Upload folder using huggingface_hub

args.json

@@ -14,7 +14,7 @@
   "init_strategy": null,
   "template": "qwen2_5_vl",
   "system": "You are a helpful assistant.\n\nSolve the following problem step by step, and optionally write Python code for image manipulation to enhance your reasoning process. The Python code will be executed by an external sandbox, and the processed image or result (wrapped in <sandbox_output></sandbox_output>) can be returned to aid your reasoning and help you arrive at the final answer.\n\n**Reasoning & Image Manipulation (Optional but Encouraged):**\n    * You have the capability to write executable Python code to perform image manipulations (e.g., cropping to a Region of Interest (ROI), resizing, rotation, adjusting contrast) or perform calculation for better reasoning.\n    * The code will be executed in a secure sandbox, and its output will be provided back to you for further analysis.\n    * All Python code snippets **must** be wrapped as follows:\n    <code>\n    ```python\n    # your code.\n    ```\n    </code>\n    * At the end of the code, print the path of the processed image (processed_path) or the result for further processing in a sandbox environment.",
-  "max_length": 20480,
+  "max_length": 10240,
   "truncation_strategy": "delete",
   "max_pixels": null,
   "agent_template": null,
@@ -27,11 +27,10 @@
   "use_chat_template": true,
   "template_backend": "swift",
   "dataset": [
-    "/mllm_hdd/yfzhang/Agent-R1/agent_latest_code/scripts/training_data/wo_system_image_180k_filter_w_image_size_filter_wo_some_code_4o_filter_1.jsonl",
+    "/mmu_mllm_hdd_2/yifanzhang/agent_latest_code/scripts/training_data/wo_system_image_180k_filter_w_image_size_filter_wo_some_code.jsonl",
     "/mllm_hdd/yfzhang/Agent-R1/agent_latest_code/scripts/training_data/vstar_2step_nooverlap_training_filtered_70k.jsonl",
     "/mllm_hdd/yfzhang/Agent-R1/agent_latest_code/scripts/training_data/vstar_2step_zoomin_training_filtered_70k.jsonl",
-    "/mllm_hdd/yfzhang/Agent-R1/agent_latest_code/scripts/training_data/wo_system_image_180k_filter_w_image_size_filter_wo_some_code_2round.jsonl",
-    "/mllm_hdd/yfzhang/Agent-R1/construct_data/math_and_chart/mm-eumath/data_gemini_code_processed_swift_train_chunk0_of_1.jsonl"
+    "/mllm_hdd/yfzhang/Agent-R1/agent_latest_code/scripts/training_data/wo_system_image_180k_filter_w_image_size_filter_wo_some_code_2round.jsonl"
   ],
   "val_dataset": [],
   "split_dataset_ratio": 0.01,
@@ -92,7 +91,7 @@
   "ddp_backend": null,
   "ignore_args_error": false,
   "use_swift_lora": false,
-  "output_dir": "/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v6-20250611-100511",
+  "output_dir": "/mmu_mllm_hdd_2/yifanzhang/models/tool_final/qwen_tool_all_data_180k_alldata_wpgemini/v0-20250616-170052",
   "overwrite_output_dir": false,
   "do_train": false,
   "do_eval": false,
@@ -122,7 +121,7 @@
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v6-20250611-100511/runs",
+  "logging_dir": "/mmu_mllm_hdd_2/yifanzhang/models/tool_final/qwen_tool_all_data_180k_alldata_wpgemini/v0-20250616-170052/runs",
   "logging_strategy": "steps",
   "logging_first_step": true,
   "logging_steps": 5,
@@ -152,10 +151,10 @@
   "debug": null,
   "dataloader_drop_last": false,
   "eval_steps": null,
-  "dataloader_num_workers": 0,
+  "dataloader_num_workers": 4,
   "dataloader_prefetch_factor": null,
   "past_index": -1,
-  "run_name": "/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v6-20250611-100511",
+  "run_name": "/mmu_mllm_hdd_2/yifanzhang/models/tool_final/qwen_tool_all_data_180k_alldata_wpgemini/v0-20250616-170052",
   "disable_tqdm": null,
   "label_names": null,
   "load_best_model_at_end": false,
@@ -209,7 +208,7 @@
   "group_by_length": false,
   "length_column_name": "length",
   "report_to": [
-    "none"
+    "wandb"
   ],
   "ddp_find_unused_parameters": null,
   "ddp_bucket_cap_mb": null,
@@ -219,7 +218,7 @@
   "skip_memory_metrics": true,
   "use_legacy_prediction_loop": false,
   "push_to_hub": false,
-  "resume_from_checkpoint": "/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v4-20250610-121125/checkpoint-2477",
+  "resume_from_checkpoint": null,
   "hub_model_id": null,
   "hub_strategy": "every_save",
   "hub_private_repo": null,
@@ -363,9 +362,9 @@
   "local_world_size": 8,
   "model_suffix": "Qwen2.5-VL-7B-Instruct",
   "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mllm_hdd/yfzhang/data/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
-  "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fab5d5ace50>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=[])",
+  "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7f24290f93f0>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=[])",
   "model_dir": "/mllm_hdd/yfzhang/data/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5",
   "hub": "<class 'swift.hub.hub.MSHub'>",
   "evaluation_strategy": "epoch",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v6-20250611-100511', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, 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=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v6-20250611-100511/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=5, 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=None, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v6-20250611-100511', 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}, tp_size=0, 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={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, 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=[], 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='/mmu_mllm_hdd_2/yifanzhang/models/qwen_tool_all_data_200k_w_imagesize_3epoch_4096_all_2round_code_4ofilter1/v4-20250610-121125/checkpoint-2477', 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, aligner_lr=None, vit_lr=None, optimizer=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', local_repo_path=None, galore_config=None)"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/mmu_mllm_hdd_2/yifanzhang/models/tool_final/qwen_tool_all_data_180k_alldata_wpgemini/v0-20250616-170052', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, 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=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/mmu_mllm_hdd_2/yifanzhang/models/tool_final/qwen_tool_all_data_180k_alldata_wpgemini/v0-20250616-170052/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=500, save_total_limit=5, 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=None, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mmu_mllm_hdd_2/yifanzhang/models/tool_final/qwen_tool_all_data_180k_alldata_wpgemini/v0-20250616-170052', 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}, tp_size=0, 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={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, 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=['wandb'], 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, aligner_lr=None, vit_lr=None, optimizer=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', local_repo_path=None, galore_config=None)"
 }

