Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

args.json

@@ -0,0 +1,690 @@
+{
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V7_MMLU/v2-20260125-211853/checkpoint-24",
+  "model_type": "qwen3_nothinking",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "qwen3_nothinking",
+  "system": null,
+  "max_length": 8192,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": true,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "RL-QA-800K"
+  ],
+  "val_dataset": [],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "data_seed": 42,
+  "dataset_num_proc": 128,
+  "load_from_cache_file": false,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "remove_unused_columns": true,
+  "model_name": [
+    "swift-robot"
+  ],
+  "model_author": [
+    "swift"
+  ],
+  "custom_dataset_info": [
+    "/scratch/hagrass/dataset_info.json"
+  ],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": null,
+  "temperature": 0.9,
+  "top_k": 50,
+  "top_p": 0.9,
+  "repetition_penalty": 1.0,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "ckpt_dir": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V7_MMLU/v2-20260125-211853/checkpoint-24",
+  "lora_modules": [],
+  "tuner_backend": "peft",
+  "train_type": "full",
+  "adapters": [],
+  "external_plugins": [],
+  "seed": 42,
+  "model_kwargs": {},
+  "load_args": false,
+  "load_data_args": false,
+  "packing": true,
+  "packing_length": 8192,
+  "packing_num_proc": 1,
+  "lazy_tokenize": false,
+  "custom_register_path": [],
+  "use_hf": false,
+  "hub_token": null,
+  "ddp_timeout": 18000000,
+  "ddp_backend": null,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "adapter_load": null,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "use_rslora": false,
+  "rlhf_type": null,
+  "ref_load": null,
+  "ref_adapter_load": null,
+  "beta": null,
+  "rpo_alpha": null,
+  "reference_free": false,
+  "label_smoothing": 0.0,
+  "f_divergence_type": "reverse_kl",
+  "loss_type": null,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "calculate_KL": null,
+  "center_rewards_coefficient": null,
+  "teacher_model": null,
+  "teacher_model_type": null,
+  "teacher_model_revision": null,
+  "lmbda": 0.5,
+  "seq_kd": false,
+  "offload_teacher_model": false,
+  "sft_alpha": 0.0,
+  "generation_batch_size": null,
+  "steps_per_generation": null,
+  "num_generations": 8,
+  "num_generations_eval": null,
+  "max_completion_length": 512,
+  "importance_sampling_level": "token",
+  "tau_pos": 1.0,
+  "tau_neg": 1.05,
+  "epsilon": 0.2,
+  "epsilon_high": null,
+  "delta": null,
+  "use_vllm": true,
+  "vllm_mode": null,
+  "vllm_enable_prefix_caching": true,
+  "vllm_gpu_memory_utilization": 0.9,
+  "vllm_tensor_parallel_size": 1,
+  "vllm_max_model_len": null,
+  "vllm_enforce_eager": false,
+  "vllm_limit_mm_per_prompt": null,
+  "vllm_disable_cascade_attn": false,
+  "vllm_max_num_seqs": null,
+  "vllm_mm_processor_cache_gb": null,
+  "vllm_engine_kwargs": null,
+  "sleep_level": 0,
+  "offload_optimizer": false,
+  "offload_model": false,
+  "offload_bridge": false,
+  "vllm_server_base_url": null,
+  "vllm_server_host": null,
+  "vllm_server_port": [
+    8000
+  ],
+  "vllm_server_timeout": 240.0,
+  "vllm_server_group_port": null,
+  "reward_funcs": [],
+  "reward_weights": null,
+  "cosine_min_len_value_wrong": -0.5,
+  "cosine_max_len_value_wrong": 0.0,
+  "cosine_min_len_value_correct": 1.0,
+  "cosine_max_len_value_correct": 0.5,
+  "cosine_max_len": null,
+  "repetition_n_grams": 3,
+  "repetition_max_penalty": -1.0,
+  "soft_max_length": null,
+  "soft_cache_length": null,
+  "dynamic_sample": false,
+  "max_resample_times": 3,
+  "overlong_filter": false,
+  "scale_rewards": "group",
+  "advantage_estimator": "grpo",
+  "kl_in_reward": false,
+  "wandb_log_unique_prompts": null,
+  "log_completions": false,
+  "rollout_importance_sampling_mode": null,
+  "rollout_importance_sampling_threshold": 2.0,
+  "log_rollout_offpolicy_metrics": false,
+  "off_policy_sequence_mask_delta": null,
