190 lines
5.2 KiB
JSON
190 lines
5.2 KiB
JSON
{
|
|
"model_config": {
|
|
"add_cross_attention": false,
|
|
"tie_word_embeddings": true,
|
|
"vocab_size": 50258,
|
|
"n_positions": 1024,
|
|
"n_embd": 768,
|
|
"n_layer": 12,
|
|
"n_head": 12,
|
|
"n_inner": null,
|
|
"activation_function": "gelu_new",
|
|
"resid_pdrop": 0.1,
|
|
"embd_pdrop": 0.1,
|
|
"attn_pdrop": 0.1,
|
|
"layer_norm_epsilon": 1e-05,
|
|
"initializer_range": 0.02,
|
|
"summary_type": "cls_index",
|
|
"summary_use_proj": true,
|
|
"summary_activation": null,
|
|
"summary_first_dropout": 0.1,
|
|
"summary_proj_to_labels": true,
|
|
"scale_attn_weights": true,
|
|
"use_cache": false,
|
|
"scale_attn_by_inverse_layer_idx": false,
|
|
"reorder_and_upcast_attn": false,
|
|
"bos_token_id": 50256,
|
|
"eos_token_id": 50256,
|
|
"pad_token_id": null,
|
|
"return_dict": true,
|
|
"output_hidden_states": false,
|
|
"dtype": "float32",
|
|
"chunk_size_feed_forward": 0,
|
|
"is_encoder_decoder": false,
|
|
"architectures": [
|
|
"GPT2LMHeadModel"
|
|
],
|
|
"id2label": {
|
|
"0": "LABEL_0",
|
|
"1": "LABEL_1"
|
|
},
|
|
"label2id": {
|
|
"LABEL_0": 0,
|
|
"LABEL_1": 1
|
|
},
|
|
"problem_type": null,
|
|
"_name_or_path": "gpt2",
|
|
"transformers_version": "5.0.0",
|
|
"model_type": "gpt2",
|
|
"n_ctx": 1024,
|
|
"task_specific_params": {
|
|
"text-generation": {
|
|
"do_sample": true,
|
|
"max_length": 50
|
|
}
|
|
},
|
|
"output_attentions": false
|
|
},
|
|
"tokenizer_config": {
|
|
"vocab_size": 50258,
|
|
"special_tokens": {
|
|
"pad_token": "<|endoftext|>",
|
|
"eos_token": "<|endoftext|>",
|
|
"bos_token": "<|endoftext|>",
|
|
"additional_special_tokens": []
|
|
}
|
|
},
|
|
"training_args": {
|
|
"output_dir": "./FEMA-checkpoints",
|
|
"do_train": false,
|
|
"do_eval": true,
|
|
"do_predict": false,
|
|
"eval_strategy": "epoch",
|
|
"prediction_loss_only": false,
|
|
"per_device_train_batch_size": 2,
|
|
"per_device_eval_batch_size": 2,
|
|
"gradient_accumulation_steps": 2,
|
|
"eval_accumulation_steps": null,
|
|
"eval_delay": 0,
|
|
"torch_empty_cache_steps": null,
|
|
"learning_rate": 5e-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",
|
|
"lr_scheduler_kwargs": null,
|
|
"warmup_ratio": null,
|
|
"warmup_steps": 100,
|
|
"log_level": "passive",
|
|
"log_level_replica": "warning",
|
|
"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": 3,
|
|
"enable_jit_checkpoint": false,
|
|
"save_on_each_node": false,
|
|
"save_only_model": false,
|
|
"restore_callback_states_from_checkpoint": false,
|
|
"use_cpu": false,
|
|
"seed": 42,
|
|
"data_seed": null,
|
|
"bf16": false,
|
|
"fp16": true,
|
|
"bf16_full_eval": false,
|
|
"fp16_full_eval": false,
|
|
"tf32": null,
|
|
"local_rank": -1,
|
|
"ddp_backend": null,
|
|
"debug": [],
|
|
"dataloader_drop_last": false,
|
|
"eval_steps": null,
|
|
"dataloader_num_workers": 0,
|
|
"dataloader_prefetch_factor": null,
|
|
"run_name": null,
|
|
"disable_tqdm": false,
|
|
"remove_unused_columns": true,
|
|
"label_names": null,
|
|
"load_best_model_at_end": true,
|
|
"metric_for_best_model": "eval_loss",
|
|
"greater_is_better": false,
|
|
"ignore_data_skip": false,
|
|
"fsdp": [],
|
|
"fsdp_config": {
|
|
"min_num_params": 0,
|
|
"xla": false,
|
|
"xla_fsdp_v2": false,
|
|
"xla_fsdp_grad_ckpt": 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,
|
|
"deepspeed": null,
|
|
"label_smoothing_factor": 0.0,
|
|
"optim": "adamw_torch_fused",
|
|
"optim_args": null,
|
|
"group_by_length": false,
|
|
"length_column_name": "length",
|
|
"report_to": [],
|
|
"project": "huggingface",
|
|
"trackio_space_id": "trackio",
|
|
"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,
|
|
"push_to_hub": false,
|
|
"resume_from_checkpoint": null,
|
|
"hub_model_id": null,
|
|
"hub_strategy": "every_save",
|
|
"hub_token": "<HUB_TOKEN>",
|
|
"hub_private_repo": null,
|
|
"hub_always_push": false,
|
|
"hub_revision": null,
|
|
"gradient_checkpointing": false,
|
|
"gradient_checkpointing_kwargs": null,
|
|
"include_for_metrics": [],
|
|
"eval_do_concat_batches": true,
|
|
"auto_find_batch_size": false,
|
|
"full_determinism": false,
|
|
"ddp_timeout": 1800,
|
|
"torch_compile": false,
|
|
"torch_compile_backend": null,
|
|
"torch_compile_mode": null,
|
|
"include_num_input_tokens_seen": "no",
|
|
"neftune_noise_alpha": null,
|
|
"optim_target_modules": null,
|
|
"batch_eval_metrics": false,
|
|
"eval_on_start": false,
|
|
"use_liger_kernel": false,
|
|
"liger_kernel_config": null,
|
|
"eval_use_gather_object": false,
|
|
"average_tokens_across_devices": true,
|
|
"use_cache": false
|
|
}
|
|
} |