Delete sft_args.json
Browse files- sft_args.json +0 -229
sft_args.json
DELETED
@@ -1,229 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"model_type": "qwen2-audio-7b-instruct",
|
3 |
-
"model_id_or_path": "qwen/Qwen2-Audio-7B-Instruct",
|
4 |
-
"model_revision": "master",
|
5 |
-
"sft_type": "full",
|
6 |
-
"freeze_parameters": 0.0,
|
7 |
-
"additional_trainable_parameters": [],
|
8 |
-
"tuner_backend": "peft",
|
9 |
-
"template_type": "qwen2-audio",
|
10 |
-
"output_dir": "/workdir/output/qwen2-audio-7b-instruct/v1-20240815-071601",
|
11 |
-
"add_output_dir_suffix": true,
|
12 |
-
"ddp_backend": "nccl",
|
13 |
-
"ddp_find_unused_parameters": null,
|
14 |
-
"ddp_broadcast_buffers": null,
|
15 |
-
"seed": 42,
|
16 |
-
"resume_from_checkpoint": null,
|
17 |
-
"resume_only_model": false,
|
18 |
-
"ignore_data_skip": false,
|
19 |
-
"dtype": "bf16",
|
20 |
-
"packing": false,
|
21 |
-
"train_backend": "transformers",
|
22 |
-
"tp": 1,
|
23 |
-
"pp": 1,
|
24 |
-
"min_lr": null,
|
25 |
-
"sequence_parallel": false,
|
26 |
-
"dataset": [
|
27 |
-
"data.json"
|
28 |
-
],
|
29 |
-
"val_dataset": [],
|
30 |
-
"dataset_seed": 42,
|
31 |
-
"dataset_test_ratio": 0.01,
|
32 |
-
"use_loss_scale": false,
|
33 |
-
"loss_scale_config_path": "/usr/local/lib/python3.10/dist-packages/swift/llm/agent/default_loss_scale_config.json",
|
34 |
-
"system": "You are a helpful assistant.",
|
35 |
-
"tools_prompt": "react_en",
|
36 |
-
"max_length": 2048,
|
37 |
-
"truncation_strategy": "delete",
|
38 |
-
"check_dataset_strategy": "none",
|
39 |
-
"streaming": false,
|
40 |
-
"streaming_val_size": 0,
|
41 |
-
"streaming_buffer_size": 16384,
|
42 |
-
"model_name": [
|
43 |
-
null,
|
44 |
-
null
|
45 |
-
],
|
46 |
-
"model_author": [
|
47 |
-
null,
|
48 |
-
null
|
49 |
-
],
|
50 |
-
"quant_method": null,
|
51 |
-
"quantization_bit": 0,
|
52 |
-
"hqq_axis": 0,
|
53 |
-
"hqq_dynamic_config_path": null,
|
54 |
-
"bnb_4bit_comp_dtype": "bf16",
|
55 |
-
"bnb_4bit_quant_type": "nf4",
|
56 |
-
"bnb_4bit_use_double_quant": true,
|
57 |
-
"bnb_4bit_quant_storage": null,
|
58 |
-
"rescale_image": -1,
|
59 |
-
"target_modules": "^(language_model|multi_modal_projector)(?!.*(lm_head|output|emb|wte|shared)).*",
|
60 |
-
"target_regex": null,
|
61 |
-
"modules_to_save": [],
|
62 |
-
"lora_rank": 8,
|
63 |
-
"lora_alpha": 32,
|
64 |
-
"lora_dropout": 0.05,
|
65 |
-
"lora_bias_trainable": "none",
|
66 |
-
"lora_dtype": "AUTO",
|
67 |
-
"lora_lr_ratio": null,
|
68 |
-
"use_rslora": false,
|
69 |
-
"use_dora": false,
|
70 |
-
"init_lora_weights": "true",
|
71 |
-
"fourier_n_frequency": 2000,
|
72 |
-
"fourier_scaling": 300.0,
|
73 |
-
"rope_scaling": null,
|
74 |
-
"boft_block_size": 4,
|
75 |
-
"boft_block_num": 0,
|
76 |
-
"boft_n_butterfly_factor": 1,
|
77 |
-
"boft_dropout": 0.0,
|
78 |
-
"vera_rank": 256,
|
79 |
-
"vera_projection_prng_key": 0,
|
80 |
-
"vera_dropout": 0.0,
|
81 |
-
"vera_d_initial": 0.1,
|
82 |
-
"adapter_act": "gelu",
|
83 |
-
"adapter_length": 128,
|
84 |
-
"use_galore": false,
|
85 |
-
"galore_target_modules": null,
|
86 |
-
"galore_rank": 128,
|
87 |
-
"galore_update_proj_gap": 50,
|
88 |
-
"galore_scale": 1.0,
|
89 |
-
"galore_proj_type": "std",
|
90 |
-
"galore_optim_per_parameter": false,
