novateur commited on
Commit
fc602db
·
verified ·
1 Parent(s): b0a0a69

Add files using upload-large-folder tool

Browse files
Files changed (43) hide show
  1. .gitattributes +1 -0
  2. v0-20250513-030424/args.json +335 -0
  3. v0-20250513-030424/checkpoint-9/added_tokens.json +24 -0
  4. v0-20250513-030424/checkpoint-9/args.json +335 -0
  5. v0-20250513-030424/checkpoint-9/chat_template.jinja +7 -0
  6. v0-20250513-030424/checkpoint-9/config.json +574 -0
  7. v0-20250513-030424/checkpoint-9/generation_config.json +4 -0
  8. v0-20250513-030424/checkpoint-9/merges.txt +0 -0
  9. v0-20250513-030424/checkpoint-9/model-00001-of-00003.safetensors +3 -0
  10. v0-20250513-030424/checkpoint-9/model-00002-of-00003.safetensors +3 -0
  11. v0-20250513-030424/checkpoint-9/model-00003-of-00003.safetensors +3 -0
  12. v0-20250513-030424/checkpoint-9/model.safetensors.index.json +0 -0
  13. v0-20250513-030424/checkpoint-9/optimizer.pt +3 -0
  14. v0-20250513-030424/checkpoint-9/preprocessor_config.json +31 -0
  15. v0-20250513-030424/checkpoint-9/rng_state.pth +3 -0
  16. v0-20250513-030424/checkpoint-9/scheduler.pt +3 -0
  17. v0-20250513-030424/checkpoint-9/special_tokens_map.json +38 -0
  18. v0-20250513-030424/checkpoint-9/spk_dict.pt +3 -0
  19. v0-20250513-030424/checkpoint-9/tokenizer.json +3 -0
  20. v0-20250513-030424/checkpoint-9/tokenizer_config.json +222 -0
  21. v0-20250513-030424/checkpoint-9/trainer_state.json +63 -0
  22. v0-20250513-030424/checkpoint-9/training_args.bin +3 -0
  23. v0-20250513-030424/checkpoint-9/vocab.json +0 -0
  24. v0-20250513-030424/images/eval_loss.png +0 -0
  25. v0-20250513-030424/images/eval_runtime.png +0 -0
  26. v0-20250513-030424/images/eval_samples_per_second.png +0 -0
  27. v0-20250513-030424/images/eval_steps_per_second.png +0 -0
  28. v0-20250513-030424/images/eval_token_acc.png +0 -0
  29. v0-20250513-030424/images/train_epoch.png +0 -0
  30. v0-20250513-030424/images/train_grad_norm.png +0 -0
  31. v0-20250513-030424/images/train_learning_rate.png +0 -0
  32. v0-20250513-030424/images/train_loss.png +0 -0
  33. v0-20250513-030424/images/train_memory(GiB).png +0 -0
  34. v0-20250513-030424/images/train_token_acc.png +0 -0
  35. v0-20250513-030424/images/train_total_flos.png +0 -0
  36. v0-20250513-030424/images/train_train_loss.png +0 -0
  37. v0-20250513-030424/images/train_train_runtime.png +0 -0
  38. v0-20250513-030424/images/train_train_samples_per_second.png +0 -0
  39. v0-20250513-030424/images/train_train_speed(iter_s).png +0 -0
  40. v0-20250513-030424/images/train_train_steps_per_second.png +0 -0
  41. v0-20250513-030424/logging.jsonl +5 -0
  42. v0-20250513-030424/runs/events.out.tfevents.1747076673.dsw-239952-646df5498f-2dn6v.54937.0 +3 -0
  43. v0-20250513-030424/val_dataset.jsonl +1 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ v0-20250513-030424/checkpoint-9/tokenizer.json filter=lfs diff=lfs merge=lfs -text
v0-20250513-030424/args.json ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/home/xj_data/jishengpeng/Code/Qwen2.5-Omni-3B",
3
+ "model_type": "qwen2_5_omni",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": null,
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "init_strategy": null,
15
+ "template": "qwen2_5_omni",
16
+ "system": null,
17
+ "max_length": null,
18
+ "truncation_strategy": "delete",
19
+ "max_pixels": null,
20
+ "agent_template": null,
21
+ "norm_bbox": null,
22
+ "response_prefix": null,
23
+ "padding_side": "right",
24
+ "loss_scale": "default",
25
+ "sequence_parallel_size": 1,
26
+ "use_chat_template": true,
27
+ "template_backend": "swift",
28
+ "dataset": [
29
+ "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/dataset.json"
30
+ ],
31
+ "val_dataset": [],
32
+ "split_dataset_ratio": 0.01,
33
+ "data_seed": 42,
34
+ "dataset_num_proc": 1,
35
+ "load_from_cache_file": false,
36
+ "dataset_shuffle": true,
37
+ "val_dataset_shuffle": false,
38
+ "streaming": false,
39
+ "interleave_prob": null,
40
+ "stopping_strategy": "first_exhausted",
41
+ "shuffle_buffer_size": 1000,
42
+ "download_mode": "reuse_dataset_if_exists",
43
+ "columns": {},
44
+ "strict": false,
45
+ "remove_unused_columns": true,
46
+ "model_name": [
47
+ null,
48
+ null
49
+ ],
50
+ "model_author": [
51
+ null,
52
+ null
53
+ ],
54
+ "custom_dataset_info": [],
55
+ "quant_method": null,
56
+ "quant_bits": null,
57
+ "hqq_axis": null,
58
+ "bnb_4bit_compute_dtype": "bfloat16",
59
+ "bnb_4bit_quant_type": "nf4",
60
+ "bnb_4bit_use_double_quant": true,
61
+ "bnb_4bit_quant_storage": null,
62
+ "max_new_tokens": 64,
63
+ "temperature": 0.0,
64
+ "top_k": null,
65
+ "top_p": null,
66
+ "repetition_penalty": null,
67
+ "num_beams": 1,
68
+ "stream": false,
69
+ "stop_words": [],
70
+ "logprobs": false,
71
+ "top_logprobs": null,
72
+ "ckpt_dir": null,
73
+ "lora_modules": [],
74
+ "tuner_backend": "peft",
75
+ "train_type": "full",
76
+ "adapters": [],
77
+ "external_plugins": [],
78
+ "seed": 42,
79
+ "model_kwargs": {},
80
+ "load_args": false,
81
+ "load_data_args": false,
82
+ "use_hf": false,
83
+ "hub_token": null,
84
+ "custom_register_path": [],
85
+ "ignore_args_error": false,
86
+ "use_swift_lora": false,
87
+ "output_dir": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424",
88
+ "overwrite_output_dir": false,
89
+ "do_train": false,
90
+ "do_eval": false,
91
+ "do_predict": false,
92
+ "eval_strategy": "steps",
93
+ "prediction_loss_only": false,
94
+ "per_device_train_batch_size": 2,
95
+ "per_device_eval_batch_size": 1,
96
+ "per_gpu_train_batch_size": null,
97
+ "per_gpu_eval_batch_size": null,
98
+ "gradient_accumulation_steps": null,
99
+ "eval_accumulation_steps": null,
100
+ "eval_delay": 0,
101
+ "torch_empty_cache_steps": null,
102
+ "learning_rate": 1e-05,
103
+ "weight_decay": 0.1,
104
+ "adam_beta1": 0.9,
105
+ "adam_beta2": 0.95,
106
+ "adam_epsilon": 1e-08,
107
+ "max_grad_norm": 1.0,
108
+ "num_train_epochs": 3.0,
109
+ "max_steps": -1,
110
+ "lr_scheduler_type": "cosine",
111
+ "lr_scheduler_kwargs": null,
112
+ "warmup_ratio": 0.0,
113
+ "warmup_steps": 0,
114
+ "log_level": "passive",
115
+ "log_level_replica": "warning",
116
+ "log_on_each_node": true,
117
+ "logging_dir": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/runs",
118
+ "logging_strategy": "steps",
119
+ "logging_first_step": true,
120
+ "logging_steps": 5,
121
+ "logging_nan_inf_filter": true,
122
+ "save_strategy": "steps",
123
+ "save_steps": 500,
124
+ "save_total_limit": null,
