Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/modelscope/hub/qwen/Qwen2-Audio-7B-Instruct",
+  "_name_or_path": "/workdir/output/qwen2-audio-7b-instruct/v0-20240811-194125/checkpoint-3000",
   "architectures": [
     "Qwen2AudioForConditionalGeneration"
   ],

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c82d73aad956039d292faa0b29363ba14cb071630836d5989b2fdd5989d406
+oid sha256:f9d6669d5af73eab4a355424d05b460b909f9575857c8bc00adb1d1a900ead02
 size 4991459544

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eca464f1e53cc23686db580f4fdcfbf42f54f6e7191b14e303dbdd83f5e4c12
+oid sha256:074eb83a0aae93b6185a7588f3513e1b25a55e331852c5f354c59dfcfe0bfc26
 size 4991757456

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59b94cf34b09ef67c1480b636aadf4b4ef94fa904c7e668fa1cebff16a2d928
+oid sha256:fdd1ca3e08a3d637464bb84473e5386355a46073afe84efeee0f70f1e5268854
 size 4947691960

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2f02eb3f254222b81e41c9656a56c6d64acf37e302b9b09cac32ed0f4de759
+oid sha256:4b97db8aff30966b23e4912378883b2b6ee2aa0ced6a395aaa333a28afec1698
 size 1863387424

sft_args.json

@@ -1,13 +1,13 @@
 {
   "model_type": "qwen2-audio-7b-instruct",
-  "model_id_or_path": "qwen/Qwen2-Audio-7B-Instruct",
+  "model_id_or_path": "/workdir/output/qwen2-audio-7b-instruct/v0-20240811-194125/checkpoint-3000",
   "model_revision": "master",
   "sft_type": "full",
   "freeze_parameters": 0.0,
   "additional_trainable_parameters": [],
   "tuner_backend": "peft",
   "template_type": "qwen2-audio",
-  "output_dir": "/workdir/output/qwen2-audio-7b-instruct/v0-20240811-194125",
+  "output_dir": "/workdir/output/qwen2-audio-7b-instruct/v5-20240812-110447",
   "add_output_dir_suffix": true,
   "ddp_backend": "nccl",
   "ddp_find_unused_parameters": null,
@@ -123,7 +123,7 @@
   "adam_epsilon": 1e-08,
   "learning_rate": 1e-05,
   "weight_decay": 0.1,
-  "gradient_accumulation_steps": 8,
+  "gradient_accumulation_steps": 32,
   "max_grad_norm": 1,
   "predict_with_generate": false,
   "lr_scheduler_type": "cosine",
@@ -131,7 +131,7 @@
   "warmup_ratio": 0.05,
   "warmup_steps": 1,
   "eval_steps": 100000,
-  "save_steps": 500,
+  "save_steps": 100,
   "save_only_model": true,
   "save_total_limit": 2,
   "logging_steps": 5,
@@ -151,7 +151,7 @@
   "use_flash_attn": null,
   "ignore_args_error": false,
   "check_model_is_latest": true,
-  "logging_dir": "/workdir/output/qwen2-audio-7b-instruct/v0-20240811-194125/runs",
+  "logging_dir": "/workdir/output/qwen2-audio-7b-instruct/v5-20240812-110447/runs",
   "report_to": [
     "tensorboard"
   ],
@@ -225,5 +225,5 @@
   "load_in_4bit": false,
   "load_in_8bit": false,
   "train_sampler_random": true,
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/workdir/output/qwen2-audio-7b-instruct/v0-20240811-194125', 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=4, per_device_eval_batch_size=4, 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, 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/v0-20240811-194125/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=500, 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/v0-20240811-194125', 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)"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/workdir/output/qwen2-audio-7b-instruct/v5-20240812-110447', 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=4, per_device_eval_batch_size=4, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=32, 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/v5-20240812-110447/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/v5-20240812-110447', 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)"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0c568922fdba28aca64b9ecf9031ace8dfe0e9d26191ba7cb6c1b08994eae1
+oid sha256:ad87dcd9f2a51df045503d88e889b01ca75d46adc06375440cfda8904aef93c6
 size 7352