|
91 |
-
"galore_with_embedding": false,
|
92 |
-
"galore_quantization": false,
|
93 |
-
"galore_proj_quant": false,
|
94 |
-
"galore_proj_bits": 4,
|
95 |
-
"galore_proj_group_size": 256,
|
96 |
-
"galore_cos_threshold": 0.4,
|
97 |
-
"galore_gamma_proj": 2,
|
98 |
-
"galore_queue_size": 5,
|
99 |
-
"adalora_target_r": 8,
|
100 |
-
"adalora_init_r": 12,
|
101 |
-
"adalora_tinit": 0,
|
102 |
-
"adalora_tfinal": 0,
|
103 |
-
"adalora_deltaT": 1,
|
104 |
-
"adalora_beta1": 0.85,
|
105 |
-
"adalora_beta2": 0.85,
|
106 |
-
"adalora_orth_reg_weight": 0.5,
|
107 |
-
"ia3_feedforward_modules": [],
|
108 |
-
"llamapro_num_new_blocks": 4,
|
109 |
-
"llamapro_num_groups": null,
|
110 |
-
"neftune_noise_alpha": null,
|
111 |
-
"neftune_backend": "transformers",
|
112 |
-
"lisa_activated_layers": 0,
|
113 |
-
"lisa_step_interval": 20,
|
114 |
-
"gradient_checkpointing": true,
|
115 |
-
"deepspeed": null,
|
116 |
-
"batch_size": 2,
|
117 |
-
"eval_batch_size": 2,
|
118 |
-
"num_train_epochs": 1,
|
119 |
-
"max_steps": -1,
|
120 |
-
"optim": "adamw_8bit",
|
121 |
-
"adam_beta1": 0.9,
|
122 |
-
"adam_beta2": 0.95,
|
123 |
-
"adam_epsilon": 1e-08,
|
124 |
-
"learning_rate": 1e-05,
|
125 |
-
"weight_decay": 0.1,
|
126 |
-
"gradient_accumulation_steps": 256,
|
127 |
-
"max_grad_norm": 1,
|
128 |
-
"predict_with_generate": false,
|
129 |
-
"lr_scheduler_type": "cosine",
|
130 |
-
"lr_scheduler_kwargs": {},
|
131 |
-
"warmup_ratio": 0.05,
|
132 |
-
"warmup_steps": 1,
|
133 |
-
"eval_steps": 100000,
|
134 |
-
"save_steps": 100,
|
135 |
-
"save_only_model": true,
|
136 |
-
"save_total_limit": 2,
|
137 |
-
"logging_steps": 5,
|
138 |
-
"acc_steps": 1,
|
139 |
-
"dataloader_num_workers": 1,
|
140 |
-
"dataloader_pin_memory": false,
|
141 |
-
"dataloader_drop_last": false,
|
142 |
-
"push_to_hub": false,
|
143 |
-
"hub_model_id": null,
|
144 |
-
"hub_token": null,
|
145 |
-
"hub_private_repo": false,
|
146 |
-
"push_hub_strategy": "push_best",
|
147 |
-
"test_oom_error": false,
|
148 |
-
"disable_tqdm": false,
|
149 |
-
"lazy_tokenize": true,
|
150 |
-
"preprocess_num_proc": 1,
|
151 |
-
"use_flash_attn": null,
|
152 |
-
"ignore_args_error": false,
|
153 |
-
"check_model_is_latest": true,
|
154 |
-
"logging_dir": "/workdir/output/qwen2-audio-7b-instruct/v1-20240815-071601/runs",
|
155 |
-
"report_to": [
|
156 |
-
"tensorboard"
|
157 |
-
],
|
158 |
-
"acc_strategy": "token",
|
159 |
-
"save_on_each_node": false,
|
160 |
-
"evaluation_strategy": "steps",
|
161 |
-
"save_strategy": "steps",
|
162 |
-
"save_safetensors": true,
|
163 |
-
"gpu_memory_fraction": null,
|
164 |
-
"include_num_input_tokens_seen": false,
|
165 |
-
"local_repo_path": null,
|
166 |
-
"custom_register_path": null,
|
167 |
-
"custom_dataset_info": null,
|
168 |
-
"device_map_config_path": null,
|
169 |
-
"device_max_memory": [],
|
170 |
-
"max_new_tokens": 2048,
|
171 |
-
"do_sample": true,
|
172 |
-
"temperature": 0.3,
|
173 |
-
"top_k": 20,
|
174 |
-
"top_p": 0.7,
|
175 |
-
"repetition_penalty": 1.0,
|
176 |
-
"num_beams": 1,
|
177 |
-
"fsdp": "",
|
178 |
-
"fsdp_config": null,
|
179 |
-
"sequence_parallel_size": 1,
|
180 |
-
"model_layer_cls_name": null,
|
181 |
-
"metric_warmup_step": 0,
|
182 |
-
"fsdp_num": 1,
|
183 |
-