125
+ "save_safetensors": true,
126
+ "save_on_each_node": false,
127
+ "save_only_model": false,
128
+ "restore_callback_states_from_checkpoint": false,
129
+ "no_cuda": false,
130
+ "use_cpu": false,
131
+ "use_mps_device": false,
132
+ "jit_mode_eval": false,
133
+ "use_ipex": false,
134
+ "bf16": true,
135
+ "fp16": false,
136
+ "fp16_opt_level": "O1",
137
+ "half_precision_backend": "auto",
138
+ "bf16_full_eval": false,
139
+ "fp16_full_eval": false,
140
+ "tf32": null,
141
+ "local_rank": -1,
142
+ "ddp_backend": null,
143
+ "tpu_num_cores": null,
144
+ "tpu_metrics_debug": false,
145
+ "debug": null,
146
+ "dataloader_drop_last": false,
147
+ "eval_steps": 500,
148
+ "dataloader_num_workers": null,
149
+ "dataloader_prefetch_factor": null,
150
+ "past_index": -1,
151
+ "run_name": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424",
152
+ "disable_tqdm": null,
153
+ "label_names": null,
154
+ "load_best_model_at_end": false,
155
+ "metric_for_best_model": "loss",
156
+ "greater_is_better": false,
157
+ "ignore_data_skip": false,
158
+ "fsdp": "",
159
+ "fsdp_min_num_params": 0,
160
+ "fsdp_config": null,
161
+ "fsdp_transformer_layer_cls_to_wrap": null,
162
+ "accelerator_config": {
163
+ "dispatch_batches": false
164
+ },
165
+ "deepspeed": null,
166
+ "label_smoothing_factor": 0.0,
167
+ "optim": "adamw_torch",
168
+ "optim_args": null,
169
+ "adafactor": false,
170
+ "group_by_length": false,
171
+ "length_column_name": "length",
172
+ "report_to": [
173
+ "tensorboard"
174
+ ],
175
+ "ddp_find_unused_parameters": null,
176
+ "ddp_bucket_cap_mb": null,
177
+ "ddp_broadcast_buffers": null,
178
+ "dataloader_pin_memory": true,
179
+ "dataloader_persistent_workers": false,
180
+ "skip_memory_metrics": true,
181
+ "use_legacy_prediction_loop": false,
182
+ "push_to_hub": false,
183
+ "resume_from_checkpoint": null,
184
+ "hub_model_id": null,
185
+ "hub_strategy": "every_save",
186
+ "hub_private_repo": null,
187
+ "hub_always_push": false,
188
+ "gradient_checkpointing": true,
189
+ "gradient_checkpointing_kwargs": null,
190
+ "include_inputs_for_metrics": false,
191
+ "include_for_metrics": [],
192
+ "eval_do_concat_batches": true,
193
+ "fp16_backend": "auto",
194
+ "push_to_hub_model_id": null,
195
+ "push_to_hub_organization": null,
196
+ "push_to_hub_token": null,
197
+ "mp_parameters": "",
198
+ "auto_find_batch_size": false,
199
+ "full_determinism": false,
200
+ "torchdynamo": null,
201
+ "ray_scope": "last",
202
+ "ddp_timeout": 1800,
203
+ "torch_compile": false,
204
+ "torch_compile_backend": null,
205
+ "torch_compile_mode": null,
206
+ "include_tokens_per_second": false,
207
+ "include_num_input_tokens_seen": false,
208
+ "neftune_noise_alpha": null,
209
+ "optim_target_modules": null,
210
+ "batch_eval_metrics": false,
211
+ "eval_on_start": false,
212
+ "use_liger_kernel": false,
213
+ "eval_use_gather_object": false,
214
+ "average_tokens_across_devices": false,
215
+ "sortish_sampler": false,
216
+ "predict_with_generate": false,
217
+ "generation_max_length": null,
218
+ "generation_num_beams": null,
219
+ "generation_config": null,
220
+ "check_model": true,
221
+ "acc_strategy": "token",
222
+ "train_dataloader_shuffle": true,
223
+ "max_epochs": null,
224
+ "metric_warmup_step": 0,
225
+ "fsdp_num": 1,
226
+ "acc_steps": 1,
227
+ "eval_use_evalscope": false,
228
+ "eval_datasets": [],
229
+ "eval_limit": null,
230
+ "eval_datasets_args": null,
231
+ "eval_generation_config": null,
232
+ "freeze_parameters": [
233
+ "thinker.audio_tower",
234
+ "thinker.visual",
235
+ "thinker.audio_tower.proj",
236
+ "thinker.visual.merger",
237
+ "talker",
238
+ "token2wav"
239
+ ],
240
+ "freeze_parameters_regex": null,
241
+ "freeze_parameters_ratio": 0.0,
242
+ "trainable_parameters": [],
243
+ "trainable_parameters_regex": null,
244
+ "freeze_llm": false,
245
+ "freeze_vit": true,
246
+ "freeze_aligner": true,
247
+ "target_modules": [
248
+ "all-linear"
249
+ ],
250
+ "target_regex": null,
251
+ "modules_to_save": [],
252
+ "lora_rank": 8,
253
+ "lora_alpha": 32,
254
+ "lora_dropout": 0.05,
255
+ "lora_bias": "none",
256
+ "lora_dtype": null,
257
+ "lorap_lr_ratio": null,
258
+ "use_rslora": false,
259
+ "use_dora": false,
260
+ "lora_ga_batch_size": 2,
261
+ "lora_ga_iters": 2,
262
+ "lora_ga_max_length": 1024,
263
+ "lora_ga_direction": "ArB2r",
264
+ "lora_ga_scale": "stable",
265
+ "lora_ga_stable_gamma": 16,
266
+ "init_weights": true,
267
+ "fourier_n_frequency": 2000,
268
+ "fourier_scaling": 300.0,
269
+ "boft_block_size": 4,
270
+ "boft_block_num": 0,
271
+ "boft_n_butterfly_factor": 1,
272
+ "boft_dropout": 0.0,
273
+ "vera_rank": 256,
274
+ "vera_projection_prng_key": 0,
275
+ "vera_dropout": 0.0,
276
+ "vera_d_initial": 0.1,
277
+ "adapter_act": "gelu",
278
+ "adapter_length": 128,
279
+ "use_galore": false,
280
+ "galore_target_modules": null,
281
+ "galore_rank": 128,
282
+ "galore_update_proj_gap": 50,
283
+ "galore_scale": 1.0,
284
+ "galore_proj_type": "std",
285
+ "galore_optim_per_parameter": false,
286
+ "galore_with_embedding": false,
287
+ "galore_quantization": false,
288
+ "galore_proj_quant": false,
289
+ "galore_proj_bits": 4,
290
+ "galore_proj_group_size": 256,
291
+ "galore_cos_threshold": 0.4,
292
+ "galore_gamma_proj": 2,
293
+ "galore_queue_size": 5,
294
+ "adalora_target_r": 8,
295
+ "adalora_init_r": 12,
296
+ "adalora_tinit": 0,
297
+ "adalora_tfinal": 0,
298
+ "adalora_deltaT": 1,
299
+ "adalora_beta1": 0.85,
300
+ "adalora_beta2": 0.85,
301
+ "adalora_orth_reg_weight": 0.5,
302
+ "llamapro_num_new_blocks": 4,
303
+ "llamapro_num_groups": null,
304
+ "lisa_activated_layers": 0,
305
+ "lisa_step_interval": 20,
306
+ "reft_layer_key": null,
307
+ "reft_layers": null,
308
+ "reft_rank": 4,
309
+ "reft_intervention_type": "LoreftIntervention",
310
+ "reft_args": null,
311
+ "swanlab_token": null,
312
+ "swanlab_project": null,
313
+ "swanlab_workspace": null,
314
+ "swanlab_exp_name": null,
315
+ "swanlab_mode": "cloud",
316
+ "add_version": true,
317
+ "resume_only_model": false,
318
+ "create_checkpoint_symlink": false,
319
+ "packing": false,
320
+ "lazy_tokenize": true,
321
+ "loss_type": null,
322
+ "optimizer": null,
323
+ "metric": null,
324
+ "zero_hpz_partition_size": null,
325
+ "rank": -1,
326
+ "global_world_size": 1,
327
+ "local_world_size": 1,
328
+ "model_suffix": "Qwen2.5-Omni-3B",
329
