Upload folder using huggingface_hub

args.json

@@ -1,5 +1,5 @@
 {
-  "output_dir": "/home/ubuntu/vgse-ms/output/qwen3_vl_32_lora/v7-20260208-035751",
+  "output_dir": "/home/ubuntu/vgse-ms/output/qwen3_vl_32b_lora/v13-20260215-040330",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
@@ -29,13 +29,13 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/home/ubuntu/vgse-ms/output/qwen3_vl_32_lora/v7-20260208-035751/runs",
+  "logging_dir": "/home/ubuntu/vgse-ms/output/qwen3_vl_32b_lora/v13-20260215-040330/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 10,
   "logging_nan_inf_filter": true,
   "save_strategy": "steps",
-  "save_steps": 200.0,
+  "save_steps": 600.0,
   "save_total_limit": null,
   "save_safetensors": true,
   "save_on_each_node": false,
@@ -60,11 +60,11 @@
   "tpu_metrics_debug": false,
   "debug": null,
   "dataloader_drop_last": false,
-  "eval_steps": 100.0,
-  "dataloader_num_workers": null,
+  "eval_steps": 300.0,
+  "dataloader_num_workers": 0,
   "dataloader_prefetch_factor": null,
   "past_index": -1,
-  "run_name": "/home/ubuntu/vgse-ms/output/qwen3_vl_32_lora/v7-20260208-035751",
+  "run_name": "/home/ubuntu/vgse-ms/output/qwen3_vl_32b_lora/v13-20260215-040330",
   "disable_tqdm": null,
   "remove_unused_columns": true,
   "label_names": null,
@@ -226,8 +226,8 @@
   "enable_thinking": null,
   "add_non_thinking_prefix": true,
   "dataset": [
-    "/home/ubuntu/squidward/datasets/train-filtered-norm-2.jsonl",
-    "/home/ubuntu/squidward/datasets/train-filtered-norm-1.jsonl"
+    "/lambda/nfs/squidward/datasets//train-filtered-norm-2-1.jsonl",
+    "/lambda/nfs/squidward/datasets//train-filtered-norm-1.jsonl"
   ],
   "val_dataset": [],
   "cached_dataset": [],
@@ -277,7 +277,9 @@
   "packing_length": null,
   "packing_num_proc": 1,
   "lazy_tokenize": true,
-  "custom_register_path": [],
+  "custom_register_path": [
+    "augmentation.py"
+  ],
   "use_hf": true,
   "ignore_args_error": false,
   "use_swift_lora": false,
@@ -377,10 +379,10 @@
   "local_world_size": 1,
   "model_suffix": "Qwen3-VL-32B-Instruct",
   "model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen3-VL-32B-Instruct/snapshots/0cfaf48183f594c314753d30a4c4974bc75f3ccb', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
-  "model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=<function get_model_tokenizer_qwen3_vl at 0x788629905080>, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
+  "model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=<function get_model_tokenizer_qwen3_vl at 0x7967358f2520>, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
   "model_dir": "/home/ubuntu/.cache/huggingface/hub/models--Qwen--Qwen3-VL-32B-Instruct/snapshots/0cfaf48183f594c314753d30a4c4974bc75f3ccb",
   "_val_dataset_exists": true,
   "hub": "<class 'swift.hub.hub.HFHub'>",
   "evaluation_strategy": "steps",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/vgse-ms/output/qwen3_vl_32_lora/v7-20260208-035751', 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=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, 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=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/vgse-ms/output/qwen3_vl_32_lora/v7-20260208-035751/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=200, 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, 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=100, dataloader_num_workers=1, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/ubuntu/vgse-ms/output/qwen3_vl_32_lora/v7-20260208-035751', 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), parallelism_config=None, deepspeed={'train_micro_batch_size_per_gpu': 'auto', 'gradient_clipping': 'auto', 'zero_optimization': {'stage': 2, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': True, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'scheduler': {'type': 'WarmupDecayLR', 'params': {'warmup_min_lr': 'auto', 'warmup_max_lr': 'auto', 'warmup_num_steps': 'auto', 'total_num_steps': 'auto'}}, 'fp16': {'enabled': 'auto'}, 'bf16': {'enabled': 'auto'}}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', 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, hub_revision=None, 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=18000000, 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, liger_kernel_config=None, 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, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='lora', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/vgse-ms/output/qwen3_vl_32b_lora/v13-20260215-040330', 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=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, 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=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/vgse-ms/output/qwen3_vl_32b_lora/v13-20260215-040330/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=600, 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, 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=300, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/home/ubuntu/vgse-ms/output/qwen3_vl_32b_lora/v13-20260215-040330', 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), parallelism_config=None, deepspeed={'train_micro_batch_size_per_gpu': 'auto', 'gradient_clipping': 'auto', 'zero_optimization': {'stage': 2, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': True, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'scheduler': {'type': 'WarmupDecayLR', 'params': {'warmup_min_lr': 'auto', 'warmup_max_lr': 'auto', 'warmup_num_steps': 'auto', 'total_num_steps': 'auto'}}, 'fp16': {'enabled': 'auto'}, 'bf16': {'enabled': 'auto'}}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', 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, hub_revision=None, 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=18000000, 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, liger_kernel_config=None, 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, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='lora', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
 }