global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4903ad115f1781a3edb94ab79f40c6a3f93dd4ca21281cf24f3e88e63f3787
+size 11423432396

global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab83ce8fdb9ac4b4fc0ca1882154c9641aacf81f8a927303d8f58b11e55cd11
+size 11423433356

global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d94c8b1026b52a76bbc2b5374078fc3effe97c91fe9a005c8e59018a1f6c9e6a
+size 11423433484

global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a5c483c3d8b87af94a89e790569ef73775356b1b708f3389f404515d5c6f4c
+size 11423433484

global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37f8310b08ff06d9e444b866683020d05af5b16922c124b402543986809e1c3
+size 11423433804

global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aba1f366bef9718320eb5ea41a3adeb51c0faefafce2fe1279ca21e5398a9d0
+size 11423433484

global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15348b3d37035573222d7e44bc7b95f9c17645567c16d98a809d45c3b84a0481
+size 11423433548

global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1b280d0de63d145ed723c43c1dd68f7b8197c8f793ef24dcdf839e39725505
+size 11423432012

global_step190/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e8390a7702e571fa6029e8cdb5bb672474458b5ea3c25162f8cbcfcf4f6d2d
+size 17937826134

latest

@@ -1 +1 @@
-global_step4954
+global_step190

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c79dd91ba67f29d8710a0839b4df9ef9d3ecd4460e937884cac376012d319cd
+oid sha256:35dea09eb661006336ce549434a1307ff409722a6cf0a69c0e2fa6e6af2371df
 size 4968243304

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90da2b983f49ee3bb33be4815804e8bff2c994336232e03fed786a7c4f554322
+oid sha256:92f8355328bb494f9860ad8458b735e7b6db1ad2e0af409acb0f30586872a81b
 size 4991495816

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6401cf110c22a98dcbcaa98a89baed6b1ffa9bb0c819094b821c59d1c48dc0a9
+oid sha256:9e90769ec71fd83d560abd732e2ca5d89c9df92145da2850d057c29a9fcffbce
 size 4932751040

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d1a621ee97e55e06b1cdeb53880e3949611d02ccc480d7b213d46b5fd9a84f
+oid sha256:51eee4b151ea3d344bc810054c869d7fac286f9bff5ba4f2cd5deda76f0ccd2f
 size 1691924384

rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d2a2034ebb05cb71c510897f2795b31164e50f17b270bc25d2be3ad9a17b22
-size 15984
+oid sha256:5ff22c72cb50d4b6353cf336b950d2c54115c739606544de9a8d3b0fab0ef188
+size 15920

rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060dfdb1c49102cbdc8868a6031e68787601b4ccd782f3fb9b137e20c1fd2c7a
-size 15984
+oid sha256:c253ad05d3ffa98dc1e5291ec640e6158218602254206e6fb97ea82185040775
+size 15920

rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af01895cb66e616591f2e4baa8dcd8151530eab133c73571ccb31c74f35422ce
-size 15984
+oid sha256:edcdbb53b869133655de3ceb14325bb161e7aa238640244125393ff4afcb7363
+size 15920

rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:677921992b1e0cef3aee776f245975003d22f51d9bd6ed20f248ded1deb72fa9
-size 15984
+oid sha256:b095e9807a468e05241a1d389fd326265bee89778655d3c00298c2f6abcee791
+size 15920

rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69353c629541c690c5471f8ec05fdab2bfecf3d37afaa436bc45939da6db68f
-size 15984
+oid sha256:a4da3805c54028ef89f9cce32b640836c54b432b251fae2dea3d0182fa96f403
+size 15920

rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e40ba6668cc03c9162c68a933d164bf38ae2d196a9a6fec03ae615491201185
-size 15984
+oid sha256:08bb3c8d2c1053a6b93a1342acb589ea4695b3fdb4dfeaf3675191c7e3390d3d
+size 15920

rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870968fea834e24b2e099cf3e4fe1e3fb8caf38d8f8e5b790d7d47386d4d05f5
-size 15984
+oid sha256:3cfebda0f5a673869a40a8a82d7e308c843f9b55ec287861a6a0670b4c43c9d4
+size 15920

rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e19618bee7c6ef43256fea25abe19bca88535eb1e7dc213cde8929ae4e8180
-size 15984
+oid sha256:34bc6aae481e0bf889f93cc019a7692fbdaba7925f341ec202dd711aa1d2a724
+size 15920

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d4ee630da491260156b1eb0cb5f833bea3b6c7bc13b43d5f68f80d26b81175
+oid sha256:d702a8a3f8a6bd01d9c0b9b47d00fb13493b6625b2b130d83744041615bf59ad
 size 1064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4724c8db9bbee65453bfd76967efff3e6f43c5d47668efd8102b96225089149
-size 8120
+oid sha256:dd32b1597af89117014632dc1c0dfbea5e1e857567df2a15713b7750a4acf718
+size 8056