+ "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/home/xj_data/jishengpeng/Code/Qwen2.5-Omni-3B', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
330
+ "model_meta": "ModelMeta(model_type='qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7f21a6587880>, model_arch='qwen2_5_omni', architectures=['Qwen2_5OmniModel'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=['*.bin', '*.safetensors'], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=[])",
331
+ "model_dir": "/home/xj_data/jishengpeng/Code/Qwen2.5-Omni-3B",
332
+ "hub": "<class 'swift.hub.hub.MSHub'>",
333
+ "evaluation_strategy": "steps",
334
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424', 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=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, 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=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, 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=42, 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=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=500, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424', 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_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, 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, 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, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
335
+ }
v0-20250513-030424/checkpoint-9/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|AUDIO|>": 151646,
5
+ "<|IMAGE|>": 151655,
6
+ "<|VIDEO|>": 151656,
7
+ "<|audio_bos|>": 151647,
8
+ "<|audio_eos|>": 151648,
9
+ "<|box_end|>": 151649,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|vision_bos|>": 151652,
22
+ "<|vision_eos|>": 151653,
23
+ "<|vision_pad|>": 151654
24
+ }
v0-20250513-030424/checkpoint-9/args.json ADDED
@@ -0,0 +1,335 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/home/xj_data/jishengpeng/Code/Qwen2.5-Omni-3B",
3
+ "model_type": "qwen2_5_omni",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": null,
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "init_strategy": null,
15
+ "template": "qwen2_5_omni",
16
+ "system": null,
17
+ "max_length": null,
18
+ "truncation_strategy": "delete",
19
+ "max_pixels": null,
20
+ "agent_template": null,
21
+ "norm_bbox": null,
22
+ "response_prefix": null,
23
+ "padding_side": "right",
24
+ "loss_scale": "default",
25
+ "sequence_parallel_size": 1,
26
+ "use_chat_template": true,
27
+ "template_backend": "swift",
28
+ "dataset": [
29
+ "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/dataset.json"
30
+ ],
31
+ "val_dataset": [],
32
+ "split_dataset_ratio": 0.01,
33
+ "data_seed": 42,
34
+ "dataset_num_proc": 1,
35
+ "load_from_cache_file": false,
36
+ "dataset_shuffle": true,
37
+ "val_dataset_shuffle": false,
38
+ "streaming": false,
39
+ "interleave_prob": null,
40
+ "stopping_strategy": "first_exhausted",
41
+ "shuffle_buffer_size": 1000,
42
+ "download_mode": "reuse_dataset_if_exists",
43
+ "columns": {},
44
+ "strict": false,
45
+ "remove_unused_columns": true,
46
+ "model_name": [
47
+ null,
48
+ null
49
+ ],
50
+ "model_author": [
51
+ null,
52
+ null
53
+ ],
54
+ "custom_dataset_info": [],
55
+ "quant_method": null,
56
+ "quant_bits": null,
57
+ "hqq_axis": null,
58
+ "bnb_4bit_compute_dtype": "bfloat16",
59
+ "bnb_4bit_quant_type": "nf4",
60
+ "bnb_4bit_use_double_quant": true,
61
+ "bnb_4bit_quant_storage": null,
62
+ "max_new_tokens": 64,
63
+ "temperature": 0.0,
64
+ "top_k": null,
65
+ "top_p": null,
66
+ "repetition_penalty": null,
67
+ "num_beams": 1,
68
+ "stream": false,
69
+ "stop_words": [],
70
+ "logprobs": false,
71
+ "top_logprobs": null,
72
+ "ckpt_dir": null,
73
+ "lora_modules": [],
74
+ "tuner_backend": "peft",
75
+ "train_type": "full",
76
+ "adapters": [],
77
+ "external_plugins": [],
78
+ "seed": 42,
79
+ "model_kwargs": {},
80
+ "load_args": false,
81
+ "load_data_args": false,
82
+ "use_hf": false,
83
+ "hub_token": null,
84
+ "custom_register_path": [],
85
+ "ignore_args_error": false,
86
+ "use_swift_lora": false,
87
+ "output_dir": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424",
88
+ "overwrite_output_dir": false,
89
+ "do_train": false,
90
+ "do_eval": false,
91
+ "do_predict": false,
92
+ "eval_strategy": "steps",
93
+ "prediction_loss_only": false,
94
+ "per_device_train_batch_size": 2,
95
+ "per_device_eval_batch_size": 1,
96
+ "per_gpu_train_batch_size": null,
97
+ "per_gpu_eval_batch_size": null,
98
+ "gradient_accumulation_steps": null,
99
+ "eval_accumulation_steps": null,
100
+ "eval_delay": 0,
101
+ "torch_empty_cache_steps": null,
102
+ "learning_rate": 1e-05,
103
+ "weight_decay": 0.1,
104
+ "adam_beta1": 0.9,
105
+ "adam_beta2": 0.95,
106
+ "adam_epsilon": 1e-08,
107
+ "max_grad_norm": 1.0,
108
+ "num_train_epochs": 3.0,
109
+ "max_steps": -1,
110
+ "lr_scheduler_type": "cosine",
111
+ "lr_scheduler_kwargs": null,
112
+ "warmup_ratio": 0.0,
113
+ "warmup_steps": 0,
114
+ "log_level": "passive",
115
+ "log_level_replica": "warning",
116
+ "log_on_each_node": true,
117
+ "logging_dir": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/runs",
118
+ "logging_strategy": "steps",
119
+ "logging_first_step": true,
120
+ "logging_steps": 5,
121
+ "logging_nan_inf_filter": true,
122
+ "save_strategy": "steps",
123
+ "save_steps": 500,
124
+ "save_total_limit": null,
125
+ "save_safetensors": true,
126
+ "save_on_each_node": false,
127
+ "save_only_model": false,
128
+ "restore_callback_states_from_checkpoint": false,
129
+ "no_cuda": false,
130
+ "use_cpu": false,
131
+ "use_mps_device": false,
132
+ "jit_mode_eval": false,
133
+ "use_ipex": false,
134
+ "bf16": true,
135
+ "fp16": false,
136
+ "fp16_opt_level": "O1",
137
+ "half_precision_backend": "auto",
138
+ "bf16_full_eval": false,
139
+ "fp16_full_eval": false,
140
+ "tf32": null,
141
+ "local_rank": -1,
142
+ "ddp_backend": null,
143
+ "tpu_num_cores": null,
144
+ "tpu_metrics_debug": false,
145
+ "debug": null,
146
+ "dataloader_drop_last": false,
147
+ "eval_steps": 500,
148
+ "dataloader_num_workers": null,
149
+ "dataloader_prefetch_factor": null,
150
+ "past_index": -1,
151
+ "run_name": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424",
152
+ "disable_tqdm": null,
153
+ "label_names": null,
154
+ "load_best_model_at_end": false,
155
+ "metric_for_best_model": "loss",
156
+ "greater_is_better": false,
157
+ "ignore_data_skip": false,
158
+ "fsdp": "",
159
+ "fsdp_min_num_params": 0,
160
+ "fsdp_config": null,
161