+  "log_entropy": false,
+  "top_entropy_quantile": 1.0,
+  "reward_model": null,
+  "reward_model_plugin": null,
+  "sync_ref_model": false,
+  "ref_model_sync_steps": 512,
+  "ref_model_mixup_alpha": 0.6,
+  "async_generate": false,
+  "move_model_batches": null,
+  "multi_turn_scheduler": null,
+  "max_turns": null,
+  "completion_length_limit_scope": "per_round",
+  "vllm_server_pass_dataset": false,
+  "num_iterations": 1,
+  "check_model": true,
+  "padded_vocab_size": 192728,
+  "initialize_embedding": false,
+  "mlp_padding_free": false,
+  "load_safetensors": true,
+  "save_safetensors": true,
+  "ref_model": null,
+  "ref_adapters": [],
+  "merge_lora": true,
+  "max_shard_size": "5GB",
+  "train_dataloader_shuffle": true,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": true,
+  "dataloader_prefetch_factor": 2,
+  "group_by_length": false,
+  "architectures": "Qwen3MoeForCausalLM",
+  "llm_architectures": "Qwen3MoeForCausalLM",
+  "max_epochs": 1,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "save_strategy": "steps",
+  "original_max_position_embeddings": null,
+  "partial_rotary_factor": null,
+  "use_shared_expert_gate": false,
+  "report_to": "wandb",
+  "vit_gradient_checkpointing": true,
+  "vit_lr": null,
+  "aligner_lr": null,
+  "gradient_checkpointing_kwargs": null,
+  "linear_num_value_heads": null,
+  "linear_num_key_heads": null,
+  "linear_key_head_dim": null,
+  "linear_value_head_dim": null,
+  "linear_conv_kernel_dim": null,
+  "layer_types": null,
+  "mrope_interleaved": false,
+  "micro_batch_size": 1,
+  "global_batch_size": 512,
+  "recompute_granularity": "full",
+  "recompute_method": "uniform",
+  "recompute_num_layers": 1,
+  "recompute_modules": [
+    "core_attn"
+  ],
+  "use_cpu_initialization": false,
+  "deterministic_mode": false,
+  "train_iters": null,
+  "log_interval": 1,
+  "tensorboard_dir": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V8-Rl-Answers/v1-20260126-210956/runs",
+  "no_masked_softmax_fusion": false,
+  "no_bias_dropout_fusion": false,
+  "no_bias_swiglu_fusion": false,
+  "no_rope_fusion": false,
+  "no_gradient_accumulation_fusion": false,
+  "cross_entropy_loss_fusion": true,
+  "cross_entropy_fusion_impl": "native",
+  "calculate_per_token_loss": true,
+  "use_flash_attn": true,
+  "attention_backend": "flash",
+  "optimizer": "adam",
+  "optimizer_cpu_offload": true,
+  "optimizer_offload_fraction": 0.7,
+  "use_precision_aware_optimizer": true,
+  "main_grads_dtype": "fp32",
+  "main_params_dtype": "fp32",
+  "exp_avg_dtype": "fp32",
+  "exp_avg_sq_dtype": "fp32",
+  "dataloader_type": "cyclic",
+  "manual_gc": false,
+  "manual_gc_interval": 0,
+  "lr": 3e-05,
+  "lr_decay_style": "cosine",
+  "lr_decay_iters": null,
+  "lr_warmup_iters": 0,
+  "lr_warmup_fraction": 0.05,
+  "min_lr": 3e-06,
+  "weight_decay": 0.1,
+  "clip_grad": 1.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_eps": 1e-08,
+  "sgd_momentum": 0.9,
+  "save": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V8-Rl-Answers/v1-20260126-210956",
+  "save_interval": 200,
+  "save_retain_interval": null,
+  "no_save_optim": true,
+  "no_save_rng": true,
+  "load": null,
+  "no_load_optim": false,
+  "no_load_rng": false,
+  "finetune": true,
+  "ckpt_format": "torch_dist",
+  "no_initialization": true,
+  "auto_detect_ckpt_format": true,
+  "exit_on_missing_checkpoint": true,
+  "async_save": false,
+  "use_persistent_ckpt_worker": false,
+  "ckpt_fully_parallel_load": false,
+  "ckpt_assume_constant_structure": false,
+  "distributed_backend": "nccl",
+  "local_rank": 0,
+  "use_distributed_optimizer": true,
+  "tensor_model_parallel_size": 1,
+  "pipeline_model_parallel_size": 1,
+  "decoder_first_pipeline_num_layers": null,
+  "decoder_last_pipeline_num_layers": null,
+  "account_for_embedding_in_pipeline_split": false,
+  "account_for_loss_in_pipeline_split": false,
+  "sequence_parallel": true,
+  "context_parallel_size": 1,
+  "tp_comm_overlap": false,