"per_device_train_batch_size": null,
|
184 |
-
"per_device_eval_batch_size": null,
|
185 |
-
"eval_strategy": null,
|
186 |
-
"self_cognition_sample": 0,
|
187 |
-
"train_dataset_mix_ratio": 0.0,
|
188 |
-
"train_dataset_mix_ds": [
|
189 |
-
"ms-bench"
|
190 |
-
],
|
191 |
-
"train_dataset_sample": -1,
|
192 |
-
"val_dataset_sample": null,
|
193 |
-
"safe_serialization": null,
|
194 |
-
"only_save_model": null,
|
195 |
-
"neftune_alpha": null,
|
196 |
-
"deepspeed_config_path": null,
|
197 |
-
"model_cache_dir": null,
|
198 |
-
"lora_dropout_p": null,
|
199 |
-
"lora_target_modules": [],
|
200 |
-
"lora_target_regex": null,
|
201 |
-
"lora_modules_to_save": [],
|
202 |
-
"boft_target_modules": [],
|
203 |
-
"boft_modules_to_save": [],
|
204 |
-
"vera_target_modules": [],
|
205 |
-
"vera_modules_to_save": [],
|
206 |
-
"ia3_target_modules": [],
|
207 |
-
"ia3_modules_to_save": [],
|
208 |
-
"custom_train_dataset_path": [],
|
209 |
-
"custom_val_dataset_path": [],
|
210 |
-
"use_self_cognition": false,
|
211 |
-
"is_multimodal": true,
|
212 |
-
"is_vision": false,
|
213 |
-
"lora_use_embedding": false,
|
214 |
-
"lora_use_all": false,
|
215 |
-
"lora_m2s_use_embedding": false,
|
216 |
-
"lora_m2s_use_ln": false,
|
217 |
-
"torch_dtype": "torch.bfloat16",
|
218 |
-
"fp16": false,
|
219 |
-
"bf16": true,
|
220 |
-
"rank": 0,
|
221 |
-
"local_rank": 0,
|
222 |
-
"world_size": 2,
|
223 |
-
"local_world_size": 2,
|
224 |
-
"bnb_4bit_compute_dtype": "torch.bfloat16",
|
225 |
-
"load_in_4bit": false,
|
226 |
-
"load_in_8bit": false,
|
227 |
-
"train_sampler_random": true,
|
228 |
-
"training_args": "Seq2SeqTrainingArguments(output_dir='/workdir/output/qwen2-audio-7b-instruct/v1-20240815-071601', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=2, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=256, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=1, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workdir/output/qwen2-audio-7b-instruct/v1-20240815-071601/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=True, 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=True, 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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=100000, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/workdir/output/qwen2-audio-7b-instruct/v1-20240815-071601', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, 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=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_8BIT: 'adamw_8bit'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, dataloader_pin_memory=False, 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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, 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, dispatch_batches=None, split_batches=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, eval_use_gather_object=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"chat_format\": \"chatml\",\n \"do_sample\": true,\n \"eos_token_id\": 151645,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 151643,\n \"temperature\": 0.3,\n \"top_k\": 20,\n \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
|
229 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|