+ "fsdp_transformer_layer_cls_to_wrap": null,
162
+ "accelerator_config": {
163
+ "dispatch_batches": false
164
+ },
165
+ "deepspeed": null,
166
+ "label_smoothing_factor": 0.0,
167
+ "optim": "adamw_torch",
168
+ "optim_args": null,
169
+ "adafactor": false,
170
+ "group_by_length": false,
171
+ "length_column_name": "length",
172
+ "report_to": [
173
+ "tensorboard"
174
+ ],
175
+ "ddp_find_unused_parameters": null,
176
+ "ddp_bucket_cap_mb": null,
177
+ "ddp_broadcast_buffers": null,
178
+ "dataloader_pin_memory": true,
179
+ "dataloader_persistent_workers": false,
180
+ "skip_memory_metrics": true,
181
+ "use_legacy_prediction_loop": false,
182
+ "push_to_hub": false,
183
+ "resume_from_checkpoint": null,
184
+ "hub_model_id": null,
185
+ "hub_strategy": "every_save",
186
+ "hub_private_repo": null,
187
+ "hub_always_push": false,
188
+ "gradient_checkpointing": true,
189
+ "gradient_checkpointing_kwargs": null,
190
+ "include_inputs_for_metrics": false,
191
+ "include_for_metrics": [],
192
+ "eval_do_concat_batches": true,
193
+ "fp16_backend": "auto",
194
+ "push_to_hub_model_id": null,
195
+ "push_to_hub_organization": null,
196
+ "push_to_hub_token": null,
197
+ "mp_parameters": "",
198
+ "auto_find_batch_size": false,
199
+ "full_determinism": false,
200
+ "torchdynamo": null,
201
+ "ray_scope": "last",
202
+ "ddp_timeout": 1800,
203
+ "torch_compile": false,
204
+ "torch_compile_backend": null,
205
+ "torch_compile_mode": null,
206
+ "include_tokens_per_second": false,
207
+ "include_num_input_tokens_seen": false,
208
+ "neftune_noise_alpha": null,
209
+ "optim_target_modules": null,
210
+ "batch_eval_metrics": false,
211
+ "eval_on_start": false,
212
+ "use_liger_kernel": false,
213
+ "eval_use_gather_object": false,
214
+ "average_tokens_across_devices": false,
215
+ "sortish_sampler": false,
216
+ "predict_with_generate": false,
217
+ "generation_max_length": null,
218
+ "generation_num_beams": null,
219
+ "generation_config": null,
220
+ "check_model": true,
221
+ "acc_strategy": "token",
222
+ "train_dataloader_shuffle": true,
223
+ "max_epochs": null,
224
+ "metric_warmup_step": 0,
225
+ "fsdp_num": 1,
226
+ "acc_steps": 1,
227
+ "eval_use_evalscope": false,
228
+ "eval_datasets": [],
229
+ "eval_limit": null,
230
+ "eval_datasets_args": null,
231
+ "eval_generation_config": null,
232
+ "freeze_parameters": [
233
+ "thinker.audio_tower",
234
+ "thinker.visual",
235
+ "thinker.audio_tower.proj",
236
+ "thinker.visual.merger",
237
+ "talker",
238
+ "token2wav"
239
+ ],
240
+ "freeze_parameters_regex": null,
241
+ "freeze_parameters_ratio": 0.0,
242
+ "trainable_parameters": [],
243
+ "trainable_parameters_regex": null,
244
+ "freeze_llm": false,
245
+ "freeze_vit": true,
246
+ "freeze_aligner": true,
247
+ "target_modules": [
248
+ "all-linear"
249
+ ],
250
+ "target_regex": null,
251
+ "modules_to_save": [],
252
+ "lora_rank": 8,
253
+ "lora_alpha": 32,
254
+ "lora_dropout": 0.05,
255
+ "lora_bias": "none",
256
+ "lora_dtype": null,
257
+ "lorap_lr_ratio": null,
258
+ "use_rslora": false,
259
+ "use_dora": false,
260
+ "lora_ga_batch_size": 2,
261
+ "lora_ga_iters": 2,
262
+ "lora_ga_max_length": 1024,
263
+ "lora_ga_direction": "ArB2r",
264
+ "lora_ga_scale": "stable",
265
+ "lora_ga_stable_gamma": 16,
266
+ "init_weights": true,
267
+ "fourier_n_frequency": 2000,
268
+ "fourier_scaling": 300.0,
269
+ "boft_block_size": 4,
270
+ "boft_block_num": 0,
271
+ "boft_n_butterfly_factor": 1,
272
+ "boft_dropout": 0.0,
273
+ "vera_rank": 256,
274
+ "vera_projection_prng_key": 0,
275
+ "vera_dropout": 0.0,
276
+ "vera_d_initial": 0.1,
277
+ "adapter_act": "gelu",
278
+ "adapter_length": 128,
279
+ "use_galore": false,
280
+ "galore_target_modules": null,
281
+ "galore_rank": 128,
282
+ "galore_update_proj_gap": 50,
283
+ "galore_scale": 1.0,
284
+ "galore_proj_type": "std",
285
+ "galore_optim_per_parameter": false,
286
+ "galore_with_embedding": false,
287
+ "galore_quantization": false,
288
+ "galore_proj_quant": false,
289
+ "galore_proj_bits": 4,
290
+ "galore_proj_group_size": 256,
291
+ "galore_cos_threshold": 0.4,
292
+ "galore_gamma_proj": 2,
293
+ "galore_queue_size": 5,
294
+ "adalora_target_r": 8,
295
+ "adalora_init_r": 12,
296
+ "adalora_tinit": 0,
297
+ "adalora_tfinal": 0,
298
+ "adalora_deltaT": 1,
299
+ "adalora_beta1": 0.85,
300
+ "adalora_beta2": 0.85,
301
+ "adalora_orth_reg_weight": 0.5,
302
+ "llamapro_num_new_blocks": 4,
303
+ "llamapro_num_groups": null,
304
+ "lisa_activated_layers": 0,
305
+ "lisa_step_interval": 20,
306
+ "reft_layer_key": null,
307
+ "reft_layers": null,
308
+ "reft_rank": 4,
309
+ "reft_intervention_type": "LoreftIntervention",
310
+ "reft_args": null,
311
+ "swanlab_token": null,
312
+ "swanlab_project": null,
313
+ "swanlab_workspace": null,
314
+ "swanlab_exp_name": null,
315
+ "swanlab_mode": "cloud",
316
+ "add_version": true,
317
+ "resume_only_model": false,
318
+ "create_checkpoint_symlink": false,
319
+ "packing": false,
320
+ "lazy_tokenize": true,
321
+ "loss_type": null,
322
+ "optimizer": null,
323
+ "metric": null,
324
+ "zero_hpz_partition_size": null,
325
+ "rank": -1,
326
+ "global_world_size": 1,
327
+ "local_world_size": 1,
328
+ "model_suffix": "Qwen2.5-Omni-3B",
329
+ "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/home/xj_data/jishengpeng/Code/Qwen2.5-Omni-3B', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
330
+ "model_meta": "ModelMeta(model_type='qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7f21a6587880>, model_arch='qwen2_5_omni', architectures=['Qwen2_5OmniModel'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=['*.bin', '*.safetensors'], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=[])",
331
+ "model_dir": "/home/xj_data/jishengpeng/Code/Qwen2.5-Omni-3B",
332
+ "hub": "<class 'swift.hub.hub.MSHub'>",
333
+ "evaluation_strategy": "steps",
334
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424', 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=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, 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=1.0, num_train_epochs=3.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, 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=42, 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=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=500, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424', 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_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, 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, 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, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