+  "overlap_grad_reduce": false,
+  "overlap_param_gather": false,
+  "distributed_timeout_minutes": 300000,
+  "num_layers_per_virtual_pipeline_stage": null,
+  "num_virtual_stages_per_pipeline_rank": null,
+  "microbatch_group_size_per_virtual_pipeline_stage": null,
+  "pipeline_model_parallel_layout": null,
+  "num_layers": 64,
+  "hidden_size": 2048,
+  "ffn_hidden_size": null,
+  "num_attention_heads": 32,
+  "group_query_attention": true,
+  "num_query_groups": 4,
+  "softmax_type": null,
+  "window_size": null,
+  "window_attn_skip_freq": null,
+  "max_position_embeddings": 262144,
+  "position_embedding_type": "rope",
+  "mrope_section": null,
+  "rotary_base": 10000000,
+  "rotary_percent": 1.0,
+  "rotary_interleaved": false,
+  "normalization": "RMSNorm",
+  "norm_epsilon": 1e-06,
+  "swiglu": true,
+  "quick_geglu": false,
+  "activation_func_clamp_value": null,
+  "glu_linear_offset": null,
+  "untie_embeddings_and_output_weights": true,
+  "disable_bias_linear": true,
+  "add_qkv_bias": false,
+  "attention_dropout": 0.0,
+  "hidden_dropout": 0.0,
+  "kv_channels": 128,
+  "qk_layernorm": true,
+  "qk_l2_norm": null,
+  "no_rope_freq": null,
+  "moe_apply_probs_on_input": null,
+  "transformer_impl": "transformer_engine",
+  "num_experts": 128,
+  "moe_layer_freq": 1,
+  "moe_ffn_hidden_size": 768,
+  "moe_shared_expert_intermediate_size": null,
+  "moe_router_topk": 8,
+  "moe_router_num_groups": null,
+  "moe_router_group_topk": null,
+  "moe_router_pre_softmax": false,
+  "moe_router_dtype": "fp32",
+  "moe_router_score_function": "softmax",
+  "moe_router_bias_update_rate": null,
+  "moe_router_enable_expert_bias": false,
+  "moe_router_topk_scaling_factor": null,
+  "moe_router_load_balancing_type": "aux_loss",
+  "expert_model_parallel_size": 4,
+  "expert_tensor_parallel_size": 1,
+  "moe_token_dispatcher_type": null,
+  "moe_enable_deepep": false,
+  "moe_grouped_gemm": true,
+  "moe_permute_fusion": true,
+  "moe_aux_loss_coeff": 0.001,
+  "moe_z_loss_coeff": null,
+  "moe_shared_expert_overlap": true,
+  "moe_layer_recompute": false,
+  "moe_expert_capacity_factor": null,
+  "moe_pad_expert_input_to_capacity": false,
+  "moe_token_drop_policy": null,
+  "multi_latent_attention": false,
+  "q_lora_rank": null,
+  "kv_lora_rank": 32,
+  "qk_head_dim": 128,
+  "qk_pos_emb_head_dim": 64,
+  "mtp_num_layers": null,
+  "mtp_loss_scaling_factor": 0.1,
+  "fp8_format": null,
+  "fp8_recipe": "delayed",
+  "fp8_amax_history_len": 1024,
+  "fp8_amax_compute_algo": "max",
+  "fp8_param_gather": false,
+  "fp16": false,
+  "bf16": true,
+  "apply_query_key_layer_scaling": false,
+  "attention_softmax_in_fp32": true,
+  "log_params_norm": false,
+  "log_throughput": false,
+  "tensorboard_log_interval": 1,
+  "tensorboard_queue_size": 50,
+  "log_timers_to_tensorboard": true,
+  "no_log_learning_rate_to_tensorboard": false,
+  "log_validation_ppl_to_tensorboard": true,
+  "log_memory_to_tensorboard": true,
+  "logging_level": null,
+  "wandb_project": "Qwen-40B-SFT-All_Arabic-English",
+  "wandb_exp_name": "Qwen-40B-SFT-All_Arabic-English",
+  "wandb_save_dir": null,
+  "eval_iters": -1,
+  "eval_interval": 200,
+  "seq_length": 8192,
+  "num_workers": 128,
+  "no_data_sharding": false,
+  "megatron_extra_kwargs": {},
+  "add_version": true,
+  "rank": 0,
+  "global_world_size": 8,
+  "local_world_size": 8,
+  "model_suffix": "checkpoint-24",
+  "model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V7_MMLU/v2-20260125-211853/checkpoint-24', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x7f2807d685e0>, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
+  "model_dir": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V7_MMLU/v2-20260125-211853/checkpoint-24",
+  "_val_dataset_exists": [],
+  "hub": "<class 'swift.hub.hub.MSHub'>",