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7037379078d067a7c464a488a1c98e4dac6fceb4a4c4ba1e1dd21e4d4ac74d5e
+oid sha256:4487da32fb2d86a8ac6b6fdb7532303708b68901c94e6953f11c2eacd00962a5
 size 4885539608

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff46b3b9fe39a30edc1f728a53b7a2b0b0da5d6696cf1bedf408ed80910e01ce
+oid sha256:afb59471a16c2fbbb93a282ec86e68a8bd4b18a4e79aa11501a9a5fbb34b85d3
 size 4875990520

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f34d3968cf428b44533b727d44c48af142ea9596740d653cfc018729e55a71d7
+oid sha256:f1af61e8167181ec77c6b9d9ed9cfd4a8d23823737585eaa5134ff684a1f6159
 size 4875990536

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:677c02ca27d1abc0ca370a4bd07ae4f5a471284d2b2102ab78d42141ddb8641b
+oid sha256:392fe960bf5b68eed3bbf2e9d131bbe486b3102e5383a3cd71406fc86bc92400
 size 4875990576

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1fa32602540e21bf81f7e03612a542282dd12f4fcb964947a3f791bcd23bc88
+oid sha256:13484e151d55c314922e6c500647e72cc5965723b7dddf68764df90691ad429e
 size 4875990576

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ceff60e542dc6298edbdb3265495cda8611cdd96f44ae84734ca8f0209c898
+oid sha256:294acbaaf1b01291ad9b5b6a39edba2f5d187d5014da977eb4c7b7b8a3eca025
 size 4875990576

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81cea91395f75e2c0e3ff0690109dbfef0d4f7e982ff1a1cf98c0f1bc3cb407
+oid sha256:9aab9c9d35b17874acf2486cb454766ef2b6e8a229fb8e0aeb32677a1d37c14b
 size 4875990576

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9debe400a150fb09d467673ce74d883edf8a705e9f08605bee4e79f710a0c330
+oid sha256:625aed6cfcaf57be672855122fc175d54025228f77e300d5952839b225bab253
 size 4875990576

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790bf522b3882234ca6200cc5d7fdc3e09a67b5540acea9de59d3c94b4c2a96c
+oid sha256:d58e084df7f2c92b3996d61a6205feffc3b72aaa0a22634622b8be77df82585e
 size 4875990576

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc042aed054aaaefe05f91f29f0c19e83e7075baf855263558bc15d6f01319eb
+oid sha256:d0e49172f98990c5d32839c026055313008f8a184af7f3a38b4848bda6925e20
 size 4875990576

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9293aeeff683cac9f5606c3c0d260dcd292fa9c7380103385008db389258e01f
+oid sha256:e0fcaeaad372192ad5d0558171a56d9cde78169bc0b52425d56e03fd6b206026
 size 4875990576

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca13fb942ab0a362566d408672116a7181fc9b7cd7c07d682d935cefaf9856a
+oid sha256:fc349fbe7fda17987d5ea206d9e0a3ba336da0b692213397c55c8f5547cd0a0a
 size 4875990576

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:868766ab7939d7346536b42aeb8181dd087f38a5f4780a25507fe0deca6d4eea
+oid sha256:aa7d0418b2c54b9920e04f57e3df13bf143be4d86f9971e867edaf55d1dd107d
 size 4875990576

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de2be1a85b5abcf774752acafd89e1550205fa6b789316e2e6f109877ba0815
+oid sha256:fdb83247c1c584b7eba8977e1a824b0fc000bcd466c633746ca9195f9b808812
 size 3317486360