335
+ }
v0-20250513-030424/checkpoint-9/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
v0-20250513-030424/checkpoint-9/config.json ADDED
@@ -0,0 +1,574 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5OmniForConditionalGeneration"
4
+ ],
5
+ "enable_audio_output": true,
6
+ "enable_talker": true,
7
+ "hidden_size": 2048,
8
+ "keys_to_ignore_at_inference": [
9
+ "past_key_values",
10
+ "hidden_states",
11
+ "attention_mask"
12
+ ],
13
+ "model_type": "qwen2_5_omni",
14
+ "pad_token_id": 151643,
15
+ "talker_config": {
16
+ "_attn_implementation_autoset": true,
17
+ "architectures": [
18
+ "Qwen2OmniTalkerForConditionalGeneration"
19
+ ],
20
+ "attention_dropout": 0.0,
21
+ "audio_end_token_id": 151648,
22
+ "audio_start_token_id": 151647,
23
+ "audio_token_index": 151646,
24
+ "embedding_size": 2048,
25
+ "head_dim": 64,
26
+ "hidden_act": "silu",
27
+ "hidden_size": 896,
28
+ "image_token_index": 151655,
29
+ "init_std": 0.02,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4864,
32
+ "max_position_embeddings": 32768,
33
+ "max_window_layers": 28,
34
+ "model_type": "qwen2_5_omni_talker",
35
+ "num_attention_heads": 14,
36
+ "num_hidden_layers": 24,
37
+ "num_key_value_heads": 2,
38
+ "position_id_per_seconds": 25,
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": {
41
+ "mrope_section": [
42
+ 16,
43
+ 16,
44
+ 0
45
+ ],
46
+ "rope_type": "default",
47
+ "type": "default"
48
+ },
49
+ "rope_theta": 1000000.0,
50
+ "seconds_per_chunk": 2,
51
+ "sliding_window": 32768,
52
+ "spatial_merge_size": 2,
53
+ "torch_dtype": "bfloat16",
54
+ "tts_codec_end_token_id": 8294,
55
+ "tts_codec_mask_token_id": 8296,
56
+ "tts_codec_pad_token_id": 8292,
57
+ "tts_codec_start_token_id": 8293,
58
+ "tts_text_end_token_id": 151861,
59
+ "tts_text_pad_token_id": 151859,
60
+ "tts_text_start_token_id": 151860,
61
+ "use_cache": false,
62
+ "use_sliding_window": false,
63
+ "video_token_index": 151656,
64
+ "vision_end_token_id": 151653,
65
+ "vision_start_token_id": 151652,
66
+ "vocab_size": 8448
67
+ },
68
+ "thinker_config": {
69
+ "_attn_implementation_autoset": true,
70
+ "architectures": [
71
+ "Qwen2OmniNaViTThinkerForConditionalGeneration"
72
+ ],
73
+ "audio_config": {
74
+ "_attn_implementation_autoset": true,
75
+ "activation_dropout": 0.0,
76
+ "activation_function": "gelu",
77
+ "add_cross_attention": false,
78
+ "architectures": null,
79
+ "attention_dropout": 0.0,
80
+ "bad_words_ids": null,
81
+ "begin_suppress_tokens": null,
82
+ "bos_token_id": null,
83
+ "chunk_size_feed_forward": 0,
84
+ "cross_attention_hidden_size": null,
85
+ "d_model": 1280,
86
+ "decoder_start_token_id": null,
87
+ "diversity_penalty": 0.0,
88
+ "do_sample": false,
89
+ "dropout": 0.0,
90
+ "early_stopping": false,
91
+ "encoder_attention_heads": 20,
92
+ "encoder_ffn_dim": 5120,
93
+ "encoder_layerdrop": 0.0,
94
+ "encoder_layers": 32,
95
+ "encoder_no_repeat_ngram_size": 0,
96
+ "eos_token_id": null,
97
+ "exponential_decay_length_penalty": null,
98
+ "finetuning_task": null,
99
+ "forced_bos_token_id": null,
100
+ "forced_eos_token_id": null,
101
+ "id2label": {
102
+ "0": "LABEL_0",
103
+ "1": "LABEL_1"
104
+ },
105
+ "init_std": 0.02,
106
+ "initializer_range": 0.02,
107
+ "is_decoder": false,
108
+ "is_encoder_decoder": false,
109
+ "label2id": {
110
+ "LABEL_0": 0,
111
+ "LABEL_1": 1
112
+ },
113
+ "length_penalty": 1.0,
114
+ "max_length": 20,
115
+ "max_source_positions": 1500,
116
+ "min_length": 0,
117
+ "model_type": "qwen2_5_omni_audio_encoder",
118
+ "n_window": 100,
119
+ "no_repeat_ngram_size": 0,
120
+ "num_beam_groups": 1,
121
+ "num_beams": 1,
122
+ "num_hidden_layers": 32,
123
+ "num_mel_bins": 128,
124
+ "num_return_sequences": 1,
125
+ "output_attentions": false,
126
+ "output_dim": 2048,
127
+ "output_hidden_states": false,
128
+ "output_scores": false,
129
+ "pad_token_id": null,
130
+ "prefix": null,
131
+ "problem_type": null,
132
+ "pruned_heads": {},
133
+ "remove_invalid_values": false,
134
+ "repetition_penalty": 1.0,
135
+ "return_dict": true,
136
+ "return_dict_in_generate": false,
137
+ "scale_embedding": false,
138
+ "sep_token_id": null,
139
+ "suppress_tokens": null,
140
+ "task_specific_params": null,
141
+ "temperature": 1.0,
142
+ "tf_legacy_loss": false,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": true,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torch_dtype": null,
149
+ "torchscript": false,
150
+ "typical_p": 1.0,
151
+ "use_bfloat16": false
152
+ },
153
+ "audio_end_token_id": 151648,
154
+ "audio_start_token_id": 151647,
155
+ "audio_token_index": 151646,
156
+ "bos_token_id": 151644,
157
+ "eos_token_id": 151645,
158
+ "ignore_index": -100,
159
+ "image_token_index": 151655,
160
+ "init_std": 0.02,
161
+ "initializer_range": 0.02,
162
+ "model_type": "qwen2_5_omni_thinker",
163
+ "pad_token_id": 151643,
164
+ "position_id_per_seconds": 25,
165
+ "seconds_per_chunk": 2,
166
+ "text_config": {
167
+ "_attn_implementation_autoset": false,
168
+ "add_cross_attention": false,
169
+ "architectures": null,
170
+ "attention_dropout": 0.0,
171
+ "bad_words_ids": null,
172
+ "begin_suppress_tokens": null,
173
+ "bos_token_id": null,
174
+ "chunk_size_feed_forward": 0,
175
+ "cross_attention_hidden_size": null,
176
+ "decoder_start_token_id": null,
177
+ "diversity_penalty": 0.0,
178
+ "do_sample": false,
179
+ "early_stopping": false,
180
+ "encoder_no_repeat_ngram_size": 0,
181
+ "eos_token_id": null,
182
+ "exponential_decay_length_penalty": null,
183
+ "finetuning_task": null,
184
+ "forced_bos_token_id": null,
185
+ "forced_eos_token_id": null,
186
+ "hidden_act": "silu",
187
+ "hidden_size": 2048,
188
+ "id2label": {
189
+ "0": "LABEL_0",
190
+ "1": "LABEL_1"
191
+ },
192
+ "init_std": 0.02,
193
+ "initializer_range": 0.02,
194
+ "intermediate_size": 11008,
195
+ "is_decoder": false,
196
+ "is_encoder_decoder": false,
197
+ "label2id": {
198
+ "LABEL_0": 0,
199
+ "LABEL_1": 1
200
+ },
201
+ "length_penalty": 1.0,
202
+ "max_length": 20,
203
+ "max_position_embeddings": 32768,
204
+ "max_window_layers": 70,
205
+ "min_length": 0,
206
+ "model_type": "qwen2_5_omni_text",
207
+ "no_repeat_ngram_size": 0,
208
+ "num_attention_heads": 16,
209
+ "num_beam_groups": 1,
210
+ "num_beams": 1,
211