+  "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'kimi_k2', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'glm4_7', 'deepseek_v3_1', 'ernie_thinking', 'gpt_oss'], is_multimodal=False, bridge_cls=<class 'swift.megatron.model.gpt_bridge.GPTBridge'>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x7f2534c209a0>, visual_cls=None, get_mtp_block_spec=None, extra_args_provider=None)",
+  "extra_args": {
+    "model_dir": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V7_MMLU/v2-20260125-211853/checkpoint-24",
+    "is_multimodal": false,
+    "hf_model_type": "qwen3_nothinking",
+    "use_ray": false,
+    "ray_exp_name": null,
+    "device_groups": null,
+    "model": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V7_MMLU/v2-20260125-211853/checkpoint-24",
+    "model_type": "qwen3_nothinking",
+    "model_revision": null,
+    "task_type": "causal_lm",
+    "torch_dtype": "bfloat16",
+    "attn_impl": null,
+    "new_special_tokens": [],
+    "num_labels": null,
+    "problem_type": null,
+    "rope_scaling": null,
+    "device_map": null,
+    "max_memory": {},
+    "max_model_len": null,
+    "local_repo_path": null,
+    "init_strategy": null,
+    "template": "qwen3_nothinking",
+    "system": null,
+    "max_length": 8192,
+    "truncation_strategy": "delete",
+    "max_pixels": null,
+    "agent_template": null,
+    "norm_bbox": null,
+    "use_chat_template": true,
+    "padding_side": "right",
+    "padding_free": true,
+    "sequence_parallel_size": 1,
+    "template_backend": "swift",
+    "response_prefix": null,
+    "enable_thinking": null,
+    "add_non_thinking_prefix": true,
+    "dataset": [
+      "RL-QA-800K"
+    ],
+    "val_dataset": [],
+    "cached_dataset": [],
+    "cached_val_dataset": [],
+    "split_dataset_ratio": 0.0,
+    "data_seed": 42,
+    "dataset_num_proc": 128,
+    "load_from_cache_file": false,
+    "dataset_shuffle": true,
+    "val_dataset_shuffle": false,
+    "streaming": false,
+    "interleave_prob": null,
+    "stopping_strategy": "first_exhausted",
+    "shuffle_buffer_size": 1000,
+    "download_mode": "reuse_dataset_if_exists",
+    "columns": {},
+    "strict": false,
+    "remove_unused_columns": true,
+    "model_name": [
+      "swift-robot"
+    ],
+    "model_author": [
+      "swift"
+    ],
+    "custom_dataset_info": [
+      "/scratch/hagrass/dataset_info.json"
+    ],
+    "quant_method": null,
+    "quant_bits": null,
+    "hqq_axis": null,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_quant_storage": null,
+    "max_new_tokens": null,
+    "temperature": 0.9,
+    "top_k": 50,
+    "top_p": 0.9,
+    "repetition_penalty": 1.0,
+    "num_beams": 1,
+    "stream": false,
+    "stop_words": [],
+    "logprobs": false,
+    "top_logprobs": null,
+    "structured_outputs_regex": null,
+    "ckpt_dir": "/scratch/hagrass/Experiments/Qwen-40B-SFT-All_Arabic-English/output_V7_MMLU/v2-20260125-211853/checkpoint-24",
+    "lora_modules": [],
+    "tuner_backend": "peft",
+    "train_type": "full",
+    "adapters": [],
+    "external_plugins": [],
+    "model_kwargs": {},
+    "load_args": false,
+    "load_data_args": false,
+    "packing": true,
+    "packing_length": 8192,
+    "packing_num_proc": 1,
+    "lazy_tokenize": false,
+    "custom_register_path": [],
+    "use_hf": false,
+    "hub_token": null,
+    "ddp_timeout": 18000000,
+    "ddp_backend": null,
+    "ignore_args_error": false,
+    "use_swift_lora": false,
+    "freeze_llm": false,
+    "freeze_vit": true,
+    "freeze_aligner": true,
+    "freeze_parameters": [],
+    "freeze_parameters_regex": null,
+    "freeze_parameters_ratio": 0.0,
+    "trainable_parameters": [],
+    "trainable_parameters_regex": null,
+    "adapter_load": null,
+    "target_modules": [
+      "all-linear"
+    ],
+    "target_regex": null,
+    "modules_to_save": [],
+    "lora_rank": 8,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "lora_bias": "none",
+    "lora_dtype": null,
+    "use_rslora": false,
+    "rlhf_type": null,
+    "ref_load": null,
+    "ref_adapter_load": null,
+    "beta": null,
+    "rpo_alpha": null,
+    "reference_free": false,
+    "label_smoothing": 0.0,
