "B-city",
"2": "I-city",
"3": "B-country_code",
"4": "I-country_code",
"5": "B-zipcode",
"6": "I-zipcode",
"7": "B-start_date",
"8": "I-start_date",
"9": "B-end_date",
"10": "I-end_date",
"11": "B-time_period",
"12": "I-time_period",
"13": "B-days",
"14": "I-days"
},
"training_args": {
"output_dir": "./results",
"overwrite_output_dir": false,
"do_train": false,
"do_eval": true,
"do_predict": false,
"evaluation_strategy": "epoch",
"prediction_loss_only": false,
"per_device_train_batch_size": 8,
"per_device_eval_batch_size": 8,
"per_gpu_train_batch_size": null,
"per_gpu_eval_batch_size": null,
"gradient_accumulation_steps": 1,
"eval_accumulation_steps": null,
"eval_delay": 0,
"learning_rate": 2e-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,
"max_steps": -1,
"lr_scheduler_type": "linear",
"warmup_ratio": 0.0,
"warmup_steps": 0,
"log_level": "passive",
"log_level_replica": "passive",
"log_on_each_node": true,
"logging_dir": "./logs",
"logging_strategy": "steps",
"logging_first_step": false,
"logging_steps": 10,
"logging_nan_inf_filter": true,
"save_strategy": "epoch",
"save_steps": 500,
"save_total_limit": null,
"save_on_each_node": false,
"no_cuda": 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": "cuda_amp",
"bf16_full_eval": false,
"fp16_full_eval": false,
"tf32": null,
"local_rank": -1,
"xpu_backend": null,
"tpu_num_cores": null,
"tpu_metrics_debug": false,
"debug": [],
"dataloader_drop_last": false,
"eval_steps": null,
"dataloader_num_workers": 0,
"past_index": -1,
"run_name": "./results",
"disable_tqdm": false,
"remove_unused_columns": true,
"label_names": null,
"load_best_model_at_end": true,
"metric_for_best_model": "loss",
"greater_is_better": false,
"ignore_data_skip": false,
"sharded_ddp": [],
"fsdp": [],
"fsdp_min_num_params": 0,
"fsdp_transformer_layer_cls_to_wrap": null,
"deepspeed": null,
"label_smoothing_factor": 0.0,
"optim": "adamw_hf",
"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,
"dataloader_pin_memory": true,
"skip_memory_metrics": true,
"use_legacy_prediction_loop": false,
"push_to_hub": false,
"resume_from_checkpoint": null,
"hub_model_id": null,
"hub_strategy": "every_save",
"hub_token": "<HUB_TOKEN>",
"hub_private_repo": false,
"gradient_checkpointing": false,
"include_inputs_for_metrics": false,
"fp16_backend": "auto",
"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
},
"lora_config": {
"r": 8,
"lora_alpha": 32,
"target_modules": [
"query",
"value",
"key"
],
"lora_dropout": 0.1,
"bias": "none",
"task_type": "TOKEN_CLS"
},
"model_type": "roberta",
"base_model_name": "climatebert/distilroberta-base-climate-detector"
}