+ "num_hidden_layers": 36,
212
+ "num_key_value_heads": 2,
213
+ "num_return_sequences": 1,
214
+ "output_attentions": false,
215
+ "output_hidden_states": false,
216
+ "output_scores": false,
217
+ "pad_token_id": null,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "pruned_heads": {},
221
+ "remove_invalid_values": false,
222
+ "repetition_penalty": 1.0,
223
+ "return_dict": true,
224
+ "return_dict_in_generate": false,
225
+ "rms_norm_eps": 1e-06,
226
+ "rope_scaling": {
227
+ "mrope_section": [
228
+ 16,
229
+ 24,
230
+ 24
231
+ ],
232
+ "rope_type": "default",
233
+ "type": "default"
234
+ },
235
+ "rope_theta": 1000000.0,
236
+ "sep_token_id": null,
237
+ "sliding_window": 32768,
238
+ "suppress_tokens": null,
239
+ "task_specific_params": null,
240
+ "temperature": 1.0,
241
+ "tf_legacy_loss": false,
242
+ "tie_encoder_decoder": false,
243
+ "tie_word_embeddings": false,
244
+ "tokenizer_class": null,
245
+ "top_k": 50,
246
+ "top_p": 1.0,
247
+ "torch_dtype": null,
248
+ "torchscript": false,
249
+ "typical_p": 1.0,
250
+ "use_bfloat16": false,
251
+ "use_cache": true,
252
+ "use_sliding_window": false,
253
+ "vocab_size": 151936
254
+ },
255
+ "torch_dtype": "bfloat16",
256
+ "user_token_id": 872,
257
+ "video_token_index": 151656,
258
+ "vision_config": {
259
+ "_attn_implementation_autoset": true,
260
+ "add_cross_attention": false,
261
+ "architectures": null,
262
+ "bad_words_ids": null,
263
+ "begin_suppress_tokens": null,
264
+ "bos_token_id": null,
265
+ "chunk_size_feed_forward": 0,
266
+ "cross_attention_hidden_size": null,
267
+ "decoder_start_token_id": null,
268
+ "depth": 32,
269
+ "diversity_penalty": 0.0,
270
+ "do_sample": false,
271
+ "early_stopping": false,
272
+ "embed_dim": 1280,
273
+ "encoder_no_repeat_ngram_size": 0,
274
+ "eos_token_id": null,
275
+ "exponential_decay_length_penalty": null,
276
+ "finetuning_task": null,
277
+ "forced_bos_token_id": null,
278
+ "forced_eos_token_id": null,
279
+ "fullatt_block_indexes": [
280
+ 7,
281
+ 15,
282
+ 23,
283
+ 31
284
+ ],
285
+ "hidden_act": "silu",
286
+ "hidden_size": 1280,
287
+ "id2label": {
288
+ "0": "LABEL_0",
289
+ "1": "LABEL_1"
290
+ },
291
+ "in_channels": 3,
292
+ "in_chans": 3,
293
+ "init_std": 0.02,
294
+ "initializer_range": 0.02,
295
+ "intermediate_size": 3420,
296
+ "is_decoder": false,
297
+ "is_encoder_decoder": false,
298
+ "label2id": {
299
+ "LABEL_0": 0,
300
+ "LABEL_1": 1
301
+ },
302
+ "length_penalty": 1.0,
303
+ "max_length": 20,
304
+ "min_length": 0,
305
+ "model_type": "qwen2_5_omni_vision_encoder",
306
+ "no_repeat_ngram_size": 0,
307
+ "num_beam_groups": 1,
308
+ "num_beams": 1,
309
+ "num_heads": 16,
310
+ "num_return_sequences": 1,
311
+ "out_hidden_size": 2048,
312
+ "output_attentions": false,
313
+ "output_hidden_states": false,
314
+ "output_scores": false,
315
+ "pad_token_id": null,
316
+ "patch_size": 14,
317
+ "prefix": null,
318
+ "problem_type": null,
319
+ "pruned_heads": {},
320
+ "remove_invalid_values": false,
321
+ "repetition_penalty": 1.0,
322
+ "return_dict": true,
323
+ "return_dict_in_generate": false,
324
+ "sep_token_id": null,
325
+ "spatial_merge_size": 2,
326
+ "spatial_patch_size": 14,
327
+ "suppress_tokens": null,
328
+ "task_specific_params": null,
329
+ "temperature": 1.0,
330
+ "temporal_patch_size": 2,
331
+ "tf_legacy_loss": false,
332
+ "tie_encoder_decoder": false,
333
+ "tie_word_embeddings": true,
334
+ "tokenizer_class": null,
335
+ "tokens_per_second": 25,
336
+ "top_k": 50,
337
+ "top_p": 1.0,
338
+ "torch_dtype": null,
339
+ "torchscript": false,
340
+ "typical_p": 1.0,
341
+ "use_bfloat16": false,
342
+ "window_size": 112
343
+ },
344
+ "vision_end_token_id": 151653,
345
+ "vision_start_token_id": 151652,
346
+ "vision_token_id": 151654
347
+ },
348
+ "token2wav_config": {
349
+ "_attn_implementation_autoset": true,
350
+ "bigvgan_config": {
351
+ "_attn_implementation_autoset": true,
352
+ "add_cross_attention": false,
353
+ "architectures": null,
354
+ "bad_words_ids": null,
355
+ "begin_suppress_tokens": null,
356
+ "bos_token_id": null,
357
+ "chunk_size_feed_forward": 0,
358
+ "cross_attention_hidden_size": null,
359
+ "decoder_start_token_id": null,
360
+ "diversity_penalty": 0.0,
361
+ "do_sample": false,
362
+ "early_stopping": false,
363
+ "encoder_no_repeat_ngram_size": 0,
364
+ "eos_token_id": null,
365
+ "exponential_decay_length_penalty": null,
366
+ "finetuning_task": null,
367
+ "forced_bos_token_id": null,
368
+ "forced_eos_token_id": null,
369
+ "id2label": {
370
+ "0": "LABEL_0",
371
+ "1": "LABEL_1"
372
+ },
373
+ "is_decoder": false,
374
+ "is_encoder_decoder": false,
375
+ "label2id": {
376
+ "LABEL_0": 0,
377
+ "LABEL_1": 1
378
+ },
379
+ "length_penalty": 1.0,
380
+ "max_length": 20,
381
+ "mel_dim": 80,
382
+ "min_length": 0,
383
+ "model_type": "qwen2_5_omni_bigvgan",
384
+ "no_repeat_ngram_size": 0,
385
+ "num_beam_groups": 1,
386
+ "num_beams": 1,
387
+ "num_return_sequences": 1,
388
+ "output_attentions": false,
389
+ "output_hidden_states": false,
390
+ "output_scores": false,
391
+ "pad_token_id": null,
392
+ "prefix": null,
393
+ "problem_type": null,
394
+ "pruned_heads": {},
395
+ "remove_invalid_values": false,
396
+ "repetition_penalty": 1.0,
397
+ "resblock_dilation_sizes": [
398
+ [
399
+ 1,
400
+ 3,
401
+ 5
402
+ ],
403
+ [
404
+ 1,
405
+ 3,
406
+ 5
407
+ ],
408
+ [
409
+ 1,
410
+ 3,
411
+ 5
412
+ ]
413
+ ],
414
+ "resblock_kernel_sizes": [
415
+ 3,
416
+ 7,
417
+ 11
418
+ ],
419
+ "return_dict": true,
420
+ "return_dict_in_generate": false,
421
+ "sep_token_id": null,
422
+ "suppress_tokens": null,
423
+ "task_specific_params": null,
424
+ "temperature": 1.0,
425
+ "tf_legacy_loss": false,
426
+ "tie_encoder_decoder": false,
427
+ "tie_word_embeddings": true,
428
+ "tokenizer_class": null,
429
+ "top_k": 50,
430
+ "top_p": 1.0,
431
+ "torch_dtype": null,
432
+ "torchscript": false,
433
+ "typical_p": 1.0,
434
+ "upsample_initial_channel": 1536,
435
+ "upsample_kernel_sizes": [
436
+ 11,
437
+ 7,
438
+ 4,
439
+ 4,
440
+ 4,
441
+ 4
442
+ ],
443
+ "upsample_rates": [
444
+ 5,
445
+ 3,
446
+ 2,
447
+ 2,
448
+ 2,
449
+ 2
450
+ ],
451
+ "use_bfloat16": false,
452
+ "use_bias_at_final": false
453
+ },
454
+ "dit_config": {
455
+ "_attn_implementation_autoset": true,
456
+ "add_cross_attention": false,
457
+ "architectures": null,
458
+ "bad_words_ids": null,
459
+ "begin_suppress_tokens": null,
460
+ "block_size": 24,
461
+ "bos_token_id": null,