+    "f_divergence_type": "reverse_kl",
+    "loss_type": null,
+    "desirable_weight": 1.0,
+    "undesirable_weight": 1.0,
+    "calculate_KL": null,
+    "center_rewards_coefficient": null,
+    "teacher_model": null,
+    "teacher_model_type": null,
+    "teacher_model_revision": null,
+    "lmbda": 0.5,
+    "seq_kd": false,
+    "offload_teacher_model": false,
+    "sft_alpha": 0.0,
+    "generation_batch_size": null,
+    "steps_per_generation": null,
+    "num_generations": 8,
+    "num_generations_eval": null,
+    "max_completion_length": 512,
+    "importance_sampling_level": "token",
+    "tau_pos": 1.0,
+    "tau_neg": 1.05,
+    "epsilon": 0.2,
+    "epsilon_high": null,
+    "delta": null,
+    "use_vllm": true,
+    "vllm_mode": null,
+    "vllm_enable_prefix_caching": true,
+    "vllm_gpu_memory_utilization": 0.9,
+    "vllm_tensor_parallel_size": 1,
+    "vllm_max_model_len": null,
+    "vllm_enforce_eager": false,
+    "vllm_limit_mm_per_prompt": null,
+    "vllm_disable_cascade_attn": false,
+    "vllm_max_num_seqs": null,
+    "vllm_mm_processor_cache_gb": null,
+    "vllm_engine_kwargs": null,
+    "sleep_level": 0,
+    "offload_optimizer": false,
+    "offload_model": false,
+    "offload_bridge": false,
+    "vllm_server_base_url": null,
+    "vllm_server_host": null,
+    "vllm_server_port": [
+      8000
+    ],
+    "vllm_server_timeout": 240.0,
+    "vllm_server_group_port": null,
+    "reward_funcs": [],
+    "reward_weights": null,
+    "cosine_min_len_value_wrong": -0.5,
+    "cosine_max_len_value_wrong": 0.0,
+    "cosine_min_len_value_correct": 1.0,
+    "cosine_max_len_value_correct": 0.5,
+    "cosine_max_len": null,
+    "repetition_n_grams": 3,
+    "repetition_max_penalty": -1.0,
+    "soft_max_length": null,
+    "soft_cache_length": null,
+    "dynamic_sample": false,
+    "max_resample_times": 3,
+    "overlong_filter": false,
+    "scale_rewards": "group",
+    "advantage_estimator": "grpo",
+    "kl_in_reward": false,
+    "wandb_log_unique_prompts": null,
+    "log_completions": false,
+    "rollout_importance_sampling_mode": null,
+    "rollout_importance_sampling_threshold": 2.0,
+    "log_rollout_offpolicy_metrics": false,
+    "off_policy_sequence_mask_delta": null,
+    "log_entropy": false,
+    "top_entropy_quantile": 1.0,
+    "reward_model": null,
+    "reward_model_plugin": null,
+    "sync_ref_model": false,
+    "ref_model_sync_steps": 512,
+    "ref_model_mixup_alpha": 0.6,
+    "async_generate": false,
+    "move_model_batches": null,
+    "multi_turn_scheduler": null,
+    "max_turns": null,
+    "completion_length_limit_scope": "per_round",
+    "vllm_server_pass_dataset": false,
+    "num_iterations": 1,
+    "check_model": true,
+    "padded_vocab_size": 192728,
+    "initialize_embedding": false,
+    "mlp_padding_free": false,
+    "load_safetensors": true,
+    "save_safetensors": true,
+    "ref_model": null,
+    "ref_adapters": [],
+    "merge_lora": true,
+    "max_shard_size": "5GB",
+    "train_dataloader_shuffle": true,
+    "dataloader_pin_memory": true,
+    "dataloader_persistent_workers": true,
+    "dataloader_prefetch_factor": 2,
+    "group_by_length": false,
+    "architectures": "Qwen3MoeForCausalLM",
+    "llm_architectures": "Qwen3MoeForCausalLM",
+    "max_epochs": 1,
+    "enable_dft_loss": false,
+    "enable_channel_loss": false,
+    "save_strategy": "steps",
+    "original_max_position_embeddings": null,
+    "partial_rotary_factor": null,
+    "use_shared_expert_gate": false,
+    "report_to": "wandb",
+    "vit_gradient_checkpointing": true,
+    "vit_lr": null,
+    "aligner_lr": null,
+    "gradient_checkpointing_kwargs": null,
+    "linear_num_value_heads": null,
+    "linear_num_key_heads": null,
+    "linear_key_head_dim": null,
+    "linear_value_head_dim": null,
+    "linear_conv_kernel_dim": null,
+    "layer_types": null,
+    "mrope_interleaved": false,
+    "add_version": true
+  }
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 192728
+}