462
+ "chunk_size_feed_forward": 0,
463
+ "cross_attention_hidden_size": null,
464
+ "decoder_start_token_id": null,
465
+ "depth": 22,
466
+ "dim": 1024,
467
+ "diversity_penalty": 0.0,
468
+ "do_sample": false,
469
+ "dropout": 0.1,
470
+ "early_stopping": false,
471
+ "emb_dim": 512,
472
+ "enc_attention_channels": 64,
473
+ "enc_channels": [
474
+ 256,
475
+ 256,
476
+ 256,
477
+ 256,
478
+ 768
479
+ ],
480
+ "enc_dilations": [
481
+ 1,
482
+ 2,
483
+ 3,
484
+ 4,
485
+ 1
486
+ ],
487
+ "enc_dim": 128,
488
+ "enc_emb_dim": 192,
489
+ "enc_global_context": true,
490
+ "enc_kernel_sizes": [
491
+ 5,
492
+ 3,
493
+ 3,
494
+ 3,
495
+ 1
496
+ ],
497
+ "enc_lin_neurons": 192,
498
+ "enc_res2net_scale": 2,
499
+ "enc_se_channels": 64,
500
+ "encoder_no_repeat_ngram_size": 0,
501
+ "eos_token_id": null,
502
+ "exponential_decay_length_penalty": null,
503
+ "ff_mult": 2,
504
+ "finetuning_task": null,
505
+ "forced_bos_token_id": null,
506
+ "forced_eos_token_id": null,
507
+ "head_dim": 64,
508
+ "heads": 16,
509
+ "hidden_size": 1024,
510
+ "id2label": {
511
+ "0": "LABEL_0",
512
+ "1": "LABEL_1"
513
+ },
514
+ "is_decoder": false,
515
+ "is_encoder_decoder": false,
516
+ "label2id": {
517
+ "LABEL_0": 0,
518
+ "LABEL_1": 1
519
+ },
520
+ "length_penalty": 1.0,
521
+ "look_ahead_layers": [
522
+ 10
523
+ ],
524
+ "look_backward_layers": [
525
+ 0,
526
+ 20
527
+ ],
528
+ "max_length": 20,
529
+ "max_position_embeddings": 32768,
530
+ "mel_dim": 80,
531
+ "min_length": 0,
532
+ "model_type": "qwen2_5_omni_dit",
533
+ "no_repeat_ngram_size": 0,
534
+ "num_attention_heads": 16,
535
+ "num_beam_groups": 1,
536
+ "num_beams": 1,
537
+ "num_embeds": 8193,
538
+ "num_hidden_layers": 22,
539
+ "num_return_sequences": 1,
540
+ "output_attentions": false,
541
+ "output_hidden_states": false,
542
+ "output_scores": false,
543
+ "pad_token_id": null,
544
+ "prefix": null,
545
+ "problem_type": null,
546
+ "pruned_heads": {},
547
+ "remove_invalid_values": false,
548
+ "repeats": 2,
549
+ "repetition_penalty": 1.0,
550
+ "return_dict": true,
551
+ "return_dict_in_generate": false,
552
+ "rope_theta": 10000.0,
553
+ "sep_token_id": null,
554
+ "suppress_tokens": null,
555
+ "task_specific_params": null,
556
+ "temperature": 1.0,
557
+ "tf_legacy_loss": false,
558
+ "tie_encoder_decoder": false,
559
+ "tie_word_embeddings": true,
560
+ "tokenizer_class": null,
561
+ "top_k": 50,
562
+ "top_p": 1.0,
563
+ "torch_dtype": "float32",
564
+ "torchscript": false,
565
+ "typical_p": 1.0,
566
+ "use_bfloat16": false
567
+ },
568
+ "model_type": "qwen2_5_omni_token2wav",
569
+ "pad_token_id": 151643,
570
+ "torch_dtype": "bfloat16"
571
+ },
572
+ "torch_dtype": "bfloat16",
573
+ "transformers_version": "4.52.0.dev0"
574
+ }
v0-20250513-030424/checkpoint-9/generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.52.0.dev0"
4
+ }
v0-20250513-030424/checkpoint-9/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
v0-20250513-030424/checkpoint-9/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6d67b12741537c36ae7bbc1236f03b8061c480168f044f33f08704ea6183e1
3
+ size 4994850880
v0-20250513-030424/checkpoint-9/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f658b183bbcea333b114a1599e6cd6ec3642a5d364387680725f13bbea72fa69
3
+ size 4999787448
v0-20250513-030424/checkpoint-9/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f2138170a87ec604b53232491a96d6dcf19e0724aca37e69aace143e508b170
3
+ size 1978024880
v0-20250513-030424/checkpoint-9/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
v0-20250513-030424/checkpoint-9/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9101d7235bfad4116d5561e5152ef78747a20e7f664670f9b60ab7f867aff18
3
+ size 13588793804
v0-20250513-030424/checkpoint-9/preprocessor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "max_pixels": 12845056,
19
+ "merge_size": 2,
20
+ "min_pixels": 3136,
21
+ "n_fft": 400,
22
+ "n_samples": 4800000,
23
+ "nb_max_frames": 30000,
24
+ "padding_side": "right",
25
+ "padding_value": 0.0,
26
+ "patch_size": 14,
27
+ "processor_class": "Qwen2_5OmniProcessor",
28
+ "return_attention_mask": true,
29
+ "sampling_rate": 16000,
30
+ "temporal_patch_size": 2
31
+ }
v0-20250513-030424/checkpoint-9/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7063580a565cb4ab0c1d36b25d817a35a16d1f21f4a993a9f25cdba6efadcb9d
3
+ size 14645
v0-20250513-030424/checkpoint-9/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b83b02a38f0ea9cd5193bd205cd321981bf84554a85cc199b42d9b65210e0ca9
3
+ size 1465
v0-20250513-030424/checkpoint-9/special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|AUDIO|>",
6
+ "<|audio_bos|>",
7
+ "<|audio_eos|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_bos|>",
12
+ "<|vision_eos|>",
13
+ "<|vision_pad|>",
14
+ "<|IMAGE|>",
15
+ "<|VIDEO|>"
16
+ ],
17
+ "audio_bos_token": "<|audio_bos|>",
18
+ "audio_eos_token": "<|audio_eos|>",
19
+ "audio_token": "<|AUDIO|>",
20
+ "eos_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "image_token": "<|IMAGE|>",
28
+ "pad_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "video_token": "<|VIDEO|>",
36
+ "vision_bos_token": "<|vision_bos|>",
37
+ "vision_eos_token": "<|vision_eos|>"
38
+ }
v0-20250513-030424/checkpoint-9/spk_dict.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18
3
+ size 259544
v0-20250513-030424/checkpoint-9/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
3
+ size 11421870
v0-20250513-030424/checkpoint-9/tokenizer_config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|AUDIO|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|audio_bos|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|audio_eos|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_bos|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_eos|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|IMAGE|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|VIDEO|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ }
180
+ },
181
+ "additional_special_tokens": [
182
+ "<|im_start|>",
183
+ "<|im_end|>",
184
+ "<|AUDIO|>",
185
+ "<|audio_bos|>",
186
+ "<|audio_eos|>",
187
+ "<|box_end|>",
188
+ "<|quad_start|>",
189
+ "<|quad_end|>",
190
+ "<|vision_bos|>",
191
+ "<|vision_eos|>",
192
+ "<|vision_pad|>",
193
+ "<|IMAGE|>",
194
+ "<|VIDEO|>"
195
+ ],
196
+ "audio_bos_token": "<|audio_bos|>",
197
+ "audio_eos_token": "<|audio_eos|>",
198
+ "audio_token": "<|AUDIO|>",
199
+ "bos_token": null,
200
+ "clean_up_tokenization_spaces": false,