latest_checkpointed_iteration.txt

@@ -0,0 +1 @@
+115

latest_wandb_artifact_path.txt

@@ -0,0 +1 @@
+abdelrahmanhagrass11-aic/Qwen-40B-SFT-All_Arabic-English

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93102469f8846c5408442aea00338ffeaccb8c599f646099ab0ee46831a2499a
+size 4997543152

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4156a724102e7811acb300e5e4b7ccd554fa91551533e4d56fc33dbf6b59ad82
+size 4997741584

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dd1813d927693587160a60bf303085d3214012231cc5b838b0184bba381dba
+size 4997742120

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ad08ffd8ec3b5202fd30e124890551b5a1c4a4d7224424538cda7f6b6abe72
+size 4997743160

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06384d7f801d58a98fe171e1c4c17f563b4678228215c79ef7ba3f3cfb3f3f7
+size 4997743160

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be6dc0ec5a3f2748598567f4807d28e5b8b242cd3c7eb65ea83ade311f8a6ec
+size 4997743160

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6bc5d15c39208908a451beabf47d88e882c32a1be1e02e27cf60ea54d48cde
+size 4997743160

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf00bc980a0e82bb1d77e0c8cf79a0bf59b8889435a7e62bfaddd5831d7eb2e
+size 4997743168

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441d6efda9997c871d7753f587f9889b7dc1f5e6aea0e158e5ff45b28c2812c7
+size 4997743168

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd562f79d874803c55be19e61b4c3e40899b72c09044cef06e8514c487e83bc
+size 4997743168

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13ed3ef135871644d7cbe2ac35ee5d6e508577685e38ed8dd1e3c743ff5b20b
+size 4997743168

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8409ed8b092a31dc6603641717260ddb19d516e7dbe13d76a56721f67e1a4632
+size 4997743168

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30485630d6f3620bb9599bd8c200c2c96e59944e7771622632347204e94c434d
+size 4997743168

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590e39498553fcfb3a80cd389f65e518fa5dc67078399f24b5f77988adb6b707
+size 4997743168

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6d51a27e6299d6f495b61a95eb715ceddc65412128971806e8fd00df985003
+size 4997743168

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d9daf67f63c3c1844c2110874a311f41ee0db607d4d6decdb87d6b75824d39
+size 4997743160

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c94a6b7e921d22c387b7ee9c635c7ebfda88a5017cde4ff6dac0cc1bf00eda
+size 1377696728

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f644d71501367aaa569353e4787cd25cadb851169b709d8712bff51c72ce76f8
+size 15658511

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}