201
+ "eos_token": "<|im_end|>",
202
+ "errors": "replace",
203
+ "extra_special_tokens": {
204
+ "audio_bos_token": "<|audio_bos|>",
205
+ "audio_eos_token": "<|audio_eos|>",
206
+ "audio_token": "<|AUDIO|>",
207
+ "image_token": "<|IMAGE|>",
208
+ "video_token": "<|VIDEO|>",
209
+ "vision_bos_token": "<|vision_bos|>",
210
+ "vision_eos_token": "<|vision_eos|>"
211
+ },
212
+ "image_token": "<|IMAGE|>",
213
+ "model_max_length": 32768,
214
+ "pad_token": "<|endoftext|>",
215
+ "processor_class": "Qwen2_5OmniProcessor",
216
+ "split_special_tokens": false,
217
+ "tokenizer_class": "Qwen2Tokenizer",
218
+ "unk_token": null,
219
+ "video_token": "<|VIDEO|>",
220
+ "vision_bos_token": "<|vision_bos|>",
221
+ "vision_eos_token": "<|vision_eos|>"
222
+ }
v0-20250513-030424/checkpoint-9/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 9,
3
+ "best_metric": 0.0812883,
4
+ "best_model_checkpoint": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/checkpoint-9",
5
+ "epoch": 2.8,
6
+ "eval_steps": 500,
7
+ "global_step": 9,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.26666666666666666,
14
+ "grad_norm": 225.0,
15
+ "learning_rate": 9.698463103929542e-06,
16
+ "loss": 4.1481547355651855,
17
+ "memory(GiB)": 36.91,
18
+ "step": 1,
19
+ "token_acc": 0.3333333333333333,
20
+ "train_speed(iter/s)": 0.020994
21
+ },
22
+ {
23
+ "epoch": 1.5333333333333332,
24
+ "grad_norm": 35.0,
25
+ "learning_rate": 4.131759111665349e-06,
26
+ "loss": 1.0293580293655396,
27
+ "memory(GiB)": 48.99,
28
+ "step": 5,
29
+ "token_acc": 0.8857142857142857,
30
+ "train_speed(iter/s)": 0.020757
31
+ },
32
+ {
33
+ "epoch": 2.8,
34
+ "eval_loss": 0.08128830045461655,
35
+ "eval_runtime": 0.8682,
36
+ "eval_samples_per_second": 1.152,
37
+ "eval_steps_per_second": 1.152,
38
+ "eval_token_acc": 1.0,
39
+ "step": 9
40
+ }
41
+ ],
42
+ "logging_steps": 5,
43
+ "max_steps": 9,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "stateful_callbacks": {
48
+ "TrainerControl": {
49
+ "args": {
50
+ "should_epoch_stop": false,
51
+ "should_evaluate": false,
52
+ "should_log": false,
53
+ "should_save": true,
54
+ "should_training_stop": true
55
+ },
56
+ "attributes": {}
57
+ }
58
+ },
59
+ "total_flos": 9094847188497408.0,
60
+ "train_batch_size": 2,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
v0-20250513-030424/checkpoint-9/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d4e455f244a46e46473d161c8e9786e2835701e5ee21412d2f9f34441782186
3
+ size 6353
v0-20250513-030424/checkpoint-9/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
v0-20250513-030424/images/eval_loss.png ADDED
v0-20250513-030424/images/eval_runtime.png ADDED
v0-20250513-030424/images/eval_samples_per_second.png ADDED
v0-20250513-030424/images/eval_steps_per_second.png ADDED
v0-20250513-030424/images/eval_token_acc.png ADDED
v0-20250513-030424/images/train_epoch.png ADDED
v0-20250513-030424/images/train_grad_norm.png ADDED
v0-20250513-030424/images/train_learning_rate.png ADDED
v0-20250513-030424/images/train_loss.png ADDED
v0-20250513-030424/images/train_memory(GiB).png ADDED
v0-20250513-030424/images/train_token_acc.png ADDED
v0-20250513-030424/images/train_total_flos.png ADDED
v0-20250513-030424/images/train_train_loss.png ADDED
v0-20250513-030424/images/train_train_runtime.png ADDED
v0-20250513-030424/images/train_train_samples_per_second.png ADDED
v0-20250513-030424/images/train_train_speed(iter_s).png ADDED
v0-20250513-030424/images/train_train_steps_per_second.png ADDED
v0-20250513-030424/logging.jsonl ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {"loss": 4.14815474, "token_acc": 0.33333333, "grad_norm": 225.0, "learning_rate": 9.7e-06, "memory(GiB)": 36.91, "train_speed(iter/s)": 0.020994, "epoch": 0.26666667, "global_step/max_steps": "1/9", "percentage": "11.11%", "elapsed_time": "47s", "remaining_time": "6m 18s"}
2
+ {"loss": 1.02935803, "token_acc": 0.88571429, "grad_norm": 35.0, "learning_rate": 4.13e-06, "memory(GiB)": 48.99, "train_speed(iter/s)": 0.020757, "epoch": 1.53333333, "global_step/max_steps": "5/9", "percentage": "55.56%", "elapsed_time": "4m 0s", "remaining_time": "3m 12s"}
3
+ {"eval_loss": 0.0812883, "eval_token_acc": 1.0, "eval_runtime": 0.8682, "eval_samples_per_second": 1.152, "eval_steps_per_second": 1.152, "epoch": 2.8, "global_step/max_steps": "9/9", "percentage": "100.00%", "elapsed_time": "7m 14s", "remaining_time": "0s"}
4
+ {"train_runtime": 503.9147, "train_samples_per_second": 0.351, "train_steps_per_second": 0.018, "total_flos": 9094847188497408.0, "train_loss": 0.97334064, "epoch": 2.8, "global_step/max_steps": "9/9", "percentage": "100.00%", "elapsed_time": "8m 23s", "remaining_time": "0s"}
5
+ {"model_parameter_info": "Qwen2_5OmniForConditionalGeneration: 5537.1206M Params (3397.1036M Trainable [61.3514%]), 1.9258M Buffers.", "last_model_checkpoint": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/checkpoint-9", "best_model_checkpoint": "/home/xj_data/jishengpeng/InteractSpeech/ms-swift/result/output_3B_fulltune_interact/v0-20250513-030424/checkpoint-9", "best_metric": 0.0812883, "global_step": 9, "log_history": [{"loss": 4.1481547355651855, "token_acc": 0.3333333333333333, "grad_norm": 225.0, "learning_rate": 9.698463103929542e-06, "memory(GiB)": 36.91, "train_speed(iter/s)": 0.020994, "epoch": 0.26666666666666666, "step": 1}, {"loss": 1.0293580293655396, "token_acc": 0.8857142857142857, "grad_norm": 35.0, "learning_rate": 4.131759111665349e-06, "memory(GiB)": 48.99, "train_speed(iter/s)": 0.020757, "epoch": 1.5333333333333332, "step": 5}, {"eval_loss": 0.08128830045461655, "eval_token_acc": 1.0, "eval_runtime": 0.8682, "eval_samples_per_second": 1.152, "eval_steps_per_second": 1.152, "epoch": 2.8, "step": 9}, {"train_runtime": 503.9147, "train_samples_per_second": 0.351, "train_steps_per_second": 0.018, "total_flos": 9094847188497408.0, "train_loss": 0.9733406371540494, "epoch": 2.8, "step": 9}], "memory": 48.986328125}
v0-20250513-030424/runs/events.out.tfevents.1747076673.dsw-239952-646df5498f-2dn6v.54937.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a22eb2db653085942306cd7cbcfb9a68c461c7ea75ae00cf85703724aeb04012
3
+ size 21887
v0-20250513-030424/val_dataset.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"messages": [{"role": "user", "content": "<audio>语音说了什么"}, {"role": "assistant", "content": "今天天气真好呀"}], "audios": ["/home/xj_data/jishengpeng/InteractSpeech/Train600/tmp/matched_audio/PLACES3.5--train--413.wav"]}